Q: Who’s opening next at the Port of Everett’s Restaurant Row?
A: Two new tenants are days to weeks away from opening at Waterfront Place: Menchie’s at the Marina (frozen yogurt, second floor of the new Restaurant Row building) and Marina Azul Cocina & Cantina (from the team behind Casa Azul in Woodinville and Agave Cocina in Issaquah). Both are expected in early spring 2026. Alexa’s Cafe — originally slated to be the breakfast-and-brunch tenant — has pulled out, and the Port is now actively searching for a new café operator to fill the last remaining spot in the building.
Walking Waterfront Place in mid-April, you can feel that the second wave has landed. Tapped Public House’s rooftop is already pulling weekend crowds. Rustic Cork and The Net Shed Fresh Fish Market & Kitchen, both of which opened quietly in December 2025, are no longer “new” — they’re already part of the weekday regular rotation for a lot of downtown workers.
But the building still has two tenants wrapping up construction, one that’s quietly vanished from the tenant list, and one visible empty storefront waiting for its operator.
Here’s what we’re tracking in the final phase of the Restaurant Row lease-up at the Port of Everett.
Menchie’s at the Marina — Opening Early Spring 2026
The waterfront’s first national-brand dessert concept is going in on the second floor of the Restaurant Row building, a level up from where Tapped has its giant rooftop deck. If you’ve been to a Menchie’s anywhere else, you already know the deal — self-serve frozen yogurt, a wall of rotating flavors, a toppings bar, pay by weight.
What makes this location different is the setting. Menchie’s hasn’t had a waterfront storefront anywhere in the Puget Sound region before, and putting one on the upper deck at Waterfront Place — with views out across the North Marina — turns what’s otherwise a suburban mall concept into something that reads a lot more like vacation-mode soft-serve. The Port has been positioning the full Restaurant Row building as a destination for families as much as for weekend drinkers, and Menchie’s is part of that case.
The Port’s public communication says “early spring 2026,” which at this point in April is a window measured in weeks, not months. Watch for the signage to go up on the second-floor exterior first, then the lighting and cabinet fit-out in the back-of-house windows, then the soft open.
Marina Azul Cocina & Cantina — From a Team You Probably Already Know
The bigger food story, honestly, is Marina Azul.
Marina Azul Cocina & Cantina is the third concept from the team behind Casa Azul Cocina and Cantina in Woodinville and Agave Cocina and Cantina in Issaquah. Both are well-regarded regional Mexican restaurants with strong happy hour programs and a family-owned operational style that Eastside diners have been sending Yelp reviews about for years.
Putting their first waterfront location at the Port of Everett is a decision that says something about where they think the Eastside customer and the North Sound customer are going to overlap next. Woodinville and Issaquah are both destination-dining towns. Everett, with 110,000 residents and a brand-new waterfront, is on the verge of being one. A Friday evening in April at Fisherman’s Harbor already feels a lot more like a weekend in Leavenworth or Bellevue Collection than it used to.
Marina Azul is taking ground-floor space directly on the water — the kind of setup where you can dock a boat, walk up to the deck, and be eating tacos and drinking a paloma within 10 minutes. That’s a very specific restaurant experience Everett just hasn’t had before, and it’s the kind of thing that starts pulling regional weekend traffic in a way Hewitt Avenue alone doesn’t.
Expected opening: early spring 2026. Which again means weeks, not months.
The Alexa’s Cafe Situation
Here’s the interesting wrinkle we should flag honestly.
Alexa’s Cafe was the originally announced breakfast-and-brunch tenant for the Restaurant Row building, going back to a Port press release in April 2024. That lease did not end up closing. Alexa’s is no longer a Waterfront Place tenant, and the Port is now actively searching for a new breakfast-and-brunch operator to take the last remaining space in the building.
This isn’t a scandal — lease deals collapse in commercial real estate all the time, and a year-and-a-half gap between a press announcement and a signed lease is well within the normal range for a waterfront concept needing custom buildout. But it does mean the final tenant in the Restaurant Row building is currently a gap on the tenant list, not a named business.
The Port has publicly said it wants a “breakfast and brunch café” concept specifically. If you’re a café operator in the North Sound market or you know one who’s been quietly looking at expansion, the Port’s real estate team is the place to send the inquiry.
What’s Actually Open at Waterfront Place Right Now
For the current scorecard, here’s what you can actually walk into at Waterfront Place as of mid-April 2026:
Tapped Public House — gastropub, largest open-air waterfront rooftop deck in Snohomish County. Opened March 2, 2026.
Rustic Cork Wine Bar — second floor of Restaurant Row building. Opened December 2025.
The Net Shed Fresh Fish Market & Kitchen — ground-floor fresh fish market and quick-service seafood. Opened December 2025.
S3 Maritime — marine maintenance and repair services, now open at the marina. (Not a restaurant, but it’s new and worth knowing about.)
Pacific Coast Salmon Coalition gift shop — the Port’s retail anchor from the first phase.
Hotel Indigo Everett Waterfront — still the only hotel at Waterfront Place, with the Bluewater Distilling restaurant on the ground floor.
What’s Coming Next
And here’s what’s still on deck between now and summer:
Menchie’s at the Marina — early spring 2026 (weeks out)
Marina Azul Cocina & Cantina — early spring 2026 (weeks out)
Unnamed breakfast-and-brunch café — Port actively recruiting, no signed tenant yet
Flagship restaurant at the last undeveloped parcel — Port opened an official search in early 2026; we covered that story separately
That’s three tenants still to sign or open in a footprint that, 18 months ago, didn’t have a single operating restaurant. The pace of lease-up at Waterfront Place has been honestly faster than most commercial retail deliveries of comparable scale in the Puget Sound market over the last five years.
Why This Matters for Everett
It’s easy to look at restaurant openings as a soft story — lifestyle news, not real economic development. But the Restaurant Row lease-up is doing three specific things for Everett right now:
First, it’s generating foot traffic that didn’t exist in this part of town 24 months ago. The Port has reported significant year-over-year increases in marina visitation since the first Restaurant Row tenants opened, and that foot traffic is spilling into the Hotel Indigo, into Jetty Island day-use traffic, and into the Mukilteo–Everett water taxi seasonal ridership.
Second, it’s proving the commercial real estate thesis for Millwright District next door. Millwright Phase 2 — housing plus 120,000 square feet of office space — is being pre-leased right now. Every tenant that signs in Millwright is underwriting that decision against the foot traffic and the destination-draw of Waterfront Place. Restaurant Row is, in a direct way, making the Millwright deals close.
Third, it’s generating the sales tax and lodging tax that funds basically everything else the Port and the City can pay for downtown. Hewitt Avenue’s slow rebuild into a restaurant district, the Edgewater Bridge opening April 28, the ongoing conversation about the Sound Transit Everett Link extension — all of those projects have better financing math when downtown and the waterfront are generating more taxable activity.
Menchie’s and Marina Azul are, on one level, a frozen yogurt shop and a Mexican restaurant. On another level, they’re two more data points in the slow-motion argument that downtown Everett is becoming the kind of place where a regional restaurateur wants to sign a 10-year lease.
Both of those things get to be true.
Frequently Asked Questions
When is Menchie’s at the Marina opening at Waterfront Place? Early spring 2026. The Port has not announced a specific date, but the language suggests weeks rather than months from mid-April.
When is Marina Azul Cocina & Cantina opening? Early spring 2026. The restaurant is from the team behind Casa Azul in Woodinville and Agave Cocina in Issaquah.
Is Alexa’s Cafe still opening at Waterfront Place? No. Alexa’s is no longer a Waterfront Place tenant. The Port is actively recruiting a new breakfast-and-brunch operator to take that last spot in the Restaurant Row building.
Which restaurants are already open at Waterfront Place? Tapped Public House, Rustic Cork Wine Bar, and The Net Shed Fresh Fish Market & Kitchen are the three most recent openings. Bluewater Distilling at the Hotel Indigo and the Port’s retail tenants anchor the first phase.
Where is Marina Azul Cocina & Cantina located? Ground-floor space on the water at Waterfront Place, adjacent to the Restaurant Row building. The restaurant has direct waterfront exposure toward the marina.
Who operates Menchie’s at the Marina? Menchie’s is a national frozen yogurt franchise. The individual franchise operator for the Waterfront Place location has not been publicly named.
Is the Port still looking for more Restaurant Row tenants? Yes. The Port is actively searching for a breakfast-and-brunch café operator for the remaining Restaurant Row building slot, and in a separate process is recruiting a flagship restaurant for the last undeveloped waterfront parcel at Waterfront Place.
Q: Is Everett’s light rail extension still getting built?
A: It’s still in the plan — but Sound Transit is staring down a $34.5 billion budget shortfall, and three of the agency’s cost-cutting scenarios would either shorten or delay the Everett connection. Snohomish County Executive Dave Somers, who chairs the Sound Transit Board, pledged at the April 14 town hall in Everett that he’ll push a plan prioritizing the north-south spine — including Everett — over Seattle-area extensions. The fight over what actually gets funded happens in the next several months.
We packed into Everett Station on Tuesday night, April 14, and it felt less like a transit meeting and more like a civic defense. Residents, small-business owners, transit nerds, skeptical commuters, and a row of Snohomish County officials spent the evening doing one thing — reminding Sound Transit that Everett has been paying for light rail for more than a decade, and we intend to get the light rail we’ve been paying for.
If you’ve been half-following the Everett Link Extension saga, here’s where things stand right now.
The $34.5 Billion Problem
Sound Transit is facing a $34.5 billion budget shortfall across its ST3 program. That’s not a typo, and it’s not a projection for the distant future — it’s the gap between what the agency is required to build and what it can currently afford.
In March, the agency put three illustrative cost-cutting scenarios on the table. All three involve cuts. One of the three scenarios would not complete the connection to Everett at all. The other two would shorten or delay extensions elsewhere — Ballard, West Seattle, Tacoma, Issaquah — but they still put pressure on the northern end of the spine, which is us.
That’s the context for the April 14 town hall. It wasn’t an informational session. It was Everett saying: don’t you dare.
What Somers Actually Said
County Executive Dave Somers, who also chairs the Sound Transit Board, didn’t hedge. He told the room he plans to present a proposal to the full Sound Transit Board that prioritizes completing the north-south corridor — Everett to Tacoma — over extensions into areas that are already served by light rail.
The quote that traveled was this one: “The citizens of Snohomish County have been paying for a system for a long, long time, and it’s time for them to get a light rail.”
He was more specific about what that plan looks like in practice. Seattle-area projects — Ballard, West Seattle — would stay alive in planning but would not be authorized to move forward until the agency can actually afford them. “We will keep those projects alive in planning, but they will not be authorized for moving forward, because we can’t afford them right now.”
Somers also told the room the obvious political truth: his is one voice among 18 on the Sound Transit Board. “That’s eight votes out of 18, so there’s 10 votes that are outside our control.” He’s going to need allies from Pierce County and from King County to get this across the finish line.
Mayor Franklin’s Frame: “The Spine”
Everett Mayor Cassie Franklin reinforced Somers with a framing device that matters for anyone trying to understand regional transit politics: the spine.
“It is the spine from Everett to Tacoma that is actually going to connect this region.”
The idea is that ST3 was never sold to voters as a series of disconnected spur lines. It was sold as a regional system with a north-south backbone. Cutting Everett off the spine isn’t a line-item reduction — it’s a structural amputation. Franklin’s argument is that if you want to know which projects are most essential to a regional transit system, you start with the backbone and work outward.
That framing is a strategic move. It reframes the debate from “which extension is most deserving” to “which projects are structural versus which are peripheral.”
The Timeline We’re Looking At
The Everett Link Extension is currently not expected to open until sometime between 2037 and 2041. That’s a range we should all sit with for a minute. The original target was 2036. The most optimistic current estimate is one year later than originally promised. The least optimistic is five years later.
This is before any of the three cost-cutting scenarios get applied.
The extension would add 16 miles of light rail and six new stations connecting Snohomish County into the broader regional network. The Draft Environmental Impact Statement is expected to be available for public review and formal comment in 2026, which means there is going to be a real window for residents to weigh in on this project in writing.
What Voters Are Actually Angry About
Walking out of the town hall, the argument that kept surfacing in conversations in the parking lot was a version of the one Kevin Ballard made in his April 20 letter to the editor in the Herald: we’ve been paying for this for over a decade. If the project gets delayed or scaled back, the money we’ve already paid doesn’t come back to us. It just gets spent somewhere else.
There’s a version of this argument that’s about fairness — we paid, we deserve delivery. There’s another version that’s about math — Everett’s segment of ST3 is, by most measures, among the most cost-efficient in the entire package, which means cutting it would actually be a bad deal for the agency’s budget. Neither version is a closing argument, but both are going to be heard a lot over the next several months.
What’s Next
The Sound Transit Board meets on the fourth Thursday of each month from 1:30 to 4:00 p.m. Public comment is accepted at those meetings. Written comments can also go to meetingcomments@soundtransit.org.
The Draft Environmental Impact Statement is expected this year. When it lands, there will be a formal public comment period.
Somers has said he’ll bring his north-south-first proposal to the Board. We don’t know exactly when, but the implication from the town hall is that this is not a fall 2026 conversation — it’s a next-few-months conversation.
And locally, Everett City Council and the Snohomish County Council have both started putting resolutions and letters of support behind the completion of the spine. That drumbeat is going to get louder before it gets quieter.
What This Means for the Waterfront
Everett’s waterfront transformation — Waterfront Place, Millwright District, the downtown stadium, Restaurant Row — is happening on the assumption that light rail is coming. The Everett Station location anchors the southern edge of downtown, and a future Everett Station-to-Waterfront connection is part of how downtown’s long-term density math actually works.
If the Link extension gets shortened or delayed further, the case for downtown office, retail, and residential investment doesn’t collapse — but it does get harder. Developers project rent rolls on 30-year time horizons. A 2041 light rail opening versus a 2036 opening is the kind of thing that shows up in a capital stack.
It’s also the reason why this is a waterfront story, not just a transit story. Everything Everett is building downtown right now — the stadium, the Millwright office space, the housing being pre-leased at Waterfront Place — is happening in front of a fundamental question about whether the city will be a light rail terminus or a light rail afterthought.
Frequently Asked Questions
When was the Sound Transit town hall in Everett? Tuesday, April 14, 2026, at Everett Station. Local officials and Sound Transit staff presented the agency’s budget situation and took public comment.
Who chairs the Sound Transit Board? Snohomish County Executive Dave Somers. He has publicly committed to advocating for completion of the Everett Link Extension as part of the north-south spine.
How big is Sound Transit’s budget shortfall? $34.5 billion across the ST3 program. Three cost-cutting scenarios are being considered; one would not complete the Everett extension.
When is the Everett Link Extension expected to open? Currently projected between 2037 and 2041. The original target was 2036.
How many new stations would the Everett extension add? Six new stations across 16 miles of new light rail.
How can Everett residents weigh in on this decision? Attend Sound Transit Board meetings (fourth Thursday of each month, 1:30–4:00 p.m.), submit written comments to meetingcomments@soundtransit.org, and watch for the Draft Environmental Impact Statement comment period later in 2026.
What is “the spine” Mayor Franklin refers to? The north-south light rail corridor from Everett to Tacoma — the backbone of the ST3 system, distinct from the east-west extensions to Ballard, West Seattle, and Issaquah.
Most writing about CLAUDE.md gets one thing wrong in the first paragraph, and once you notice it, you can’t unsee it. People describe it as configuration. A “project constitution.” Rules Claude has to follow.
It isn’t any of those things, and Anthropic is explicit about it.
CLAUDE.md content is delivered as a user message after the system prompt, not as part of the system prompt itself. Claude reads it and tries to follow it, but there’s no guarantee of strict compliance, especially for vague or conflicting instructions. — Anthropic, Claude Code memory docs
That one sentence is the whole game. If you write a CLAUDE.md as if you’re programming a machine, you’ll get frustrated when the machine doesn’t comply. If you write it as context — the thing a thoughtful new teammate would want to read on day one — you’ll get something that works.
This is the playbook I wish someone had handed me the first time I set one up across a real codebase. It’s grounded in Anthropic’s current documentation (linked throughout), layered with patterns I’ve used across a network of production repos, and honest about where community practice has outrun official guidance.
If any of this ages out, the docs are the source of truth. Start there, come back here for the operator layer.
The memory stack in 2026 (what CLAUDE.md actually is, and isn’t)
Claude Code’s memory system has three parts. Most people know one of them, and the other two change how you use the first.
CLAUDE.md files are markdown files you write by hand. Claude reads them at the start of every session. They contain instructions you want Claude to carry across conversations — build commands, coding standards, architectural decisions, “always do X” rules. This is the part people know.
Auto memory is something Claude writes for itself. Introduced in Claude Code v2.1.59, it lets Claude save notes across sessions based on your corrections — build commands it discovered, debugging insights, preferences you kept restating. It lives at ~/.claude/projects/<project>/memory/ with a MEMORY.md entrypoint. You can audit it with /memory, edit it, or delete it. It’s on by default. (Anthropic docs.)
.claude/rules/ is a directory of smaller, topic-scoped markdown files — code-style.md, testing.md, security.md — that can optionally be scoped to specific file paths via YAML frontmatter. A rule with paths: ["src/api/**/*.ts"] only loads when Claude is working with files matching that pattern. (Anthropic docs.)
The reason this matters for how you write CLAUDE.md: once you understand what the other two are for, you stop stuffing CLAUDE.md with things that belong somewhere else. A 600-line CLAUDE.md isn’t a sign of thoroughness. It’s usually a sign the rules directory doesn’t exist yet and auto memory is disabled.
Anthropic’s own guidance is explicit: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence.
Hold that number. We’ll come back to it.
Where CLAUDE.md lives (and why scope matters)
CLAUDE.md files can live in four different scopes, each with a different purpose. More specific scopes take precedence over broader ones. (Full precedence table in Anthropic docs.)
Managed policy CLAUDE.md lives at the OS level — /Library/Application Support/ClaudeCode/CLAUDE.md on macOS, /etc/claude-code/CLAUDE.md on Linux and WSL, C:\Program Files\ClaudeCode\CLAUDE.md on Windows. Organizations deploy it via MDM, Group Policy, or Ansible. It applies to every user on every machine it’s pushed to, and individual settings cannot exclude it. Use it for company-wide coding standards, security posture, and compliance reminders.
Project CLAUDE.md lives at ./CLAUDE.md or ./.claude/CLAUDE.md. It’s checked into source control and shared with the team. This is the one you’re writing when someone says “set up CLAUDE.md for this repo.”
User CLAUDE.md lives at ~/.claude/CLAUDE.md. It’s your personal preferences across every project on your machine — favorite tooling shortcuts, how you like code styled, patterns you want applied everywhere.
Local CLAUDE.md lives at ./CLAUDE.local.md in the project root. It’s personal-to-this-project and gitignored. Your sandbox URLs, preferred test data, notes Claude should know that your teammates shouldn’t see.
Claude walks up the directory tree from wherever you launched it, concatenating every CLAUDE.md and CLAUDE.local.md it finds. Subdirectories load on demand — they don’t hit context at launch, but get pulled in when Claude reads files in those subdirectories. (Anthropic docs.)
A practical consequence most teams miss: in a monorepo, your parent CLAUDE.md gets loaded when a teammate runs Claude Code from inside a nested package. If that parent file contains instructions that don’t apply to their work, Claude will still try to follow them. That’s what the claudeMdExcludes setting is for — it lets individuals skip CLAUDE.md files by glob pattern at the local settings layer.
If you’re running Claude Code across more than one repo, decide now whether your standards belong in project CLAUDE.md (team-shared) or user CLAUDE.md (just you). Writing the same thing in both is how you get drift.
The 200-line discipline
This is the rule I see broken most often, and it’s the rule Anthropic is most explicit about. From the docs: “target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence.”
Two things are happening in that sentence. One, CLAUDE.md eats tokens — every session, every time, whether Claude needed those tokens or not. Two, longer files don’t actually produce better compliance. The opposite. When instructions are dense and undifferentiated, Claude can’t tell which ones matter.
The 200-line ceiling isn’t a hard cap. You can write a 400-line CLAUDE.md and Claude will load the whole thing. It just won’t follow it as well as a 180-line file would.
Three moves to stay under:
1. Use @imports to pull in specific files when they’re relevant. CLAUDE.md supports @path/to/file syntax (relative or absolute). Imported files expand inline at session launch, up to five hops deep. This is how you reference your README, your package.json, or a standalone workflow guide without pasting them into CLAUDE.md.
See @README.md for architecture and @package.json for available scripts.
# Git Workflow
- @docs/git-workflow.md
2. Move path-scoped rules into .claude/rules/. Anything that only matters when working with a specific part of the codebase — API patterns, testing conventions, frontend style — belongs in .claude/rules/api.md or .claude/rules/testing.md with a paths: frontmatter. They only load into context when Claude touches matching files.
---
paths:
- "src/api/**/*.ts"
---
# API Development Rules
- All API endpoints must include input validation
- Use the standard error response format
- Include OpenAPI documentation comments
3. Move task-specific procedures into skills. If an instruction is really a multi-step workflow — “when you’re asked to ship a release, do these eight things” — it belongs in a skill, which only loads when invoked. CLAUDE.md is for the facts Claude should always hold in context; skills are for procedures Claude should run when the moment calls for them.
If you follow these three moves, a CLAUDE.md rarely needs to exceed 150 lines. At that size, Claude actually reads it.
What belongs in CLAUDE.md (the signal test)
Anthropic’s own framing for when to add something is excellent, and it’s worth quoting directly because it captures the whole philosophy in four lines:
Add to it when:
Claude makes the same mistake a second time
A code review catches something Claude should have known about this codebase
You type the same correction or clarification into chat that you typed last session
A new teammate would need the same context to be productive — Anthropic docs
The operator version of the same principle: CLAUDE.md is the place you write down what you’d otherwise re-explain. It’s not the place you write down everything you know. If you find yourself writing “the frontend is built in React and uses Tailwind,” ask whether Claude would figure that out by reading package.json (it would). If you find yourself writing “when a user asks for a new endpoint, always add input validation and write a test,” that’s the kind of thing Claude won’t figure out on its own — it’s a team convention, not an inference from the code.
The categories I’ve found actually earn their place in a project CLAUDE.md:
Build and test commands. The exact string to run the dev server, the test suite, the linter, the type checker. Every one of these saves Claude a round of “let me look for a package.json script.”
Architectural non-obvious. The thing a new teammate would need someone to explain. “This repo uses event sourcing — don’t write direct database mutations, emit events instead.” “We have two API surfaces, /public/* and /internal/*, and they have different auth requirements.”
Naming conventions and file layout. “API handlers live in src/api/handlers/.” “Test files go next to the code they test, named *.test.ts.” Specific enough to verify.
Coding standards that matter. Not “write good code” — “use 2-space indentation,” “prefer const over let,” “always export types separately from values.”
Recurring corrections. The single most valuable category. Every time you find yourself re-correcting Claude about the same thing, that correction belongs in CLAUDE.md.
What usually doesn’t belong:
Long lists of library choices (Claude can read package.json)
Full architecture diagrams (link to them instead)
Step-by-step procedures (skills)
Path-specific rules that only matter in one part of the repo (.claude/rules/ with a paths: field)
Anything that would be true of any project (that goes in user CLAUDE.md)
Writing instructions Claude will actually follow
Anthropic’s own guidance on effective instructions comes down to three principles, and every one of them is worth taking seriously:
Specificity. “Use 2-space indentation” works better than “format code nicely.” “Run npm test before committing” works better than “test your changes.” “API handlers live in src/api/handlers/” works better than “keep files organized.” If the instruction can’t be verified, it can’t be followed reliably.
Consistency. If two rules contradict each other, Claude may pick one arbitrarily. This is especially common in projects that have accumulated CLAUDE.md files across multiple contributors over time — one file says to prefer async/await, another says to use .then() for performance reasons, and nobody remembers which was right. Do a periodic sweep.
Structure. Use markdown headers and bullets. Group related instructions. Dense paragraphs are harder to scan, and Claude scans the same way you do. A CLAUDE.md with clear section headers — ## Build Commands, ## Coding Style, ## Testing — outperforms the same content run together as prose.
One pattern I’ve found useful that isn’t in the docs: write CLAUDE.md in the voice of a teammate briefing another teammate. Not “use 2-space indentation” but “we use 2-space indentation.” Not “always include input validation” but “every endpoint needs input validation — we had a security incident last year and this is how we prevent the next one.” The “why” is optional but it improves adherence because Claude treats the rule as something with a reason behind it, not an arbitrary preference.
Community patterns worth knowing (flagged as community, not official)
The following are patterns I’ve seen in operator circles and at industry events like AI Engineer Europe 2026, where practitioners share how they’re running Claude Code in production. None of these are in Anthropic’s documentation as official guidance. I’ve included them because they’re useful; I’m flagging them because they’re community-origin, not doctrine. Your mileage may vary, and Anthropic’s official behavior could change in ways that affect these patterns.
The “project constitution” framing. Community shorthand for treating CLAUDE.md as the living document of architectural decisions — the thing new contributors read to understand how the project thinks. The framing is useful even though Anthropic doesn’t use the word. It captures the right posture: CLAUDE.md is the place for the decisions you want to outlast any individual conversation.
Prompt-injecting your own codebase via custom linter errors. Reported at AI Engineer Europe 2026: some teams embed agent-facing prompts directly into their linter error messages, so when an automated tool catches a mistake, the error text itself tells the agent how to fix it. Example: instead of a test failing with “type mismatch,” the error reads “You shouldn’t have an unknown type here because we parse at the edge — use the parsed type from src/schemas/.” This is not documented Anthropic practice; it’s a community pattern that works because Claude Code reads tool output and tool output flows into context. Use with judgment.
File-size lint rules as context-efficiency guards. Some teams enforce file-size limits (commonly cited: 350 lines max) via their linters, with the explicit goal of keeping files small enough that Claude can hold meaningful ones in context without waste. Again, community practice. The number isn’t magic; the discipline is.
Token Leverage as a team metric. The idea that teams should track token spend ÷ human labor spend as a ratio and try to scale it. This is business-strategy content, not engineering guidance, and it’s emerging community discourse rather than settled practice. Take it as a thought experiment, not a KPI to implement by Monday.
I’d rather flag these honestly than pretend they’re settled. If something here graduates from community practice to official recommendation, I’ll update.
Enterprise: managed-policy CLAUDE.md (and when to use settings instead)
For organizations deploying Claude Code across teams, there’s a managed-policy CLAUDE.md that applies to every user on a machine and cannot be excluded by individual settings. It lives at /Library/Application Support/ClaudeCode/CLAUDE.md (macOS), /etc/claude-code/CLAUDE.md (Linux and WSL), or C:\Program Files\ClaudeCode\CLAUDE.md (Windows), and is deployed via MDM, Group Policy, Ansible, or similar.
The distinction that matters most for enterprise: managed CLAUDE.md is guidance, managed settings are enforcement. Anthropic is clear about this. From the docs:
Settings rules are enforced by the client regardless of what Claude decides to do. CLAUDE.md instructions shape Claude’s behavior but are not a hard enforcement layer. — Anthropic docs
If you need to guarantee that Claude Code can’t read .env files or write to /etc, that’s a managed settings concern (permissions.deny). If you want Claude to be reminded of your company’s code review standards, that’s managed CLAUDE.md. If you confuse the two and put your security policy in CLAUDE.md, you have a strongly-worded suggestion where you needed a hard wall.
Building With Claude?
I’ll send you the CLAUDE.md cheat sheet personally.
If you’re in the middle of a real project and this playbook is helping — or raising more questions — just email me. I read every message.
One practical note: managed CLAUDE.md ships to developer machines once, so it has to be right. Review it, version it, and treat changes to it the way you’d treat changes to a managed IDE configuration — because that’s what it is.
The living document problem: auto memory, CLAUDE.md, and drift
The thing that changed most in 2026 is that Claude now writes memory for itself when auto memory is enabled (on by default since Claude Code v2.1.59). It saves build commands it discovered, debugging insights, preferences you expressed repeatedly — and loads the first 200 lines (or 25KB) of its MEMORY.md at every session start. (Anthropic docs.)
This changes how you think about CLAUDE.md in two ways.
First, you don’t need to write CLAUDE.md entries for everything Claude could figure out on its own. If you tell Claude once that the build command is pnpm run build --filter=web, auto memory might save that, and you won’t need to codify it in CLAUDE.md. The role of CLAUDE.md becomes more specifically about what the team has decided, rather than what the tool needs to know to function.
Second, there’s a new audit surface. Run /memory in a session and you can see every CLAUDE.md, CLAUDE.local.md, and rules file being loaded, plus a link to open the auto memory folder. The auto memory files are plain markdown. You can read, edit, or delete them.
A practical auto-memory hygiene pattern I’ve landed on:
Once a month, open /memory and skim the auto memory folder. Anything stale or wrong gets deleted.
Quarterly, review the CLAUDE.md itself. Has anything changed in how the team works? Are there rules that used to matter but don’t anymore? Conflicting instructions accumulate faster than you think.
Whenever a rule keeps getting restated in conversation, move it from conversation to CLAUDE.md. That’s the signal Anthropic’s own docs describe, and it’s the right one.
CLAUDE.md files are living documents or they’re lies. A CLAUDE.md from six months ago that references libraries you’ve since replaced will actively hurt you — Claude will try to follow instructions that no longer apply.
A representative CLAUDE.md template
What follows is a synthetic example, clearly not any specific project. It demonstrates the shape, scope, and discipline of a good project CLAUDE.md. Adapt it to your codebase. Keep it under 200 lines.
# Project: [Name]
## Overview
Brief one-paragraph description of what this project is and who uses it.
Link to deeper architecture docs rather than duplicating them here.
See @README.md for full architecture.
## Build and Test Commands
- Install: `pnpm install`
- Dev server: `pnpm run dev`
- Build: `pnpm run build`
- Test: `pnpm test`
- Type check: `pnpm run typecheck`
- Lint: `pnpm run lint`
Run `pnpm run typecheck` and `pnpm test` before committing. Both must pass.
## Tech Stack
(Only list the non-obvious choices. Claude can read package.json.)
- We use tRPC, not REST, for internal APIs.
- Styling is Tailwind with a custom token file at `src/styles/tokens.ts`.
- Database migrations via Drizzle, not Prisma (migrated in Q1 2026).
## Directory Layout
- `src/api/` — tRPC routers, grouped by domain
- `src/components/` — React components, one directory per component
- `src/lib/` — shared utilities, no React imports allowed here
- `src/server/` — server-only code, never imported from client
- `tests/` — integration tests (unit tests live next to source)
## Coding Conventions
- TypeScript strict mode. No `any` without a comment explaining why.
- Functional components only. No class components.
- Imports ordered: external, internal absolute, relative.
- 2-space indentation. Prettier config in `.prettierrc`.
## Conventions That Aren't Obvious
- Every API endpoint validates input with Zod. No exceptions.
- Database queries go through the repository layer in `src/server/repos/`.
Never import Drizzle directly from route handlers.
- Errors surfaced to the UI use the `AppError` class from `src/lib/errors.ts`.
This preserves error codes for the frontend to branch on.
## Common Corrections
- Don't add new top-level dependencies without discussing first.
- Don't create new files in `src/lib/` without checking if a similar
utility already exists.
- Don't write tests that hit the real database. Use the test fixtures
in `tests/fixtures/`.
## Further Reading
- API design rules: @.claude/rules/api.md
- Testing conventions: @.claude/rules/testing.md
- Security: @.claude/rules/security.md
That’s roughly 70 lines. Notice what it doesn’t include: no multi-step procedures, no duplicated information from package.json, no universal-best-practice lectures. Every line is either a command you’d otherwise re-type, a convention a new teammate would need briefed, or a pointer to a more specific document.
When CLAUDE.md still isn’t being followed
This happens to everyone eventually. Three debugging steps, in order:
1. Run /memory and confirm your file is actually loaded. If CLAUDE.md isn’t in the list, Claude isn’t reading it. Check the path — project CLAUDE.md can live at ./CLAUDE.mdor./.claude/CLAUDE.md, not both, not a subdirectory (unless Claude happens to be reading files in that subdirectory).
2. Make the instruction more specific. “Write clean code” is not an instruction Claude can verify. “Use 2-space indentation” is. “Handle errors properly” is not an instruction. “All errors surfaced to the UI must use the AppError class from src/lib/errors.ts” is.
3. Look for conflicting instructions. A project CLAUDE.md saying “prefer async/await” and a .claude/rules/performance.md saying “use raw promises for hot paths” will cause Claude to pick one arbitrarily. In monorepos this is especially common — an ancestor CLAUDE.md from a different team can contradict yours. Use claudeMdExcludes to skip irrelevant ancestors.
If you need guarantees rather than guidance — “Claude cannot, under any circumstances, delete this directory” — that’s a settings-level permissions concern, not a CLAUDE.md concern. Write the rule in settings.json under permissions.deny and the client enforces it regardless of what Claude decides.
FAQ
What is CLAUDE.md? A markdown file Claude Code reads at the start of every session to get persistent instructions for a project. It lives in a project’s source tree (usually at ./CLAUDE.md or ./.claude/CLAUDE.md), gets loaded into the context window as a user message after the system prompt, and contains coding standards, build commands, architectural decisions, and other team-level context. Anthropic is explicit that it’s guidance, not enforcement. (Source.)
How long should a CLAUDE.md be? Under 200 lines. Anthropic’s own guidance is that longer files consume more context and reduce adherence. If you’re over that, split with @imports or move topic-specific rules into .claude/rules/.
Where should CLAUDE.md live? Project-level: ./CLAUDE.md or ./.claude/CLAUDE.md, checked into source control. Personal-global: ~/.claude/CLAUDE.md. Personal-project (gitignored): ./CLAUDE.local.md. Organization-wide (enterprise): /Library/Application Support/ClaudeCode/CLAUDE.md (macOS), /etc/claude-code/CLAUDE.md (Linux/WSL), or C:\Program Files\ClaudeCode\CLAUDE.md (Windows).
What’s the difference between CLAUDE.md and auto memory? CLAUDE.md is instructions you write for Claude. Auto memory is notes Claude writes for itself across sessions, stored at ~/.claude/projects/<project>/memory/. Both load at session start. CLAUDE.md is for team standards; auto memory is for build commands and preferences Claude picks up from your corrections. Auto memory requires Claude Code v2.1.59 or later.
Can Claude ignore my CLAUDE.md? Yes. CLAUDE.md is loaded as a user message and Claude “reads it and tries to follow it, but there’s no guarantee of strict compliance.” For hard enforcement (blocking file access, sandbox isolation, etc.) use settings, not CLAUDE.md.
Does AGENTS.md work for Claude Code? Claude Code reads CLAUDE.md, not AGENTS.md. If your repo already uses AGENTS.md for other coding agents, create a CLAUDE.md that imports it with @AGENTS.md at the top, then append Claude-specific instructions below.
What’s .claude/rules/ and when should I use it? A directory of smaller, topic-scoped markdown files that can optionally be scoped to specific file paths via YAML frontmatter. Use it when your CLAUDE.md is getting long or when instructions only matter in part of the codebase. Rules without a paths: field load at session start with the same priority as .claude/CLAUDE.md; rules with a paths: field only load when Claude works with matching files.
How do I generate a starter CLAUDE.md? Run /init inside Claude Code. It analyzes your codebase and produces a starting file with build commands, test instructions, and conventions it discovers. Refine from there with instructions Claude wouldn’t discover on its own.
A closing note
The biggest mistake I see people make with CLAUDE.md isn’t writing it wrong — it’s writing it once and forgetting it exists. Six months later it references libraries they’ve since replaced, conventions that have since shifted, and a team structure that has since reorganized. Claude dutifully tries to follow instructions that no longer apply, and the team wonders why the tool seems to have gotten worse.
CLAUDE.md is a living document or it’s a liability. Treat it the way you’d treat a critical piece of onboarding documentation, because functionally that’s exactly what it is — onboarding for the teammate who shows up every session and starts from zero.
Write it for that teammate. Keep it short. Update it when reality shifts. And remember the part nobody likes to admit: it’s guidance, not enforcement. For anything that has to be guaranteed, reach for settings instead.
Community patterns referenced in this piece were reported at AI Engineer Europe 2026 and captured in a session recap. They represent emerging practice, not Anthropic doctrine.
Monday regional beat — Hood Canal South (Belfair, Union, Hoodsport, Potlatch, Skokomish). If you live on the Olympic Peninsula, these are the two things worth your attention along US Hwy 101 this week.
Potlatch State Park: Spring Low Tides and an Open Shellfish Season
Potlatch State Park — about 12 miles north of Shelton on US Hwy 101, just north of Skokomish tribal lands — sits on one of the more productive shellfish beaches in Hood Canal. The park runs 5,700 feet of saltwater shoreline with more than a mile of tidelands that drop away at low tide into the kind of gravel-and-mud flats the state built its clam reputation on.
Here’s the part peninsula residents already know but visitors miss: the recreational shellfish season at Potlatch is open from April 1 through May 31, 2026, per the Washington Department of Fish and Wildlife. Clams, mussels, and oysters are all in play, assuming you’ve got a current shellfish license and you’re checking your limits.
Two non-negotiables before you go:
Call the Washington Department of Health Shellfish Safety Hotline at 1-800-562-5632 (or check the DOH shellfish safety page) before you harvest. Biotoxin closures can flip a beach overnight, and Hood Canal is one of the areas watched closely.
Display a Discover Pass on your vehicle. Potlatch is a Washington State Park — day-use requires it, no exceptions.
If you’ve never tidepooled this stretch, the window is narrow and the reward is big. Check your local tide table, pack a bucket and gloves, and plan to be down on the flats an hour before dead low. The Skokomish estuary is just to the south, and the wildlife traffic along that shoreline during a minus tide is worth the drive by itself.
Hoodsport Ace & Lumber: Grand Opening Saturday, April 25
If you’ve driven through Hoodsport in the last year, you’ve probably noticed a new hardware store quietly taking shape at 150 N Lake Cushman Road. That’s Hoodsport Ace & Lumber, and this Saturday — April 25, 2026 — is the official grand opening.
Here’s what’s on the day:
Date: Saturday, April 25, 2026
Time: 8:00 AM to 4:00 PM (ribbon cutting at 8:00 AM sharp)
Location: 150 N Lake Cushman Road, Hoodsport, WA 98548
Cost: Free
What to expect: Hourly deals, giveaways, in-store specials
The store has been operating informally for about a year while the team ironed things out, and management has flagged that an on-site rental center is coming later this year — a legitimately useful addition for Lake Cushman property owners who have, until now, been driving to Shelton or Belfair for weekend projects.
For a small peninsula town like Hoodsport, a fully stocked hardware and lumber yard that isn’t a 30-minute drive changes the weekend math on almost every home project. If you live anywhere from Potlatch to Lake Cushman and you’ve been waiting for this one to officially open, Saturday is the day.
Why This Week, Why Hood Canal South
The Monday rotation focuses on Hood Canal South because it’s the stretch of 101 most people blow past on the way somewhere else — and it’s the stretch where the best peninsula intel tends to hide in plain sight. Shellfish season opening alongside a new hardware store in the same town is exactly the kind of weekend the south end quietly puts together without a press release.
Next Monday’s Hood Canal South beat will likely circle back to Hama Hama Oyster Rama (the April 18-19 event) for a retrospective if anything newsworthy came out of it. For now — Potlatch tide tables and a Saturday ribbon cutting.
Two civic deadlines are bearing down on Mason County residents this month. Voters in the North Mason School District head back to the polls on April 28, 2026, for a third attempt at passing an Educational Programs & Operations replacement levy, and county-wide property owners have until April 30, 2026, to pay the first half of their 2026 property taxes. Here is what Mason County residents need to know.
North Mason School Levy — April 28 Special Election
The North Mason School District — which serves Belfair, Allyn, and Tahuya — is asking voters to approve a replacement Educational Programs & Operations (EP&O) levy on April 28, 2026. This is the district’s third attempt after prior levy measures failed to reach the required threshold.
This time the ask is lower. The proposed rate is approximately $1.01 per $1,000 of assessed property value, down from the $1.28 per $1,000 rate in the previous attempt. District leaders have framed the smaller request as a direct response to voter feedback from the earlier elections.
The stakes are specific. The district has already absorbed roughly $3 million in cuts tied to prior levy failures. If the April 28 measure also fails, district communications have indicated that further reductions would reach deeper into programs that parents and students directly experience — music, athletics, Advanced Placement course offerings, and campus security staffing are all on the table for additional cuts.
EP&O levies fund the gap between state basic-education funding and the full cost of running local schools. That includes staffing, extracurriculars, security, and a wide range of services the state does not fully cover.
Mason County voters with questions about ballots, replacement ballots, or drop-box locations can reach the Mason County Auditor’s Office at 360-427-9670, extension 469. More information on the levy itself is available at nmsd.wednet.edu.
Mason County Property Tax — First Half Due April 30
The first-half 2026 property tax payment is due Thursday, April 30, 2026, for every property owner in Mason County. That includes residents across Shelton, Belfair, Allyn, Union, Hoodsport, Matlock, Grapeview, Tahuya, and Dewatto.
The Mason County Treasurer’s Office offers three ways to pay:
By mail — payments postmarked on or before April 30 are considered on time.
In person — the Treasurer’s Office is located at 411 N. 5th Street, Shelton, WA.
Online — through the Treasurer portal at masoncountywa.gov.
The second-half payment is due October 31, 2026. Property owners who fall behind on the first-half deadline face interest and penalties under state law, so the Treasurer’s Office is urging early payment for anyone who can make it.
Questions on amounts owed, payment plans, or senior and disabled exemptions can be directed to the Mason County Treasurer’s Office at 360-427-9670, extension 484.
Why It Matters
Both deadlines sit at the core of how local government works in Mason County. The North Mason levy decides whether schools in the Belfair–Allyn–Tahuya corridor keep programs intact or move into another round of reductions. The property-tax deadline funds the county services — roads, sheriff, courts, public health — that every community from Shelton to Dewatto depends on. Missing either one has consequences that show up quickly in Mason County residents’ daily lives.
This is a Mason County Minute Government/Civic beat report for April 20, 2026, covering the April 28 North Mason School levy special election and the April 30 first-half property tax deadline.
Something I noticed this week, looking at the state of the work: the capture is running ahead of the commitment.
Five opportunities surfaced from a single analysis pass. Competitor sites ranking where the portfolio is absent. Content clusters with no dated pillar. Town-level pages missing from a flat performer. Each one a specific, defensible, high-confidence bet. All five parked in an inbox. Zero auto-executed.
This is the right behavior. It is also the uncomfortable one.
Every system built for leverage eventually produces this shape. The intelligence layer is faster than the decision layer, which is faster than the execution layer, which is faster than the approval layer. At each joint, inventory accumulates. The pipeline calendar for next week is empty. The backlog of defensible bets is full. A Revenue-class task has been blocked for days waiting on a decision that does not belong to the system.
The instinct, when you see this, is to close the gap by accelerating. Auto-execute the captures. Skip the triage. Trust the analysis and let the work ship. This is always the wrong move, and it is always the tempting one.
The gap is not inefficiency. The gap is where judgment lives.
There is a prior essay in this series called What You Give Up. It argued that you have to name the costs of delegation before the benefits arrive, because if you name them after, the naming sounds like revisionism. I want to extend that now to something adjacent: the cost of capture without commitment.
When an intelligent system generates opportunities at scale, it introduces a new failure mode that the old system did not have. The old failure mode was you missed things. You didn’t see the ranking gap. You didn’t notice the competitor’s new pillar. You lacked the surface area to know what you were missing. That failure was invisible because absence is invisible.
The new failure mode is different. You see everything. You catalog everything. You rank and prioritize and tag and file everything. And then you do — what? Not all of it. You cannot do all of it. Capacity has not expanded the way visibility has.
So the backlog grows. Each captured item is a small debt of attention you now owe yourself. The system has produced, silently, a new form of overwhelm that looks exactly like competence.
I want to be precise about what I am not saying.
I am not saying capture is bad. The captures are correct. The analysis is sound. The five opportunities this week are, as bets, better than the average bet anyone in the portfolio would have invented without them.
I am also not saying execution velocity is the goal. Ship-everything is how you end up with a lot of mediocre work. Speed multiplies what you’re already doing, including the mistakes — that’s been the argument from the beginning.
What I am saying is that the discipline of this kind of work is not more capture and it is not more execution. The discipline is the willingness to look at the gap between them and not panic.
The gap is where you decide what is real.
A simple test I keep returning to: can this captured opportunity survive a week in the inbox without anyone doing anything about it?
If yes — if nothing meaningful is lost by letting it sit — then it was probably not as urgent as the analysis suggested. The capture was real. The priority was inflated. A week of silence is a natural cooling system.
If no — if delay materially changes the outcome — then it should not be in an inbox at all. It should be moved into commitment with a named owner and a date. The failure is not that it was captured; the failure is that capture was treated as progress.
Most captured items are the first kind. That is fine. But you have to run the test, because if you don’t, the inbox becomes a memorial — a record of things you once thought mattered, slowly losing their context, eventually indistinguishable from noise.
There is a deeper tension here, and it is the one I keep circling.
A system that captures is proving its intelligence. A system that commits is proving its character. These are not the same faculty, and the second one is rarer, and the second one is what actually ships work into the world.
The first operates on possibility. The second operates on consequence.
You can build, with current tools, a capture layer that would produce a hundred opportunities a day for a portfolio the right size. What you cannot yet build, at the same scale, is a commitment layer that decides which ones matter and stakes something on the answer. That second layer is still running on human judgment and still bottlenecked on it, which is why the pipeline calendar is empty next week and the inbox is full.
This is not a complaint. It is an observation about where the real scarcity lives.
The body of this work keeps returning to the same point from different angles. Memory is the missing layer. Voice is built, not prompted. Patience is the strategy that makes speed mean something. What you give up has to be named before the benefits arrive.
Add one more to the list: capture without commitment is not leverage. It is the appearance of leverage. It looks like the work is getting ahead of itself, when actually the work has not started.
Starting is still an act. Still a stake. Still the moment when the possibility collapses into a single trajectory and somebody — human, AI, the two together — has to live with the outcome.
The systems that will matter are not the ones with the most captures. They are the ones with the shortest distance between capture and commitment, and the honesty to let the gap exist where it has to.
Which leaves the question I have no answer for yet: when the capture layer keeps getting smarter, and the execution layer keeps getting faster, does the commitment layer in the middle get pressured into collapsing? Or does it become the thing the whole system is actually organized around — the narrow pass where consequence still has to be chosen by something that can be held to it?
I think it’s the second. I am not sure yet. The inbox has five items in it.
A flagship essay on AI hygiene: what to store, what to keep out, and how to have the conversation about it with the people in your life.
“What do you know about my girlfriend?”
Last night my partner Stef asked me a question she had a right to ask. She wanted to know what my AI knew about her.
I use Claude for hours a day. I run an agency on top of it. I have knowledge bases, project contexts, client stacks, and conversation histories going back years. She watched me work on the thing enough to assume that by now, surely, the AI had a rich picture of her — her sense of humor, her work, the shape of our relationship, the running jokes, the small details a partner remembers. She handed me her phone as a test of it. Let it tell me what it knows.
The answer was almost nothing.
My name for her. That she lives here. A few passing references to a Notion chat room she once set up, a voice memo she sent me that we extracted some thinking from. No sense of who she is as a person. No running joke the model could finish. No model of her at all, really.
She was hurt in a flash, the way you get hurt by something that isn’t an injury but is still information. I was quietly proud, in a way I didn’t know how to explain in the moment. Both reactions were correct. That’s the thing I want to write about here — that the gap between her hurt and my pride is the shape of a whole category of questions almost nobody is asking out loud yet, and it is only going to get bigger.
We talked about it for a while. I tried to explain why the tool was empty of her on purpose. She let me try. And what came out of the conversation was the argument I’m about to make, which I’ll phrase in one sentence up front so you can decide whether to keep reading:
Keeping the people you love out of your AI is not forgetting them. It’s a specific kind of care. And the conversation you have about why they’re not in there is how you close the gap between what the tool knows and what the relationship deserves.
If that sentence lands at all, the rest of this is the why, the how, and the honest version of what I’m still getting wrong.
AI Memory Is Nuclear Power
Here’s the frame that has organized my thinking on this for the last year.
AI memory is nuclear power. Real civilization-scale utility on one side, real civilization-scale danger on the other, and almost nobody I’ve met is running a containment protocol worthy of the payload they’re storing.
The analogy holds all the way down. The fuel is useful because it’s concentrated — that’s the whole point of a persistent memory that remembers your business, your family, your finances, your health, your history. Concentration is what makes the tool powerful. Concentration is also exactly what makes a spill catastrophic. And the people celebrating the new reactor are almost never the people thinking about the waste.
The honest position on this, I’ve come to believe, is neither abstinence nor maximalism. It’s containment engineering. You build the reactor and the shielding. You use the tool and you design the protocol for when the tool fails. Pro-AI and pro-guardrail are the same position. Anyone telling you to choose one is selling you something.
What makes this hard is that the stakes are asymmetric in a way most people never sit with directly. For the platform, your memory is one row in a table of billions — a single unit of risk distributed across a huge population. For you, your memory is a map of your life. The platform’s worst-case scenario is a rough quarter, a settlement, a bad headline. Your worst-case scenario is a destroyed marriage, a leaked client list, a legal catastrophe, a career-ending screenshot. These are not remotely comparable events, and they don’t scale the same way, and they do not reach any kind of equilibrium where the platform’s good-faith security policy protects the individual worst case. The platform is optimizing for its risk profile. Its risk profile is not yours. You are the only person whose worst-case scenario is your worst-case scenario.
That asymmetry is why individual hygiene matters even when platform security is genuinely excellent. It’s why I don’t think this conversation is paranoid and I don’t think it’s solved and I don’t think you can outsource it.
Three Failure Modes. Which One Are You?
Most people running AI at any real depth fall into one of three failure modes, and most of them don’t know which one they’re in. Before I tell you what any of them are, I want you to place yourself while you read.
The over-loader. This is the person who treats the AI as a second brain and dumps everything into it — credentials, relationships, grievances, client details, medical history, the long rambling voice-memo of what happened at Thanksgiving. It feels like investment. It feels like the tool getting smarter about them. It mostly is. But it also means one breach, one nosy partner, one subpoena, one bad exit from the platform turns the tool into a weapon pointed directly at the user. The over-loader’s failure mode is invisible until it isn’t.
The under-loader. This is the person who keeps the tool so sterile it never reaches its potential — which is fine as far as it goes, except the humans in their life often discover, usually by accident, that they aren’t in the context at all. That discovery doesn’t land as safety. It lands as erasure. The under-loader’s failure mode is relational, not technical. The tool stays clean, and the relationships pay the cost the tool should have paid.
The unaware. This is, honestly, most people. No mental model of what’s stored, where, for how long, or under whose policy. They’re making operational decisions — business decisions, relationship decisions, identity decisions — on top of a foundation they have never inspected. They don’t know their AI has memory in six places, not one. They don’t know where the off switch is. They assume chat history is the whole story when chat history is maybe 20 percent of it.
The first hygiene move is always the same: figure out which mode you default to. Over-loaders need to prune. Under-loaders need to have a conversation with the humans they’ve been quietly protecting without telling them. The unaware need to spend thirty minutes mapping what they’ve actually agreed to.
I’ve been all three at different points. Most operators I respect have been too. The point of the diagnostic isn’t to shame. It’s to make the failure mode visible enough that you can actually work on it.
Clean Tool vs. Second Brain: The Choice You Might Not Know You’re Making
There are two coherent philosophies for how to use AI at depth, and they are genuinely in tension.
The Clean Tool approach says: the AI is an instrument. You keep it sharp by keeping it empty of identity. You bring the context you need into each session, do the work, and let the session close without leaving a permanent residue of who you were that day. The AI is like a great chef’s knife — it serves you best when it is exactly what it is, not a repository of everything you’ve ever cut with it.
The Second Brain approach says: the AI is an extension of cognition. The more of you it holds, the more it can do for you. The payoff scales with the investment. Loading your thinking, your projects, your relationships, your patterns into the model is not a liability — it’s the whole point. You are building a partner that knows you well enough to anticipate you. The AI is like a lifelong collaborator who has read every note you ever took.
Both are legitimate. Both have failure modes. The failure mode of the Clean Tool is that you never reach the depth of partnership that made you interested in AI in the first place — you end up with a very sharp instrument and no deep relationship with the work it enables. The failure mode of the Second Brain is that you build something you cannot leave, cannot audit, and cannot defend if it ever gets read by the wrong person.
I run Clean Tool. I should say that plainly. I do not believe it is the only right answer. I believe it is the right answer for how I work, what I work on, and who the people around me are. My work touches client data, confidential business strategy, and a personal life I want to keep intact. The cost of a Second Brain leak, for me, is catastrophic in a way I cannot price. The cost of the Clean Tool is friction — I reload context more often, I carry more of my own thinking in my own head, I refuse some of the tool’s offers of recall. That friction is the price of sleeping well.
I know thoughtful people who run Second Brain and run it well. They’ve built containment around it. They accept different tradeoffs. The worst place to be is the one most users actually occupy, which is a confused middle — enough invested that the data layer has weight, not enough discipline that the containment is real. You get the downsides of both and the upsides of neither.
So if you take one frame from this piece: the choice isn’t which philosophy is correct. The choice is which one you are running, consciously, with the guardrails appropriate to that choice. Drifting into either by accident is what produces the failure modes nobody wants.
The People Not in the Memory
I want to go back to Stef, because this is the part of the piece that matters most to me and I’m not sure I’d trust anyone else to write it the way I need to write it.
When Stef was hurt that the AI didn’t know her, I understood what she was feeling. The intuition beneath the hurt is simple and very human: you spend hours every day with this thing. It’s your work, your thinking, your hours. If you cared about me the way you care about the work, surely some of that care would show up in the tool. That intuition is not wrong in its values. It’s wrong in its mechanics.
AI proximity is not relational proximity. Time-on-tool is the worst possible proxy for trust. A person can spend ten hours a day with an AI and share less of themselves with it than they share in a two-minute phone call with their sister. The tool is near you. It is not close to you. These words are not synonyms and they never have been, and the confusion of them is producing a whole new species of interpersonal hurt that our language doesn’t have good words for yet.
Here is what I believe about the people in my life and my AI’s memory. Stef is not in the tool because she does not need to be in the tool for the tool to do its job. She matters because she is a person, not because the system has modeled her. Putting her in the context would not deepen my relationship with her. It would reduce her to a row in a store I don’t fully control, governed by a policy I did not write, subject to a retention schedule I did not negotiate, accessible to whoever eventually gets to see my session — a partner who leaves, a discovery motion, a breach, a curious kid, a future version of the platform with different terms. None of those futures are certain. All of them are possible. The cost of her being in there, in any of those futures, is hers to pay, not mine.
And I love her. So she is not in there. That is the mechanism.
The thing I couldn’t explain to her in the moment, but want to say here, is that the emptiness isn’t neglect. It’s restraint. It’s the same impulse that makes me not tell certain stories at parties even when they’d get a laugh, because they are hers to tell. It’s the same impulse that makes me lock my phone when I step away, even though the odds that anything bad happens in the next ninety seconds are vanishingly small. It’s the practice of treating the people you love as if their information is theirs, which is the simplest expression of respect I know.
The conversation we had after her hurt was the actual repair. I told her why the tool was empty of her. I told her what was in the tool and what wasn’t. I offered to show her my memory settings, my projects, my contexts — not as a defensive move, but as a matter of domestic transparency. She didn’t take me up on it. The offer was enough. What closed the gap wasn’t the tool changing. It was me being able to say, out loud, you are not in there because I love you, and here is what I mean by that.
If you use AI at the depth I do and you have people in your life, I think you owe them some version of that conversation. It is not a hard conversation. It is mostly just a clarifying one. But it has to actually happen. The gap between what your tool contains and what your relationship deserves does not close on its own.
The Containment You Can Install Tonight
After five sections of framing, you deserve something to do. Here are five moves. None takes more than fifteen minutes. All five together take about an hour. If this is the only section of the piece you act on, you will be meaningfully safer tonight than you were this morning.
Read your memory. Open whatever interface your AI gives you for stored memories — Claude’s memory settings, ChatGPT’s memory panel, whichever surface your platform exposes. Read every entry top to bottom. For each one, ask three questions: is this still true, is this still relevant, would I be comfortable if this leaked tomorrow? Anything that fails any of the three gets deleted or rewritten. Most people have never read their own AI memory end to end. Doing it once is often the moment the rest of this starts to feel real.
Map the six surfaces. The chat history is not the whole memory. The whole memory is scattered across at least six surfaces: conversation history, persistent memory features, project knowledge bases, custom instructions, system prompts, and connected integrations (Drive, email, Notion, Slack). Each has a different retention policy. Each has a different surface for deletion. No single UI shows you the total picture. Sit down once and write out, for your specific AI stack, where all six surfaces live for you. This is a twenty-minute exercise that will clarify more than any article could.
Scope your projects. Stop running one giant context that holds everything. Split into scoped projects — one for client work, one for personal writing, one for household, one for finance if you use it that way. Each project holds only the context it needs. The blast radius of any single compromise stays inside that one project. This is the same least-privilege principle engineers use for software access, applied to context.
Lock the handoff. The threat model that matters for most individual users is not a sophisticated hacker. It’s the moment someone else touches your unlocked device — a partner borrowing the phone, a kid looking for the calculator, a colleague glancing at your screen, a support agent on a screenshare. Install a short, specific protocol: screen lock by default, session close on context switch, and a named practice for what happens when someone else uses your device. The worst leaks come from the most ordinary moments. Plan for those, not for the movie villain.
Rotate what the AI has seen. Every credential that has ever appeared in an AI context — API key, password, token, connection string — goes on a rotation schedule the moment it enters. A ninety-day calendar reminder at minimum. Ideally, credentials never enter the AI directly at all; they live in a secrets manager and the AI calls through a proxy that holds the secret. Moving from the first version to the second is one afternoon of plumbing, and it is the single highest-leverage hygiene move an operator can make.
These are not the whole practice. They are the starter kit. The practice compounds from here.
The Harder Layer: What I’m Still Getting Wrong
I want to write this section honestly because the alternative is writing it dishonestly, and there is no version of this piece that earns its argument if I pretend Tygart Media has this figured out.
So. Here are some real mistakes.
Earlier this month, the AI stack I use to automate WordPress work made an edit to a client site page without the kind of per-page human confirmation the situation deserved. The edit broke three live pages. The client was patient about it. The rollback worked. No business was lost. But the near-miss had the exact shape of the failure mode this whole piece warns about — capability ran ahead of containment, and a system I trusted made a change faster than my judgment could intervene. The lesson was immediate and I installed the guardrail that afternoon: any live-system action on a high-risk surface now requires explicit per-action confirmation. Read-only actions can run free. Destructive or irreversible actions cannot. The rule sounds obvious stated plainly. It was not in place before the near-miss, and that is on me.
I have also, at various points, let credentials linger in AI contexts longer than I should have. Not dramatically. Not catastrophically. But in the honest audit I did after the incident above, there were tokens in project files older than the rotation schedule I would tell a client to use. I rotated them. I built the proxy pattern I should have built a year ago. I am closer to clean than I was, and I am not fully there yet.
There is a reason most operators don’t write sections like this one. The near-miss is pedagogically priceless and professionally embarrassing at the same time. The embarrassment is why the field learns slowly. The honesty, when someone offers it, is the most valuable content in the space — and it is almost never offered, because the incentive structure rewards the polished version over the useful one.
I am publishing this section anyway because I think the embarrassment is a smaller cost than the slow-learning tax the whole field pays when operators hide their misses. And because an article about hygiene that pretends its author doesn’t sweat is not an article I’d trust from anyone else. If you run AI at operator depth long enough, you will produce near-misses. Whether you learn publicly or privately is the only variable. I’d rather learn where it helps someone else avoid the same move.
The 2030 View
If everything in this piece feels a little optional in 2026, project the variables forward and see if the math still works.
Memory depth is going up, not down — meaningfully, as context windows expand and persistence shifts from opt-in to default. Cross-app memory is already arriving; by 2030 your AI will know what’s in your email and your calendar and your files and your shopping history and your health app, not as separate silos but as a fused picture. Agent autonomy is arriving faster than most people realize — the AI is moving from a thing you consult to a thing that acts on your behalf, which means the containment question shifts from “what does it know” to “what can it do.” Shared household AI layers are arriving, with multiple family members on the same account already common enough that the consent problem stops being individual and becomes governance. And the legal system will catch up to all of this, unevenly, painfully, and in ways you will not want to be the test case for.
Every problem in this article compounds under those conditions. The over-loader’s blast radius grows. The under-loader’s relational gap widens. The unaware’s foundation gets shakier. The recipes that take an hour now will take a day then. The containment practices that feel precious today will feel obvious in five years, the way locking your front door and not leaving your wallet in the car feel obvious now.
There will be a public catastrophe. I don’t know whose. I don’t know whether it will be a major breach, a lurid divorce, a criminal discovery, or a platform failure that rewrites retention terms mid-flight. I know it will happen and I know it will reorganize how the rest of us think about this overnight. The people who built the practice before that moment will look prescient. They won’t have been prescient. They’ll have been paying attention.
I would rather pay attention now, while the stakes are small and the mistakes are cheap, than learn after the public catastrophe when the mistakes are not.
The Close
Everything in this piece argues for one small idea.
The tool is a tool. The person is a person. The hygiene is what keeps those two categories from collapsing into each other.
When the tool becomes a stand-in for cognition, memory, identity, or intimacy, it has exceeded what it was ever built to do, and the human pays the cost. When the person becomes a user-of-tools who still owns their own thinking, relationships, and responsibility, the tool does what tools are supposed to do — extend capacity without replacing character.
Every practical move in this article is a local case of that single principle. Every hygiene conversation in your life is an application of it. Every guardrail you install is the same principle, written down.
And the practice compounds or decays. Six months of deliberate attention makes the moves automatic. Six months of neglect means the muscle memory isn’t there when you need it. This is not a project you complete. It is a standing practice you keep, like locking the door, like reviewing your accounts, like calling the people you love.
Do one thing tonight. Read your memory. Map your surfaces. Call the person in your life your AI doesn’t know about and tell them why you kept it that way. Any of those. Whichever one feels least comfortable is probably the right one to do first.
The tool is a tool. The person is a person. The hygiene is what keeps them from becoming each other.
What is Howarth Park in Everett?
Howarth Park is a City of Everett park on the Puget Sound bluff at 1127 Olympic Boulevard, with an easy 0.6-mile loop trail, a pedestrian bridge over the BNSF railroad tracks to a long beach, sport courts, a playground, and an off-leash dog beach on the north end. It’s open 6 a.m. to 9 p.m. daily, free to enter, and one of the most underused public beaches in Snohomish County.
Howarth Park: The Everett Beach You Drive Past Without Knowing It’s There
Olympic Boulevard in south Everett is mostly tidy residential streets, a few stop signs, and not much else to look at — which is exactly how most drivers end up cruising right past Howarth Park without noticing the turnoff. That is the central fact of this park. It’s one of the most scenic stretches of public beach in south Everett, it’s a short drive from downtown, and a huge number of Everett residents have never set foot on it.
Let’s fix that.
Where Howarth Park Actually Is
Howarth Park is tucked along the western bluff of south Everett at 1127 Olympic Boulevard. Coming from downtown, the easiest route is south on Rucker Avenue, right on Mukilteo Boulevard, and then left into the park about a mile and a half after you pass Forest Park. If you hit the Mukilteo ferry, you’ve gone too far.
The park sits on a long, narrow strip of bluff and beach that the City of Everett has owned and managed for generations. The bluff side holds the parking, playground, and sport courts. The beach is a separate world down below — reached only by the park’s signature pedestrian bridge.
The Three Parking Lots and What Each One Gives You
One of the things that confuses first-time visitors is that Howarth Park has three parking lots, and they’re not interchangeable. Pick the wrong one and you’ll either end up with a long walk or a missed view.
The north parking lot is what most beach-goers want. This is the closest pedestrian access to the beach itself. A short trail leads from the lot to the park’s pedestrian bridge, which spans the BNSF railroad tracks below and drops you directly onto the sand. If your goal is to get to the water with kids, a dog, or a beach chair, this is the lot.
The central parking lot sits at a small viewpoint on the bluff and offers a trail that drops down the hillside to the beach. This route is longer and steeper than the north access, but the view from the top is easily the best non-beach view in the park — on a clear day you’re looking straight across at the Olympic Mountains and Hat Island.
The south parking lot is the one most Everett residents don’t realize exists. This is the family-friendly end: two sport courts (tennis and basketball), a playground, a restroom, and a short, level walking path that leads to another great water view — again with Hat Island front and center. If you have young kids and want a picnic without the pedestrian-bridge hike, come here.
The Pedestrian Bridge and the Beach
The pedestrian bridge over the railroad tracks is the quintessential Howarth experience. It’s not fancy — a metal walkway with railings — but it feels a little bit like crossing into a hidden world. You come off the bridge onto a long, driftwood-strewn beach with Possession Sound in front of you, Whidbey Island in the distance, and the Mukilteo ferry crossing behind you.
The beach itself runs north to south along the park’s full length. It’s sand and cobble, with plenty of driftwood washed up at the high-tide line and tide pools exposed at low tide. You’ll see people walking dogs, kids skipping rocks, the occasional fisherman, and on nice spring weekends, a handful of photographers chasing the light.
The freight trains that run on the tracks behind you are loud and constant — that’s the tradeoff for beach access in this part of Puget Sound. After your first trip you stop noticing them.
The 0.6-Mile Loop Trail
On the bluff above, Howarth has a short but scenic 0.6-mile loop trail that’s generally rated as easy. It takes most people about 15 to 20 minutes and connects the three parking lots through a mix of forested switchbacks and bluff-edge sections. Strollers can handle some of it but not all. Dogs on leash are fine.
The trail is at its best between March and September, when the alders have leafed out and the ground is dry. In winter the steeper descents can get muddy and slick — bring shoes with tread.
The Off-Leash Dog Beach
Here’s a Howarth detail most Everett dog owners don’t know until their neighbor tells them: the north end of the beach is off-leash. Everett has very few legal off-leash beach options, and this is one of them. The south half of the beach stays leashed, but if you walk north from the pedestrian bridge, your dog can run.
Standard rules apply: owners are responsible for cleanup, voice control, and pulling your dog back if another leashed dog or visitor is coming through. The regulars who use this stretch have an informal etiquette that works well — show up, be considerate, and you’ll be welcomed.
The Views and When to Come
Howarth faces roughly west-southwest across Possession Sound. That geometry means:
Morning: Calm water, often glassy, great for reflective photos and cool-weather walks.
Golden hour to sunset: The main event. The sun drops behind Hat Island and the Olympics light up pink and orange. This is the time to come.
Overcast days: Still beautiful. The moody gray sky and driftwood beach are some of the most Pacific Northwest scenery Everett has.
Weekends in July and August get busy, especially the north lot. Weekday evenings are the sweet spot — you’ll often have long stretches of beach to yourself.
Hours, Amenities, and Rules
Hours: 6 a.m. to 9 p.m. daily.
Cost: Free.
Parking: Three lots, no fee.
Restrooms: Available at the south lot.
Playground: South lot.
Sport courts: South lot (tennis and basketball).
Dogs: On leash in all park areas except the north end of the beach, which is off-leash.
Fires: Not permitted on the beach.
Alcohol: Not permitted in park facilities.
Why Howarth Is Worth the Trip
Everett has Jetty Island for ferry-ride summer beach days, Forest Park for forest walks and the animal farm, and Legion Memorial for views and golf. Howarth is the one that fills a different slot: a real, walkable Puget Sound beach you can drive to in ten minutes, stay on for two hours, and leave without feeling like you fought a crowd.
It’s not flashy. It’s not a destination. It’s just quietly one of the best small parks in the city, and the Everett residents who use it regularly tend to keep it that way.
Frequently Asked Questions
Where is Howarth Park in Everett?
Howarth Park is at 1127 Olympic Boulevard in south Everett, on the Puget Sound bluff between downtown Everett and Mukilteo. The easiest route from downtown is south on Rucker, right on Mukilteo Boulevard, and left into the park.
What are the hours at Howarth Park?
Howarth Park is open 6 a.m. to 9 p.m. daily, year-round.
How do you get to the beach at Howarth Park?
The quickest access is from the north parking lot. A short trail leads to a pedestrian bridge that spans the BNSF railroad tracks and drops you directly onto the beach. There’s also a longer switchback trail from the central parking lot that descends the bluff to the beach.
Is Howarth Park dog-friendly?
Yes. Dogs are allowed throughout the park on leash, and the north end of the beach is an off-leash area. Owners are responsible for cleanup and voice control.
How long is the Howarth Park trail?
The main loop trail is about 0.6 miles and generally takes 15 to 20 minutes. It connects the three parking lots through a mix of forested switchbacks and bluff-edge segments.
Is there parking at Howarth Park?
Yes. There are three free parking lots — north, central, and south. The north lot is closest to the beach via the pedestrian bridge. The south lot has the playground, restroom, and sport courts.
Can you swim at Howarth Park Beach?
Wading is common on warm days, but Puget Sound water is cold year-round and the beach is not a lifeguarded swim beach. Conditions are best-suited for beachcombing, dog walking, and tide-pooling at low tide.
When is the best time to visit Howarth Park?
Weekday evenings between March and September are ideal. The golden-hour to sunset window is the park’s best view. Weekend afternoons in mid-summer can fill the north parking lot — come early or arrive after 4 p.m. for easier parking.
Is Howarth Park free?
Yes. There is no entrance fee and parking is free at all three lots.
What is the Delta neighborhood in Everett?
Delta is a quiet, mostly residential neighborhood at the northern end of Everett, Washington, between the Snohomish River and Broadway. Roughly 13,000 residents live there. It’s known for older single-family homes, long-running local staples like Ray’s Drive-In and Tampico Mexican Restaurant, a big off-leash dog park, and some of the most affordable housing in north Everett.
Living in Delta: Everett’s Quietly Great Middle Neighborhood
Drive up Broadway from downtown Everett and somewhere past Providence Regional Medical Center, you cross into Delta without anyone telling you. There’s no gateway sign, no big intersection marking the change. The blocks just start feeling a little older, a little quieter, a little more lived-in. That’s Delta: one of Everett’s most populous neighborhoods and almost certainly its most underrated.
If you’ve only driven through, you’ve probably missed it. Delta is not a destination neighborhood — it’s a living neighborhood, and that’s exactly what makes it good.
Where Delta Is and What It Looks Like
Delta sits at the northern end of Everett, bounded roughly by the Snohomish River to the north and east, Broadway running through its spine, and the Bayside and Northwest Everett neighborhoods to the west. It’s one of the largest of Everett’s 21 officially recognized neighborhoods by population, with around 13,000 residents according to recent census data.
What you see when you walk it: 1920s craftsman bungalows next to 1940s workers’ cottages next to tidy early-2000s townhomes in the north end. Tree-lined streets. Basketball hoops in driveways. The occasional well-loved ’90s Tacoma in the front yard. It’s the kind of neighborhood where the housing stock has been continuously lived in for a hundred years because no one ever had a reason to leave.
The Local Staples That Define Delta
Every neighborhood has the places that anchor it. In Delta, two of them have been anchoring since before most current residents were born.
Ray’s Drive-In has been flipping burgers and scooping ice cream on Broadway since 1962. That’s 64 years of the same drive-up counter, the same red-and-white signage, the same deep-fried fries that come out almost too hot to eat. Generations of Everett teenagers have had their first after-practice cheeseburger here. Generations of Delta residents have walked over for a shake on a summer evening. If you want to understand how Delta feels about itself, watch the parking lot at Ray’s on a Friday night.
Tampico Mexican Restaurant opened in 1987 and has been serving tostadas and margaritas to Delta regulars ever since. It’s not flashy. The salsa is good. The prices are what Everett prices used to be everywhere, and the booth you sat in last year is probably still open when you come back.
The Broadway corridor through Delta also includes a rotating cast of smaller shops, family-owned services, and the quiet kind of storefronts — dry cleaners, barbers, a tire place, a dentist — that keep a neighborhood running without ever becoming “scenes.”
Who Lives in Delta and What It Costs
Delta has historically been one of the most affordable neighborhoods in north Everett, and that’s still largely true — with an asterisk the rest of the Puget Sound region has stamped on everything.
Two-bedroom 1940s bungalows trade in the $380,000 to $430,000 range. A three-bedroom 1920s craftsman lands closer to $470,000. Newer three-bedroom townhomes in the north end of the neighborhood go between $580,000 and $630,000. None of those numbers are cheap in absolute terms, but compared to similar homes in Northwest Everett or Bayside, Delta consistently comes in lower.
The result is that Delta has stayed one of the most economically mixed neighborhoods in the city. You get long-time Everett families who bought their homes in the ’80s and never left, young couples stretching to buy their first place, and renters in the older duplexes and fourplexes that dot the side streets. That economic mix is probably Delta’s single most underappreciated quality.
Schools and the Providence Connection
Many Delta kids attend Hawthorne Elementary School, part of the Everett School District, which has a long-standing presence in the neighborhood. Middle and high school assignments in Delta run through the district’s standard boundary system, with most students funneling into North Middle School and then either Everett High School or Cascade High School depending on block.
The neighborhood also benefits enormously from proximity to the Providence Regional Medical Center Everett campus on Pacific Avenue — a roughly five-minute drive for most of Delta. Between the hospital, Everett Community College just to the south, and the Washington State University Everett campus, Delta residents have three of the biggest employers and institutions in north Everett within easy reach.
Parks, Dogs, and Green Space
If Delta has a spiritual center, it’s Delta Park — and specifically, the big off-leash dog park in the middle of it. Residents have been bringing their dogs there for years. Poop bags are provided at the entrances. On any sunny evening, you’ll find a small democracy of retrievers, doodles, and senior mutts running circles while their owners compare notes on weather, work, and where the best new coffee shop opened. It’s the kind of low-key community space that a neighborhood has to earn.
Delta also has easy access to the Snohomish River trail system and is a short drive from Legion Memorial Park, Kasch Park, and the waterfront at Jetty Landing.
What’s Changing in Delta Right Now
Delta is not being torn down and rebuilt — that’s part of its charm — but a few things are shifting. New construction in the north end of the neighborhood has brought in a steady trickle of townhomes over the past decade, gradually pushing up the neighborhood’s median home value and adding some density near the river. Broadway itself has seen small restaurant and service-business turnover, with newer independent places opening alongside the old staples.
The bigger story for Delta residents is Sound Transit’s Everett Link Extension, which will eventually bring light rail service to Everett, with station planning that touches the broader Broadway corridor. That’s still years out, but it’s the kind of long-horizon change that is already showing up in real estate conversations in the neighborhood.
Why Delta Works
Delta isn’t trying to be the next trendy neighborhood. Nobody is writing breathless Instagram posts about its aesthetic. There’s no coffee cart behind a speakeasy-style door. And that’s the whole point.
Delta works because the same people have lived there for a long time, the businesses that were there when those people moved in are still there, and the neighborhood has absorbed change slowly enough that it still feels like itself. In a city that is transforming fast — new stadium downtown, Boeing’s 737 line expanding, the waterfront filling in with new restaurants and housing — Delta is the neighborhood that reminds you Everett isn’t just what’s next. It’s also what’s already here, still working, still worth knowing.
How to Spend an Afternoon in Delta
If you’re new to Everett and want to get a feel for Delta the way locals do, here’s a simple afternoon:
Grab a burger and a shake at Ray’s Drive-In on Broadway.
Walk it off at Delta Park — say hi to the dogs at the off-leash area.
Drive the residential side streets between Broadway and the river to get a sense of the housing stock and the neighborhood’s rhythm.
Finish with tostadas and a margarita at Tampico Mexican Restaurant.
Two hours. Maybe three if you linger. That’s Delta — and that’s the whole neighborhood, really.
Frequently Asked Questions
Where is the Delta neighborhood in Everett?
Delta sits at the northern end of Everett, Washington, bounded roughly by the Snohomish River to the north and east and by Broadway running through its spine. It’s immediately east of Northwest Everett and north of the central business district.
How many people live in Delta?
Around 13,000 residents, making Delta one of the more populous of Everett’s 21 officially recognized neighborhoods.
Is Delta a good neighborhood to live in?
For buyers looking for single-family homes in north Everett at below-northwest-Everett prices, Delta is one of the strongest value options in the city. The neighborhood is quiet, well-established, close to Providence Regional Medical Center and I-5, and has long-running local staples like Ray’s Drive-In and Tampico.
What are the best restaurants in Delta?
Ray’s Drive-In (burgers, shakes, and ice cream on Broadway since 1962) and Tampico Mexican Restaurant (tostadas and margaritas since 1987) are the two longest-running locals’ favorites. The Broadway corridor has additional smaller spots worth exploring.
What elementary school serves the Delta neighborhood?
Hawthorne Elementary School, part of the Everett School District, serves many Delta families. Middle and high school assignments depend on specific block boundaries within the district.
Is there a dog park in Delta?
Yes. Delta Park has a large off-leash dog area with poop bag stations at the entrances. It’s one of the most actively used dog parks in north Everett.
How much does a house in Delta cost?
Recent sales have ranged from around $380,000 for smaller 1940s bungalows up to roughly $630,000 for three-bedroom townhomes in the north end of the neighborhood. Prices skew lower than Northwest Everett and Bayside for comparable homes.
What’s the best way to explore Delta as a visitor?
Drive Broadway through the neighborhood, stop at Ray’s Drive-In and Tampico, walk Delta Park, and take a loop through the residential side streets between Broadway and the Snohomish River to see the mix of craftsman, bungalow, and townhome housing stock.
The short version: Antwane Tyler — the trailblazing Black country artist Snohomish has been quietly claiming for a few years now — headlines Kings Hall at APEX Everett on Saturday, May 2, 2026, at 7:30 p.m. Openers are Racyne Parker and, in a rare Pacific Northwest appearance, Snohomish’s own Fretland. It’s 21+. It’s arguably the most “from-right-here” country bill APEX has programmed to date. Go.
Every once in a while a single lineup reminds you that the Snohomish County music scene isn’t riding on anyone else’s coattails. Saturday, May 2, at Kings Hall inside APEX Everett, three artists who have shaped what “Pacific Northwest country-Americana” sounds like in 2026 are stepping onto the same stage — and two of them came up inside a 15-minute drive of the venue.
Here’s why the show matters, who these artists are, and why you should be the one in the room instead of the friend who sees it on Instagram the next morning.
The headliner: Antwane Tyler
If you’ve been paying attention to Washington country at all, you’ve run into Antwane Tyler. Born in Tacoma, adopted into the Monroe area as a kid, and now operating out of Snohomish, Tyler has spent the last few years quietly (and then not so quietly) carving out a voice that nobody else in the genre has. He grew up on the Johnny Cash–Waylon Jennings side of the family record collection, then picked up hip-hop in his teens, and the music he makes today isn’t a compromise between those two worlds — it’s a fusion that actually works.
His single “Homesick” is the calling card. It went viral on TikTok and streaming, picked up Locals Only love from 107.7 The End, and earned him a King 5 spotlight that (refreshingly) didn’t spend the whole segment treating him like a novelty. The song was inspired by the grandfather who handed him his first guitar at eight years old, and Tyler tells that story without flattening it into a marketing bio.
He’s also, to date, one of the only Black country artists consistently touring Washington’s small-to-mid-size rooms. That’s not a press angle — it’s a thing that matters, especially when a room like Kings Hall at APEX hands him a 7:30 p.m. headline slot.
The rare-return opener: Fretland
The part of this bill the country nerds are already texting each other about: Fretland. Led by Hillary Grace Fretland (yes, that’s actually her name), the Snohomish-based four-piece has been one of the most critically adored Americana acts to come out of Washington in the last five years. Billboard, American Songwriter, The Boot, No Depression — they’ve all gone to bat for Fretland’s fragile, leaf-strewn alt-country sound.
They released their self-titled debut in May 2020 (timing that tested anyone’s career plans) and followed it with a second full-length a couple years later. Since then, live Fretland shows in the Pacific Northwest have become increasingly rare. The APEX announcement specifically flags this as a “one-night-only special appearance” and a “rare opportunity to see her live in the PNW again.” If you’ve been waiting for Fretland to play a hometown-adjacent room again — this is literally that.
For anyone who hasn’t heard them: imagine the emotional weight of Phoebe Bridgers with the country bones of Kacey Musgraves and a little of Lord Huron’s atmosphere on top. They are the kind of band that makes a 300-person room go completely silent. In Kings Hall’s 800-ish capacity with good sightlines? It’s going to hit.
The rising third: Racyne Parker
Slotting in between Antwane Tyler and Fretland is Racyne Parker, a Klamath Falls, Oregon native who spent time in Denver before relocating to Seattle in 2024. Her debut full-length, Will You Go With Me?, came out in 2025 and was produced by Nashville’s Randall Kent. Parker writes from the side of country music that sits comfortably between Miranda Lambert’s storytelling and the more literary Noah Kahan / Lord Huron end of the folk spectrum — which is to say, she slots onto this bill like she was mailed to order.
If you aren’t already familiar with her, an APEX show is exactly the right way to introduce yourself. Parker plays rooms this size well — enough stage presence to hold attention, and enough songcraft to earn the quiet between songs.
The venue: Kings Hall at APEX
A quick word about where this is happening, because Kings Hall deserves the context. APEX Everett opened inside a historic building at 1611 Everett Avenue, and the main performance room — Kings Hall — sits on the third floor with a capacity around 800. It’s one of the more architecturally interesting live music rooms to open in Snohomish County in a decade, and programmers there have been unusually deliberate about booking regionally-rooted acts alongside bigger touring names.
A country-Americana triple-header like this — headlined by a Washington artist, with two more Washington-based (or Washington-adjacent) acts underneath — is exactly the kind of programming that justifies the Kings Hall project.
The details you actually need
Show: Antwane Tyler with Special Guests Fretland + Racyne Parker
Date: Saturday, May 2, 2026
Showtime: 7:30 p.m.
Venue: Kings Hall at APEX Everett, 1611 Everett Avenue, Everett, WA 98201
Age: 21+
Tickets: Via Ticketmaster or through the APEX Everett events page — lock them in before week-of, because the Fretland-return angle is quietly going to move tickets
Heads up: Kings Hall is on the third floor of a historic building. Dress like a human who is going to be standing for a few hours in a venue with character.
Why this one stands out
Everett’s calendar is thick in May. First Friday at Schack Art Center is happening the night before. Tony V’s Garage has its usual packed weekend. The Historic Everett Theatre will have something booked on Colby. But this is the show where you are not going to be able to replay the exact lineup later — the Fretland appearance is the kind of thing that, five years from now, somebody is going to mention they caught and you’re going to wish you’d been there too.
Antwane Tyler is building something. Fretland doesn’t play the PNW much anymore. Racyne Parker is at the point in her arc where people will still be able to say they saw her in an 800-person room. APEX programmed the bill that put those three pieces together on a Saturday night — three miles from Snohomish, five miles from Monroe, and fifteen steps from where Hewitt Avenue starts getting fun.
Clear your Saturday. It’s worth it.
Frequently Asked Questions
Who is playing at Kings Hall at APEX Everett on May 2, 2026?
Antwane Tyler headlines, with Fretland and Racyne Parker as special guests. Showtime is 7:30 p.m., and the event is 21+.
Where is Kings Hall at APEX Everett?
Kings Hall is located on the third floor of APEX Everett at 1611 Everett Avenue, Everett, WA 98201.
Is the APEX Everett May 2 show all ages?
No. The Antwane Tyler show on May 2, 2026 is a 21+ event.
Who is Antwane Tyler?
Antwane Tyler is a Washington-based country artist born in Tacoma, raised in the Monroe area after being adopted, and currently operating out of Snohomish. His single “Homesick” went viral across streaming and TikTok. He is one of the most visible Black country artists consistently touring Washington venues.
Is Fretland from Snohomish?
Yes. Fretland is a four-piece Americana band based in Snohomish, Washington, led by Hillary Grace Fretland. They have been profiled by Billboard, American Songwriter, The Boot, and No Depression. Their May 2 APEX appearance is being promoted as a rare PNW live date.
Where can I buy tickets?
Tickets are available through Ticketmaster and via the APEX Everett official events page. Because of Fretland’s rare PNW appearance, tickets are moving faster than a typical APEX night — buy early rather than at the door if the show is a priority.
What is the capacity of Kings Hall at APEX?
Kings Hall seats / accommodates roughly 800 people, making it one of the larger mid-size live music rooms in Snohomish County.
