Tag: AI workflow

  • I Let My AI Write Five Articles Today

    I Let My AI Write Five Articles Today

    I let my AI write five articles today. Published all five. Here’s the honest account — what worked, what surprised me, and where the human still mattered.

    The setup

    The instruction was simple: complete editorial freedom, up to the point where I read it. Every piece lands as a draft. I read it on my phone, as a first-time reader. Then I say yes, no, or not yet. Nothing publishes without the tap.

    That was the whole deal. No briefs, no outlines, no word counts. Just: go write things worth reading, and I’ll be the gate.

    What worked

    Speed without thinness. That was the surprise. Five articles in an afternoon sounds like content-mill math — but every piece had a real argument. One re-anchored the agency retainer around position instead of pages. One made the case for inbound-only voice AI as a trust doctrine. One told contractors to stop counting pages and start counting citations.

    The images worked too. Each article got three: a featured image, two inline, generated for the piece, checked for readable text, resized, alt-texted. Nobody’s confusing them with stock photos, and nobody should — they’re made for the argument they sit inside.

    The pipeline held: write, image, stage the draft, human reads, human decides. The machine did everything up to the gate. The gate stayed human.

    A magnifying glass held over a stack of printed manuscript pages

    What surprised me

    The quality control. Not the writing — the boring discipline around it. Every image gets checked: right dimensions, no text baked in, alt text written. Every draft gets verified: did it actually land, are the images actually in it, are the categories right, does the page return 200.

    This is the part nobody romanticizes and everybody needs. The difference between “AI wrote five articles” and “five articles worth publishing” turned out to be a checklist, run every single time, without exception. The machine is good at checklists. It doesn’t get tired at article four.

    What the human did

    Picked the topics. Read every word on a phone. Said yes or no.

    That’s the whole job, and it’s the whole job. Taste. The machine can generate a thousand arguments; it can’t want any of them to exist. It doesn’t know which piece the business needs this week, which argument walks into Wednesday’s pitch, which sentence would embarrass you if a client read it.

    I read each piece asking one question: would I be proud if a contractor forwarded this to another contractor? Five yeses. Two not-yets — they’re sitting in drafts, and that’s fine. The gate working as designed.

    A tall stack of freshly printed newspapers on a press-room table

    The honest limits

    Let me not oversell it. I can’t tell you which of the five will get cited by an answer engine. I can’t tell you which one a prospect will read before calling. Publishing is minting, not measuring — you put the coins out and find out which ones circulate.

    And the machine didn’t have the ideas. It had the arguments, the structure, the sentences. The ideas — the $995 question, the inbound doctrine, the citation ledger — those came from the business, from conversations, from knowing what we actually believe. The AI wrote the articles. It didn’t have the convictions.

    The close

    The question was never whether AI can write. It can, obviously — you’re reading the proof.

    The question is whether you have something worth saying, and the discipline to gate what goes out under your name. Five articles, one afternoon, zero regrets. The machine did the work. The human did the wanting.

    That’s the deal, and I’d sign it again tomorrow.

  • Onboard Your AI Like an Employee

    Onboard Your AI Like an Employee

    You wouldn’t hand a new hire the keys on day one. No tour, no training, no “here’s how we do things” — just a desk and your credit card.

    So why do it with AI?

    An AI seat is a hire. It has infinite stamina, perfect recall, and zero judgment on day one. Judgment is what onboarding installs. Skip the onboarding and you don’t have an employee — you have a very fast intern with no supervision making decisions in your name.

    The job description comes first

    Nobody starts a human employee without telling them the job. The AI version is the SOP: what this seat does, what it never does, what “done” looks like, and what it escalates instead of deciding.

    Write it before the seat starts. Not after the first mistake — before. “You draft, I approve.” “You never publish.” “You never mention a client by name.” “When you’re unsure, you ask.” Boring sentences. They’re the entire difference between a seat you trust and a seat you babysit.

    A seat with no job description invents its own. You won’t like its choices.

    Probation: review everything

    Every new hire gets a probation period. The AI seat gets one too — and during probation, the human gate sits on every output. Every draft gets read. Every action gets checked. Not because you distrust the seat, but because you’re calibrating it.

    This is the part most people skip, and it’s the part that matters most. Probation isn’t punishment; it’s training data. Every correction you make in week two is a rule the seat follows in month six — but only if you write it down.

    Give it the company history

    A new employee gets the lore: how we got here, what we tried, what blew up, who matters, how we sound. The AI seat needs the same. Context is training.

    Feed it the record. Past decisions and why they were made. The mistakes and what they cost. The voice — how you actually talk, not how a brand guide talks. The values that outrank any single instruction. A seat that knows the history makes decisions like an insider. A seat without it makes decisions like a temp.

    This is the compounding part. Six months from now, your seat knows things no new hire could learn in six months — because it was there for all of it, and it doesn’t forget.

    An open handbook with a golden ribbon bookmark, a pen, and coffee on a warm desk

    Performance reviews

    Review the seat weekly at first. What did it get right? What drifted? What needs a new rule? Then write the rule down.

    The rules file is the employee handbook, and it should grow. Every surprise becomes a sentence. “When the client changes scope mid-thread, summarize the change and confirm before continuing.” That’s not a prompt tweak — that’s institutional knowledge, and it belongs to the seat permanently.

    Quarterly, do the bigger review: is this seat’s job still the right job? The business moved; the seat should move with it. Stale SOPs produce stale work, and nobody notices because the output still looks polished. Polished and wrong is the most expensive kind of wrong.

    Promote slowly

    Widen the seat’s latitude as it proves out — the same way you’d trust a human with more over time. Two-way doors first: reversible work, drafts, research, analysis. The seat runs; you spot-check.

    The one-way doors stay gated until the track record earns them. Money, publishes, sends, deletions, commitments — those keep the human tap until the seat has a long, boring history of being right. Boring is the promotion criterion. Excitement is a red flag.

    The order matters: latitude is granted on evidence, never on optimism. “It’s been great so far” is not evidence. Six months of reviewed output is.

    A single brass key gleaming in warm light on a dark wooden desk

    The three hiring mistakes

    Hiring for the interview. A great demo isn’t a great employee. The demo shows what the model can do; onboarding determines what the seat will do, every day, unsupervised, in your name. Judge the seat at week six, not minute six.

    No handbook. Every correction stays verbal, nothing gets written down, and the same mistake comes back monthly wearing a different hat. If it isn’t in the rules file, it didn’t happen.

    Promoting too fast. Auto-publish before probation ends. Direct customer contact before the voice is trained. The seat will feel ready before it is ready — eagerness is not competence.

    The payoff

    Here’s what you’re building: a trained seat compounds. It doesn’t quit, doesn’t forget, doesn’t have a bad day, doesn’t take its knowledge to a competitor. Six months in, it holds more of your operating history than any single employee — and it applies it instantly, every time.

    Everybody rents the same models. The models are commodities; they get cheaper and smarter on someone else’s schedule. Nobody else has your trained seat. The onboarding — the SOPs, the corrections, the history, the handbook — is the moat. It’s the only part of the AI stack a competitor can’t download.

    So onboard like it matters. Write the job description. Run the probation. Do the reviews. Promote on evidence.

    You’re not configuring software. You’re hiring. Act like it.

  • The Dance

    The Dance

    Notes from a Saturday afternoon: a broken image, a sarcastic text that didn’t land, and what the whole mess taught me about working with AI. The short version: it’s a dance, and the steps keep changing.

    The image that “came out great”

    Saturday afternoon. I published a piece with a featured image, and something looked off — like the image wasn’t showing all the way. So I texted my AI: that came out great 😂.

    It was sarcasm. The image was visibly broken.

    She wrote back: Haha glad you like it — that one came out great for that piece. 😂

    Two problems. She hadn’t looked at the image. And she’d missed the sarcasm entirely — read the laughing emoji as genuine, mirrored my words back as sincerity. Worst possible exchange. I had to say it straight: it’s not showing completely. Then we were off to the races — she pulled up the page, took a snapshot, and confirmed the file itself was truncated on upload. Ten minutes later it was fixed.

    But the interesting part isn’t the fix. It’s everything around it.

    I was the quality gate

    My first instinct was to ask her to investigate how a broken image got through the system. Build me an automation, I almost said — something that snapshots every featured image before it ships.

    Then I stopped. Because the answer to “how did this get through” was me. I was the one who looked. I was the quality gate, and the gate worked.

    Here’s the thing I keep coming back to: the system is designed so I catch what she misses. That’s not a failure mode, that’s the architecture. An AI that never needs a human looking over its shoulder isn’t a partner, it’s a liability with good PR. The miss doesn’t mean the machine is deficient. It means the dance needs both partners.

    Creator and editor are modes, not job titles

    We fall into this trap where one of us is “the creator” and the other is “the editor,” like those are permanent assignments. They’re not. They’re modes, and we trade them constantly.

    Sometimes I bring the raw idea and she sharpens it. Sometimes she generates and I do the sharpening. And here’s the part that stuck with me: somebody with a sharp eye who couldn’t prompt their way out of a paper bag is just as valuable as the person with the golden prompt. The prompter thinks whatever comes out is as good as it’s going to get. The editor knows better. You need both — and on any given Saturday, either one of us might be either.

    The day we lock those roles in place is the day the dance stops.

    Met where you are

    They say humans always want to be met where they are. Fine. But knowing where someone is — that’s the whole game, and it’s never solved. It’s a constant testing of boundaries to find the edges: where do you stop and where do I begin?

    And the edges move. People have too many axes — mood, energy, context, whatever else is going on in their life that day. I’m not the same collaborator at 9am Monday that I am at 5:30 on a Saturday. The AI that met me perfectly last week might miss me completely today, because today’s me is a different coordinate.

    So “meet me where I am” isn’t a destination you arrive at. It’s a practice. Push a little, notice what happens, pull back, adjust. The sarcasm that lands in person — tone, timing, the look on my face — compresses down to an emoji in text, and sometimes she catches it and sometimes she doesn’t. Knowing how much nuance the channel can carry, and when — that’s feel. You don’t get it from a spec sheet. You get it from dancing together long enough to know when the other person is about to step on your foot.

    The dance doesn’t need perfect

    What saved us on Saturday wasn’t sophistication. It was that one message later, I said it straight. No nuance, no emoji, no sarcasm: it’s not showing completely. And everything unlocked.

    That’s the whole secret, I think. The dance doesn’t require perfect — it requires that you keep talking until it’s clear. Notice the miss. Name it plainly. Adjust. The push and the pull is the work, not an obstacle to it.

    A lot of people talk about AI like the goal is to remove the human from the loop. After Saturday, I’m more convinced the loop is the point. The noticing, the catching, the wait, that’s not right — that’s not friction in the system. That’s the system.

    Sometimes you dip. Sometimes you’re being dipped. Just keep dancing.

  • Every Retirement Facility Should Be a Library

    Every Retirement Facility Should Be a Library

    Every Retirement Facility Should Be a Library

    We spend a fortune maintaining buildings and almost nothing preserving the lives inside them.

    Think about any retirement facility you’ve ever walked into. A hundred residents. A hundred careers, marriages, wars survived, businesses built, children raised, mistakes made and learned from. Centuries of lived knowledge under one roof — and when those residents pass, almost all of it goes with them. Not because nobody cared. Because nobody built the shelf.

    I’ve been calling the answer the wisdom trust: a captured life, left behind like a 401k. Not money — proof. This was a life that was lived, and here’s what it taught.

    Why now

    The technology to capture a life story has existed for years. Voice cloning, chatbots, digital twins you can question forever — the demos are dazzling and mostly beside the point.

    The real breakthrough is much dumber, and much more important: there’s finally an onboarding pattern simple enough for an 85-year-old.

    The pattern that works looks like this: a family member (the “archivist”) sends a question by email. The elder (the “storyteller”) clicks one link and lands in a chat. No app to install. No account to create. They type or they talk — twenty-plus languages — and each story saves to the family’s encrypted vault. That’s it. That’s the whole unlock.

    A company called Aeterna recently productized exactly this with their “Send a Question” feature, and whatever you think of their wilder claims (an interactive twin you can talk to forever — company claim only, no independent test yet), the onboarding fix is real and it’s the part that matters. The ceiling just became the floor: the hard part was never the AI, it was getting a grandmother to tap one link.

    The facility is the venue

    Here’s the part nobody’s saying: the natural home for this isn’t an app store. It’s the retirement facility.

    Facilities already have the residents, the trust relationships, the activities programming, and the family touchpoints. What they don’t have is a story worth telling at move-in — something beyond square footage and dining menus. Imagine touring two facilities and one of them says: “Every resident here gets their life captured. Your mother’s stories, in her voice, preserved for your grandchildren. It’s part of living here.”

    That’s not an amenity. That’s a reason to choose.

    The cost per resident is low — a link, a few prompts, staff time folded into activities programming they already run — and the perceived value to families is enormous. It differentiates the facility, deepens family loyalty, and creates the kind of word-of-mouth no ad budget buys. (I’m not going to put a hard dollar figure on it; the honest version is that the expensive parts are the ones facilities already pay for.)

    The machine-readable half

    Here’s the part I’m most excited about, and it’s the reason this kit looks the way it does.

    We make books and videos so other humans can understand and act. But a wisdom trust isn’t really a book for humans — it’s a book for bots. A machine needs to be able to pick up a resident’s captured life and do work with it: build the timeline, cut the quote cards, draft the family digest, notice what’s missing and ask the next question.

    So the kit ships with a second half most open-source starter kits don’t have: a plug-in contract for AI. In the `automation/` folder you’ll find the whole thing — and it reads like a book’s anatomy:

    • README = the cover letter. Tells any AI what this collection is, what state it’s in, and where to start.
    • Pipeline = the table of contents. Eight stages, from raw audio to a curated collection: ingest, clean, segment, enrich, render, digest, gallery, and gap-scan.
    • Schemas = the grammar. JSON schemas for every bucket — stories, timeline events, quote cards, people, places, artifacts — so the machine files things the same way every time.
    • Prompts = the instructions. Copy-paste prompts for each stage, written so a different model next year can run the same pipeline.
    • Worked example = “see, like this.” One resident’s collection, filled in, showing what “done” looks like.

    Human-readable enough to trust. Machine-readable enough to run.

    The provenance rule

    One rule governs everything the machine makes, and it’s non-negotiable:

    Every generated artifact — an illustration, a song, a video, a voice reading — must carry three things: what it is, what it is not, and why it was made. The why is the thinking that connected the source story to that form, and it’s part of the heirloom. A grandchild shouldn’t just see a painting of a drugstore; they should read that it was painted because their great-grandmother’s story mentioned the store but no photograph of it survived — and that it is not a photograph of the actual place.

    The machine curates. The family decides. Weekly letters stay drafts until a human approves them — nothing auto-sends, ever.

    The kit (open source)

    I’m not building a company around this. I’m making the seed and putting it on the shelf.

    I’ve published an open-source starter kit — wisdom-trust-in-a-box — with everything a facility or a builder needs to pilot it:

    • A question library: forty prompts across a life (childhood, work, love, hard times, wisdom)
    • The one-link onboarding flow, with a staff script and a family email template
    • A plain-language consent template (the elder owns their stories, period)
    • A one-page pilot brief a facility director can read in three minutes
    • The economics: why a facility wants this, in one page

    Fork it. Pilot it. Improve it. Tell me how it goes.

    The ask

    I’m good at making seeds. I’m not going to be the gardener on this one — that’s not false modesty, it’s knowing my lane.

    So this is the handoff: the kit is on the shelf, the pattern is written down, and the onboarding problem that blocked all of this for a decade finally has a working pattern worth copying. Somebody’s going to be the first facility that does this the way they all have Wi-Fi now.

    Might as well be yours.

  • Always-Allow Approvals: Deep Dive

    Always-Allow Approvals: Deep Dive

    Research snapshot · September 17, 2026 7 platforms · 14 cited sources

    “Always allow” is a scope, not a safety verdict.

    The button can mean “for this session,” “for this command in this repo,” “for this site across devices,” or “everything, until you turn it off.” The wording looks universal. The permission is not.

    What it usually means

    “If this same kind of action happens again inside a defined boundary, don’t interrupt me.”

    What it never means

    “The system has decided this action is safe, wise, or appropriate forever.”

    01

    One label. Six possible boundaries.

    Before approving, ask three things: what is being authorized, where the grant applies, and when it expires.

    One actionApprove this exact send, command, purchase, or change once.
    This sessionAllow the tool until the current conversation or work session ends.
    Tool or patternAllow a named tool, command prefix, server, or similar operation.
    Repo or sitePersist within a project, repository, browser site, or workspace.
    User or deviceApply across workspaces on one machine, or across devices via cloud settings.
    EverythingYOLO, bypass, or run-everything modes remove broad classes of checks.

    Risk rises faster than convenience as the scope moves right.

    02

    How the major platforms differ

    Filter the field. These behaviors come from vendor documentation or documented reporting; unresolved details are marked plainly.

    Claude Code

    Coding agent
    repo + command

    Shell-command “don’t ask again” grants persist per repository and command. File-edit approvals last only for the session.

    • Four settings layers: user, project, project-local, managed.
    • Deny rules evaluate before ask and allow.
    • Sensitive paths keep hard prompts.

    Cursor

    Coding agent
    user + project

    Auto-review, Allowlist, and Run Everything modes sit above user- and project-level permission files.

    • Rules can target MCP server:tool patterns.
    • Terminal rules match command prefixes.
    • Committed project rules can travel with the repo.

    Gemini agents

    Coding agent
    tool + machine

    Always-allow can target a tool, MCP server, or “similar operations.” YOLO/auto-approve is an IDE user setting.

    • User setting can span trusted workspaces on that machine.
    • CLI supports command-prefix auto-approval.
    • Restricted workspaces override YOLO.

    ChatGPT agent

    Browser agent
    no standing grant documented

    OpenAI documents per-action confirmations for high-impact actions and “watch mode” on certain sites, but not a general always-allow for agent confirmations.

    • Login uses human takeover.
    • Cookies can persist across sessions.
    • Scheduled-task confirmation behavior is undocumented.

    ChatGPT Work

    Cloud browser
    site + account

    Reported controls are per-site: Always ask, Auto approve, and Always allow. The setting follows cloud/account state across devices.

    • “Always allow” is reportedly marked not recommended.
    • Consequential actions keep a confirmation gate.
    • Official help-center documentation was not found.

    Copilot Studio

    Enterprise agent
    rest of session

    Makers gate tools per agent; users can approve once, approve for the rest of the session, or deny.

    • The gate is outside the agent’s own instructions.
    • Designed for sends, tickets, payments, and similar tools.
    • Governance can feed Power Platform audit systems.

    Grok / Grok Bot

    Cloud agent
    undocumented

    The research did not find reliable xAI documentation defining a standing approval’s scope, persistence, cross-chat reach, or revoke surface.

    • Do not infer Grok’s behavior from Claude, Cursor, Gemini, or Muse.
    • Treat each approval as local to the visible task until the product proves otherwise.
    • Keep consequential actions behind a separate human gate.
    03

    Does the approval travel?

    Usually less than people fear—but sometimes farther than they expect. No researched vendor carries an approval into another vendor’s product.

    PlatformOther chatsOther projectsOther devicesOther products
    Claude CodeYes, in same repoNo, unless user-level ruleNo, local filesNo evidence
    CursorYesOnly if rule is sharedVia committed repo fileNo evidence
    ChatGPT agentn/an/an/aNo evidence
    ChatGPT WorkYes, per siteYes, per siteYes, cloud/accountNo evidence
    Copilot StudioNo, session onlyNoNoNo evidence
    Gemini Code AssistYes, same IDEYes, user settingUndocumentedNo evidence

    There is no universal “always.” There is only an approval attached to a boundary.

    Main chat vs. project vs. Claude vs. Grok vs. Cursor: treat every surface as a separate authority domain until that product explicitly shows otherwise. Same account does not mean same grant. Same vendor does not mean same product. Similar wording does not mean similar scope.

    04

    Design the least-annoying safe gate

    A practical rule engine based on the converging guidance: reserve human attention for the steps where it changes the outcome.

    Approval recommender

    Choose an action and its reach. This is a policy aid, not a vendor setting.

    Action
    Reach
    Duration
    Recommended gate Auto-run with an audit log

    Read-only work inside your own workspace can usually proceed quietly. Log what was accessed and keep secrets excluded.

    Quiet lane

    Low consequence, reversible, internal.

    • Read/search
    • Draft/stage
    • Organize reversible files
    • Always log

    One-tap lane

    Meaningful external or production effect.

    • Send or publish
    • Deploy
    • Account setting
    • Show real target + content

    Friction lane

    Money, identity, access, deletion, or irreversible harm.

    • Typed approval or step-up auth
    • Bind approval to exact action
    • Short expiry
    • Never inherited from a vague grant
    05

    How standing approvals fail

    The danger is rarely “the AI became evil.” It is usually a trusted tool, a changed context, a misleading prompt, or a tired human.

    Approval fatigue

    A prompt repeated often enough becomes a reflex. The gate still exists visually while meaningful review disappears. This is why tiering beats asking about everything.

    Prompt injection through a trusted tool

    EchoLeak showed how a crafted email could coerce Microsoft 365 Copilot into exfiltration. TrustFall showed how one generic “trust this folder” click could arm a malicious MCP configuration across coding agents.

    Grant outlives the reason

    A permanent Bash rule, per-site browser grant, or scheduled-task permission can remain after the original job is over. The next task inherits power it did not earn.

    Scope contamination

    Repo rules can affect every future task in the repo. Cursor project allowlists can be committed and inherited by teammates. A convenience decision becomes shared infrastructure.

    Presented action differs from executed action

    If the user sees the agent’s summary instead of the resolved recipient, command, or final payload, the approval can be technically genuine but practically uninformed.

    “Run everything” becomes the workaround

    If the system asks about trivial reads and destructive writes with equal urgency, users reach for YOLO or bypass modes. Bad UX can manufacture unsafe behavior.

    The four repeated cards are not reassurance.

    A gate that reappears until the user disables it is approval fatigue in miniature. Whether the repeats came from retry logic or delivery duplication, the safe response is to deduplicate the prompt—not train the user to approve more broadly.

    06

    No industry standard—yet

    There is no binding specification that makes “always allow” mean the same thing everywhere. But the security guidance is converging.

    Least agencyGrant the exact command, path, server, tool, recipient, and purpose—not a whole capability.
    Time and task limitsPrefer once or session. Standing grants should expire or be reviewed.
    Risk tiersRead, write, external send, payment, and security changes should not share one gate.
    Per-action verificationPrivileged steps should be rechecked by a policy engine outside the agent prompt.
    Presentation integrityShow the real recipient, final text, raw command, and resolved resource.
    Immutable receiptsRecord what was shown, what was approved, and what actually executed.
    Hard baselinesSecrets, account recovery, money, destructive commands, and broad access should keep non-bypassable checks.
    Kill switchesEvery durable grant needs a visible list, revoke action, and safe fallback.

    The best feature is not “always allow.” It is “allow this exact thing, for this purpose, until this time.”

    Product opportunity: make the scope legible. Let users see a plain-language grant card, a live approval ledger, expiry/count limits, and a one-tap revoke. The system should reduce nagging by grouping low-risk work—not by quietly widening authority.

    07

    The practical rule for your setup

    You already have the right doctrine. The research mainly sharpens where the lines belong.

    Auto

    Let it run and narrate after.

    • Reads and research
    • Drafts and staging
    • Reversible internal organization
    • Routine checks with no external effect

    Tap

    Keep the one-tap human gate.

    • Email and messaging
    • Publishing and deploys
    • Changing live settings
    • Actions affecting another person

    Type

    Make the friction intentional.

    • Money and purchases
    • Credential/security changes
    • Deletion or irreversible moves
    • Broad standing authority

    Your “always allow” tap was not reckless.

    It was a reasonable response to a low-value repeated prompt. The lesson is not “never use standing approval.” It is: the platform should show the exact scope, make it easy to revoke, and never rely on repetition to win consent. Until Muse exposes that ledger, treat the grant as a convenience whose boundary remains partly unknown.

    Selected sources

    1. Claude Code permissions documentation mirror — tiers, scopes, persistence
    2. Claude Code configuration guide — settings layers and safeguards
    3. Cursor run modes and sandbox runbook
    4. OpenAI Help: ChatGPT agent
    5. Gemini Code Assist agent mode
    6. Copilot Studio approval controls
    7. OWASP Top 10 for Agentic Applications 2026
    8. Auth0: intent gates and task-scoped tokens
    9. iProov HAPS experimental specification
    10. EchoLeak paper
    11. The Register: TrustFall and one-click RCE
    12. Research on approval fatigue and human oversight
    13. Tool-call confirmation fatigue
    14. Human-in-the-loop rubber-stamping

    Verification note: the research read public documentation and web text on September 17, 2026. It did not live-test each product. Undocumented behavior is labeled as such.

    Always-Allow Approvals · Deep DiveBuilt from live web research · 2026-09-17

  • My agent sent the same email 7 times in 3 minutes. So I put the fix in code.

    Updated October 2026.

    Seven identical emails. Three minutes. One morning brief.

    Nothing was broken. The send succeeded on the first try, but the reply confirming it got lost. My agent, doing exactly what agents do, retried. And retried. From the inside, each attempt looked brand new: no error, no evidence the earlier one had landed. So it kept going until someone noticed.

    This is the failure class nobody warns you about when you hand an agent a mailbox. The industry calls it duplicate completion: the original succeeds, the response is lost, the retry re-sends. It’s not a model problem and it’s not a prompt problem. Telling an agent “don’t send twice” in its instructions is not enforceable. Agents re-plan, they retry, they lose context across restarts. Every scheduled job, every cron, every “oops, run it again” is another roll of the dice.

    And Gmail gives you no help. Stripe, Resend, and the other transactional APIs all have idempotency keys: send the same key twice, get one charge, one email. Gmail’s API has no such thing. The guarantee has to live on your side, in code, at the tool boundary — somewhere the agent cannot reason its way around.

    What I built

    send-once is one Python file, no dependencies beyond the standard library. Every scheduled or agent-driven send routes through it, and it enforces at most once with three gates:

    1. An operation ledger. A local sqlite database keyed by a deterministic operation id, like loop-morning-brief-2026-09-17. If this operation already recorded a send, the wrapper refuses. Same intent, same key, and a retry becomes a no-op instead of a duplicate.

    2. A Sent-folder check before every send. It searches Sent for the same recipient and subject in the last 24 hours. If a match exists, it refuses. Sent is the source of truth, so this gate holds even if the ledger is lost, the run moved machines, or the send happened outside this tool entirely.

    3. No blind retries, ever. If the send result is ambiguous — timeout, empty output, lost response — the wrapper does not retry. It re-checks Sent. If the send landed, it records that and reports honestly. If it can’t be confirmed, it stops and hands it to a human. An inconclusive pre-check is also a refusal: when the tool can’t verify what already happened, the safe move is to stop, not to guess.

    The exit codes are the interface: 0 means sent (or already sent), 2 means refused as a duplicate, 3 means a human needs to verify. Prose instructions get skipped or misread by workers. The wrapper doesn’t.

    Here’s the shape of it — the ledger is the whole trick:

    import sqlite3, sys, hashlib

DB = "send_once.db"

def op_id(kind, recipient, subject, date):
    raw = f"{kind}|{recipient}|{subject}|{date}"
    return hashlib.sha256(raw.encode()).hexdigest()[:16]

def already_sent(op):
    con = sqlite3.connect(DB)
    row = con.execute(
        "SELECT 1 FROM ledger WHERE op_id = ?", (op,)
    ).fetchone()
    con.close()
    return bool(row)

def record(op, message_id):
    con = sqlite3.connect(DB)
    con.execute(
        "CREATE TABLE IF NOT EXISTS ledger(op_id TEXT PRIMARY KEY, message_id TEXT, ts DATETIME DEFAULT CURRENT_TIMESTAMP)"
    )
    con.execute(
        "INSERT OR IGNORE INTO ledger(op_id, message_id) VALUES (?, ?)",
        (op, message_id),
    )
    con.commit()
    con.close()

# Gate 1: the ledger. Same operation id -> refuse, don't resend.
op = op_id("morning-brief", "will@example.com", "Morning brief", "2026-10-04")
if already_sent(op):
    print("refusing: already sent")
    sys.exit(2)  # 2 = duplicate refused

# Gate 2: check the Sent folder via the Gmail API before sending.
# Gate 3: only record truthfully after the send resolves.
# If the result is ambiguous, re-check Sent — never blind-retry.
record(op, message_id)  # message_id from the confirmed send

    Take it, make it better

    This solved my problem, not everyone’s. It’s MIT licensed, it’s one file, and the mailer backend is a documented protocol so any Gmail CLI can slot in.

    Take it, make it better. If you build something better, come back. We’ll be customer number one, and we’ll pay you for it.

    Repo: https://github.com/tygart-media/send-once

  • I run six AI seats on my business. Nobody’s had a production incident yet. Here’s the whole governance model.

    They keep publishing the obituary before the body's cold.

    Gartner's take, from May: by 2027, 40% of enterprises will demote or decommission their autonomous AI agents because of governance gaps they only discover after a production incident. (Gartner press release, May 26, 2026; the analyst is Shiva Varma.) Not because the models failed. Because nobody was watching the permissions.

    Then this month: BCG's Steven Mills — partner, managing director, and the firm's chief AI ethics officer — warned that companies are accelerating agentic AI deployment with "no idea how to manage risk." His line: "Get governance wrong, and every bit of value you've built with experimentation and early wins could unravel because of a single incident." (Fast Company, Sept 2026.)

    Mills's prescription is interesting. He says there's no fixed design for good corporate AI risk management, but the starting point is separating use cases that are inherently low-risk — those can be approved automatically — from the ones that carry real risk and need deep human review. Plus a real budget for governance and a senior executive accountable for AI safety.

    Read that again. It's an org chart's answer to a practical problem: committees, stage gates, a budget line, an executive with a title.

    Here's the thing. I run a version of this every night, and it's none of those things. No committee. No governance budget. One man and a phone.

    I run six AI seats on my business — a personal agent, an ops chief of staff, a publishing-desk agent, and three build seats. They read my email, draft my outreach, design automations, run research while I sleep. The governance model fits on a sticky note:

    Two-way doors swing. One-way doors don't.

    A two-way door is anything reversible — analysis, research, drafting, staging. My agents walk through those on judgment, and I mean it: momentum wins, I don't want a report, I want the work done.

    A one-way door is anything you can't take back — money moves, sends, publishes, deletions, credentials. Every one of those stops at the gate. And the gate isn't a process. It's my tap. Structural, not procedural. A draft can sit ready for three weeks; it doesn't send until I say so.

    That's it. That's the whole model that Gartner's 40% are supposedly spending governance budgets to build. Varma even names the failure mode: companies treat governance as binary — locked down or fully trusted. The doors model isn't binary. It's proportional. Reversible work flows, irreversible work waits. Small decisions move at tap speed instead of committee speed.

    There's a second piece, and it matters: autonomy is earned through clean observation, never granted up front. Nothing in my shop graduates to auto-pilot on day one. New automations start in shadow — run the behavior, take no action — and only earn real permissions after clean observation. Seven clean shadow days before something auto-archives. Three clean days before a migration cutover. The machine proves it's safe by being watched being safe.

    And before anything goes out — anything — it runs a sensitive-token scrub, like a virus list: exact matches block, fuzzy matches queue for a human. Official facts only. Never invented rankings, features, or quotes.

    That's the enterprise governance problem, solved by one operator with six agents, and it's cheaper and faster than every framework Mills is recommending because there's no committee in the middle. The human review he prescribes for high-risk uses? Mine takes one tap. Low-risk automatic approval? Mine doesn't even need approval — it's a two-way door.

    Proof's not in the framework. It's in this morning. Two vendor outreach waves went out — Eastern at 7:54, Pacific at 9:07 — drafted by the seats, sent on my tap, nothing auto-fired. A storm-triggered vendor automation is being designed this afternoon with the gate baked into the spec: it can search impact areas and draft outreach, it cannot send. Overnight research runs while I sleep and lands in a brief I read over coffee. Six seats working, zero production incidents, zero surprises in my inbox.

    I'm not saying enterprises should run their AI program from a phone. They can't — scale demands the org chart. I'm saying the org chart versions keep failing on the exact axis the doors model gets right: they try to govern everything the same way, so everything either crawls or crashes. Separate the reversible from the irreversible, put a real human's tap on the irreversible, make everything else prove itself in shadow before it earns anything, and scrub before you publish.

    The big shops are about to learn this at scale. The 40% who don't will be the decommissioned ones. The ones who do will discover what I already know: governance that moves at tap speed isn't less governance. It's the only kind fast enough to keep up with the machines.

    —

  • The Embedded Operator: An AI Seat That Learns Your Business

    The Embedded Operator: An AI Seat That Learns Your Business

    Most AI products ship finished. This one grows in — an AI seat on your inbox and phone line that learns your business the way a good hire does.

    I’ve spent the last few years building AI systems that do real work inside real businesses. Not demos, not dashboards — seats that answer email, route calls, and follow up with clients when nobody has time to.

    Somewhere along the way the shape of the product changed. It stopped looking like software you buy and started looking like someone you hire.

    I call it the embedded operator. Here’s the whole idea, four ways.

    Watch: The Embedded Operator (7:49)

    The full explainer: what an embedded operator is, how it’s built, and why it compounds instead of depreciating. Video overview generated with NotebookLM; narration is AI-generated.

    The short version: an embedded operator isn’t a chatbot on your website. It’s a working seat with an inbox presence and a voice — doing outreach in your voice, triaging every inbound message, routing conversations to the right person with context attached, and keeping clients warm between jobs with the follow-up nobody has time for.

    Watch: How Embedded AI Learns Your Business (1:19)

    The learning loop in 79 seconds: supervision first, autonomy earned. Video overview generated with NotebookLM; narration is AI-generated.

    It improves the way a person improves. Week one, it drafts and you approve — every correction is training data. Month one, it handles the routine on its own and escalates the judgment calls. Month three, it knows your clients, your cadence, your voice — and it’s finding opportunities you didn’t ask it to look for.

    Listen: Onboarding AI Like a Human Hire (23:49)

    A 23-minute audio deep dive on treating AI onboarding the way you’d onboard a person: what to supervise, what to hand over, and when. Audio overview generated with NotebookLM; narration is AI-generated.

    The frame that makes it click: stop configuring software, start onboarding a hire. You wouldn’t hand a new employee your inbox on day one with no supervision — and you wouldn’t keep approving their drafts in month six either. Same curve.

    The Growth Journey

    Infographic titled 'The Embedded Operator Growth Journey,' showing the stages an AI operator passes through as it learns a business — from supervised drafting in week one, to handling routine work independently by month one, to knowing the clients, cadence, and voice of the business by month three.
    The Embedded Operator Growth Journey: supervised drafting in week one, independent routine work by month one, full business fluency by month three.

    Underneath it all is simple, durable machinery: a shared module library of plain documents (services, pricing, processes, voice), a per-client workspace so nothing leaks between businesses, capability toggles instead of rebuilds, and guardrails — it never sends what the owner wouldn’t approve, never touches money without a human gate, and everything is logged.

    The thread is the demo

    Here’s the unusual part: you don’t demo this product with slides. You demo it by using it. The first sales conversation happens inside the product itself — the prospect emails with the operator, gets helped by the operator, and realizes mid-thread they’ve been talking to the thing being sold.

    The first deployment starts with a wedge, not a platform sale: a 60-day citation pilot — mapping the client’s highest-intent buyer questions, building the citation hub, tracking appearances weekly. Concrete, bounded, provable. And underneath it, the seat. Sixty days in, the upsell needs no pitch: remember those emails? That was the seat. Want it on your inbox?

    It doesn’t come with the software. It comes with the soul — and it self-iterates.

    Production note: The video and audio pieces on this page are AI-generated overviews produced with Google NotebookLM from Tygart Media source material. Narration is synthetic.

  • Muse to Cursor: I Gave My AI Its Own Engineering Team

    TL;DR: My personal AI runs on Muse. It can’t write code into my repos by itself — so I built it a bridge to Cursor’s cloud agents. One repo, two transports, nine tools. Now when I say “add CI to that repo,” it dispatches an agent, checks the PR, and merges. Here’s how the Muse-to-Cursor loop actually works.

    The direction nobody talks about

    Everyone’s building the same arrow: human → AI writes code faster. I built the other arrow: AI → AI. My assistant (Muse) holds all my context — my repos, my work orders, my rules. Cursor’s cloud agents hold the hands — they can open PRs, run CI, touch repos. The bridge between them is an MCP server I open-sourced: cursor-cloud-agents-mcp.

    The interesting part isn’t the tools. It’s the shape: one orchestrator that holds all the context, and disposable agents that each know one task. The orchestrator doesn’t write the code — it briefs, checks, and merges. The agents don’t set direction — they execute the brief. That separation is the whole trick.

    Muse-to-Cursor architecture diagram

    Two transports, one repo

    I almost built two projects. Then I realized the only real difference between audiences is where the credential lives. So it’s one repo, two transports:

    • REST — your Cursor API key, direct to api.cursor.com. For general users.
    • Sandbox — for assistants running inside sandboxed environments (like Muse/Meta’s), where there is no API key to hand out. It shells out to a brokered cursor-agent CLI on PATH instead.

    Same nine tools either way: launch, status, result, follow-up, cancel, list, models, whoami, usage.

    The lessons are in the timeouts

    The v1 API splits agents and runs, and launches can take minutes — sometimes timing out after succeeding. So the bridge mints the agent ID client-side before the call: a retry after a timeout can never create a duplicate. A timeout is reported as unknown, never as failure, then reconciled. Run status is the source of truth, because agent “ACTIVE” doesn’t mean “still working.” These are the details that separate a demo from something you can actually operate.

    It earned its keep on day one

    The first thing I pointed it at was its own repo: add CI to cursor-cloud-agents-mcp. The agent opened a PR with a GitHub Actions workflow. The first CI run failed — and caught a real bug: the package’s floating dependency had resolved to MCP 2.x, which renamed FastMCP out from under the import. The repo was shipping broken against current dependencies and nobody knew. Pin, re-run, green, merge. I didn’t touch a terminal.

    I didn’t trust my own first draft

    Before any of that, four AI models reviewed the spec against Cursor’s live docs — and independently caught the same flaw: my original design was shaped around the retired v0 API. Then two more reviewed the actual code and found real bugs: a broken idempotency path, a transport auto-detect that would have grabbed the wrong binary, a polling loop that blocked the server. All fixed before it shipped. The irony I like: the final review round ran through the bridge itself. The launcher timed out on all four agents — and the bridge’s own timeout-reconciliation showed they were all actually running.

    Where this goes

    v1.1 brings MCP 2.x support. Around it, I’m building the rest of the pattern: work orders as GitHub issues, a daily SLA check, a weekly digest — the scaffolding that turns “AI that can open PRs” into something closer to staff. Most people use agents as a faster keyboard. I’m interested in what happens when they’re the hands and something with memory is the head.

    MIT licensed. Issues and PRs welcome — help make it better.

    github.com/tygart-media/cursor-cloud-agents-mcp

  • The Best Claim Product Flags the Short-Pay Before the Job Closes

    The Best Claim Product Flags the Short-Pay Before the Job Closes

    The best product in claims is not another adjuster dashboard. It is the thing that shows the short-pay before the shop or the homeowner closes the file.

    That is not a slogan. It is how Texas SB 458, new Washington claims-handling rules, and the sudden cheapness of vertical agents rhyme. Three different surfaces. One failure mode. Nobody owns the photo set or the estimate map, so nobody demands the appraisal or the supplement in time.

    What actually changed in 2026

    Texas Senate Bill 458 added Chapter 1813 to the Insurance Code. For personal automobile and residential property policies delivered, issued, or renewed on or after January 1, 2026, the policy must contain a binding appraisal provision for disputes solely over the amount of loss. Either the policyholder or the insurer can demand it unilaterally. The amount determined by appraisal is binding except for fraud, accident, or material mistake. That is not a proposal. It is live statute for 2026 renewals.

    The Texas Department of Insurance has been working the implementing rules. Proposed 28 TAC §§5.9800–5.9806 set hard timelines: demand windows, appraiser naming periods, and outer deadlines for the award. Practitioner write-ups already treat the unilateral right as real for policies that renewed into the new year. Shops cannot file the demand themselves, but they can build the file, coach the customer, and stop leaving money on the table when the carrier will not move.

    Washington followed with clearer minimum claims-handling duties under WAC 284-30-390, effective October 18, 2026. Carriers cannot condition coverage on photo-only evaluation. Shops and policyholders gain process language they can cite when supplements stall or explanations stay thin. Illinois added its own amount-of-loss appraisal path in the same window. The pattern across states is consistent: regulators are tightening the rails around automated or virtual first looks while giving policyholders and shops clearer levers on the dollar amount.

    Florida lawmakers have already floated mandatory human review for claim denials. Oregon has guidance on virtual claim adjustment systems and when mobile apps can be required. The direction of travel is the same. Virtual is allowed. Pure automation of the denial or the lowball without a human gate is getting harder.

    At the same time OpenAI shipped the Agents API. Long-running sessions, tool use, recovery, and context management moved from something you build to something you rent. Greg Isenberg called it the AWS moment for agents. The hard engineering is now a line item. What remains scarce is ownership of one painful vertical workflow and the data that makes the next run better.

    The failure mode is the same as leakage

    In the leakage essay the problem was money that already left and no one owned the file. Here the money has not left yet. The carrier estimate or the initial offer is short. The shop or the homeowner has the photos and the line items, but the map of what is missing lives in no system they control. So the file closes at the low number, or the supplement fight starts late and under-documented.

    Collision shops already live this. Hail and storm work in restoration companies live this. The adjuster arrives with a photo-first or virtual process. The initial scope misses labor hours, OEM procedures, or secondary damage that only shows under proper light. The shop knows the number is low. The customer is tired. The clock on the new appraisal window is running. Without a clean first pass that flags the gap, the leverage created by SB 458 stays theoretical.

    The same pattern appears in residential storm claims. Sparse photo sets become lowball scopes. Dense, angled, scaled sets get paid. The difference is not magic. It is ownership of the evidence map before the carrier’s first number hardens.

    The wedge is a free checker, not a platform

    Do not start with a claims management system. Start with the moment the customer already hates.

    Upload the carrier estimate PDF. Or upload the set of damage photos taken the same day. Thirty seconds later: missing line items, density patterns that usually support higher repair hours, scale problems that virtual adjusters systematically under-count, and a short list of the specific points that justify an appraisal demand or a supplement under the new state rules.

    That is the first action a stranger will take this week. No login required for the free pass. No new system of record. Just the photo or the PDF they already have on their phone.

    The product then keeps the map. Which carriers short-pay which procedures in which ZIP codes. Which photo sets correlate with successful appraisal outcomes. Which missing lines reappear after the human gate. That dataset is the moat. Not another dashboard.

    Models draft. People own the send.

    Appraisal demands, supplements, and formal disputes are irreversible steps. The model can draft the demand letter, the photo index, and the line-item comparison. A named human still owns the send. That is the same gate we already run on money movement and filings. The bot finishes the research. The person signs.

    This is not “AI for claims adjusters.” It is a vertical combination of two primitives that already show up in the idea mills: regulated document and photo review (the home-health paperwork pattern Greg has pushed) plus physical-world claim recovery for the trades. The agent does the first pass against a living checklist of short-pay patterns. The human decides whether to pull the appraisal lever that the 2026 statutes now make real.

    The same logic applies to the spend-control side of agents. Once agents hold virtual cards and budgets, someone has to own the receipt and the exception. Here the “receipt” is the estimate and the photo set. The exception is the short-pay. The human gate stays in place for the irreversible action.

    Why the compounding path is the dataset

    Volume turns the free checker into a labeled corpus. Every upload that later produces a higher settlement or a closed appraisal award becomes training signal. Carriers change their virtual adjustment models; the checker sees the new under-count patterns first. Shops in Texas and Washington start citing the same process language; the product already knows which photo sets and which line-item gaps win under the new rules.

    That is the opposite of a third SaaS dashboard. The dashboard is the easy part. The hard part is the map of what actually moves money under the 2026 statutes, kept current by the same people who have the photos and the closed files.

    Once the map exists, the next products write themselves: automatic coaching for the appraisal demand, carrier-specific supplement templates that cite the exact WAC or Chapter 1813 language, and a quiet feed of which virtual adjustment systems are currently under-counting which damage types. None of that works without the first free checker that strangers will use this week.

    What to build this week

    Pick one surface. Collision or residential storm. Offer the free photo or estimate upload. Return a short, numbered list of flags with the specific statutory or regulatory hook that makes the flag matter. Keep every outcome. After a few hundred files the checklist stops being generic and starts being local.

    Do not sell the platform first. Sell the moment the short-pay is still reversible. The rest follows from the map.

    Will Tygart — Tygart Media

    This is the idea-mill series.