Tygart Media

Author: will_tygart

  • Crawl Space Rim Joist Insulation: Why It Matters and How to Do It Right

    The Distillery — Brew № 2 · Crawl Space

    The rim joist — the band of framing that sits on top of the foundation wall and closes the floor joist cavities at the perimeter — is consistently identified by building scientists and energy auditors as the largest single air leakage and heat loss site in most homes with crawl spaces. More heat escapes through an uninsulated, unsealed rim joist than through any other single component of the crawl space building envelope, and more crawl space air enters the home through the rim joist than through any other pathway. Addressing the rim joist is the highest-leverage action in any crawl space improvement project.

    Why the Rim Joist Is the Priority

    The rim joist area is a thermal and air sealing weak point for structural reasons: it is the intersection of multiple framing members (floor joist ends, blocking, the rim joist itself, the sill plate below, and the subfloor above), and these members rarely meet perfectly. Gaps at joist ends, misaligned blocking, gaps between the rim joist and the sill plate, and the inherently porous nature of lumber create a permeable air barrier. Hot-box blower door tests consistently find that the rim joist contributes disproportionately to total building air leakage — often 15–25% of total air infiltration in a home with an uninsulated crawl space rim joist.

    The thermal impact is equally significant. The rim joist is typically the coldest structural wood surface in a vented crawl space in winter — it is exposed on the exterior face to outdoor temperatures, has no insulation between it and the interior, and is the wood member most prone to condensation from warm interior air hitting the cold exterior-connected wood. Condensation on the rim joist is the leading cause of mold growth at the top of crawl space foundation walls.

    Option 1: Spray Foam (Best Performance)

    Professional two-component closed-cell spray polyurethane foam (ccSPF) applied to the rim joist area is the gold standard for rim joist insulation and air sealing. Closed-cell spray foam:

    • Adheres directly to wood, concrete, and masonry surfaces — filling all gaps, cracks, and voids in the rim joist framing assembly
    • Provides both insulation (R-6.5 to R-7 per inch) and complete air sealing simultaneously
    • At 2″ applied thickness: approximately R-13, and essentially complete air sealing across the entire rim joist area
    • Adds structural rigidity to the rim joist assembly — a secondary benefit particularly relevant in older homes where rim joist framing may be degraded
    • Is vapor semi-impermeable at 2″ thickness — in most climate zones, this provides appropriate vapor control at the rim joist without requiring a separate vapor barrier

    Professional closed-cell spray foam requires specialized equipment (a proportioner that heats and mixes the two-component foam at precise ratios), protective equipment (Tyvek suits, respirator with organic vapor cartridges, eye protection), and training to apply uniformly and safely. DIY two-component kits (available from Froth-Pak and similar) can handle small areas but are expensive per board-foot and not practical for a full rim joist treatment in a large crawl space.

    Professional spray foam cost for rim joist: $1.50–$3.00 per square foot of rim joist area, which typically means $600–$1,500 for a full perimeter treatment of a standard single-family home.

    Option 2: Rigid Foam Panels (DIY-Accessible)

    Rigid foam boards (EPS, XPS, or polyisocyanurate) cut to fit between the floor joists and sealed at all four edges with one-component spray foam is the DIY-accessible alternative to professional spray foam. This approach provides:

    • Thermal insulation from the foam board — 1″ XPS provides R-5; 2″ XPS provides R-10; 2″ polyiso provides R-12–13
    • Air sealing from the spray foam seal at the perimeter of each panel — not as complete as professional ccSPF but substantially better than no treatment
    • DIY-accessible — cutting foam board with a utility knife and applying spray foam perimeter seal requires only basic skills and inexpensive tools

    The installation process:

    • Measure each joist bay width (spacing varies in older homes)
    • Cut rigid foam panels to fit snugly in each bay — the panel should be cut 1/4″ smaller than the actual bay dimensions to allow spray foam to seal the perimeter
    • Apply construction adhesive to the back of the panel or use the spray foam itself as the adhesive
    • Press the panel firmly against the rim joist and hold until adhesion is achieved
    • Apply a continuous bead of one-component spray foam (Great Stuff or equivalent) around all four edges of each panel — this is the air sealing step and must be continuous without gaps

    DIY rigid foam + spray foam material cost: $0.50–$1.50 per square foot of rim joist area. For a 1,200 sq ft home with 150 LF of perimeter × 2 joist courses (approximately 250 sq ft of rim joist area): $125–$375 in materials. This is 3–5× less expensive than professional spray foam for equivalent coverage, though the air sealing performance is somewhat lower.

    Climate Zone Considerations

    The appropriate R-value target for rim joist insulation varies by climate zone, similar to wall insulation requirements:

    • Climate Zones 1–2 (Deep South): R-13 at the rim joist. 2″ ccSPF or 2″ rigid foam + spray foam seal meets this requirement.
    • Climate Zones 3–4 (Mid-Atlantic, Southeast transition, Pacific Coast): R-13–19. 2″ ccSPF provides R-13; adding rigid foam behind the spray foam or increasing thickness to 3″ achieves R-19.
    • Climate Zones 5–6 (Midwest, Northeast, Pacific Northwest): R-19–20. 3″ ccSPF provides approximately R-19–21; 2″ ccSPF + 2″ rigid foam achieves similar performance.
    • Climate Zones 7–8 (Northern climates): R-20+. Higher-thickness spray foam or layered spray foam + rigid foam is needed.

    Frequently Asked Questions

    Should I use spray foam or rigid foam for my crawl space rim joist?

    For the best air sealing performance: professional two-component closed-cell spray foam. For a DIY-accessible, lower-cost alternative that provides good (but not perfect) air sealing: rigid foam boards sealed at all four edges with one-component spray foam. The choice depends on budget and DIY capability — rigid foam is approximately 3–5× less expensive in material cost and requires no professional application.

    How much does rim joist spray foam cost?

    Professional closed-cell spray foam for the rim joist: $1.50–$3.00 per square foot of rim joist area. For a standard single-family home with approximately 250 sq ft of rim joist area: $375–$750 in material + labor. DIY rigid foam + one-component spray foam: $125–$375 in materials for the same area.

    Do I need to insulate the rim joist if my crawl space is vented?

    In a vented crawl space, the rim joist is part of the building thermal envelope — insulating it reduces heat loss between the conditioned living space and the vented, unconditioned crawl space. Rim joist insulation is valuable in both vented and sealed crawl spaces, though the approach differs slightly: in a vented space, the rim joist insulation must accommodate some moisture management; in a sealed space, the spray foam approach is fully appropriate without additional vapor barrier considerations in most climate zones.

  • Does Crawl Space Encapsulation Increase Home Value? What Buyers and Appraisers Look For

    The Distillery — Brew № 2 · Crawl Space

    Crawl space encapsulation is a significant home investment — $5,000 to $15,000 or more — and homeowners understandably want to know whether it translates to increased home value at resale. The honest answer is nuanced: encapsulation rarely adds dollar-for-dollar value to the appraised price, but it consistently helps homes sell faster, with fewer inspection contingencies, and without the price discounts that unaddressed crawl space problems typically generate. Understanding how buyers, agents, and appraisers view crawl space encapsulation helps set realistic expectations about the return on this investment.

    How Buyers View Crawl Space Encapsulation

    Buyer perception of crawl space encapsulation varies significantly by market. In high-radon or high-humidity regions where crawl space problems are common — the Southeast, Mid-Atlantic, Pacific Northwest, Appalachian states — buyers and their agents are more likely to ask about crawl space condition during the offer process and to view a documented encapsulation system as a positive feature.

    The positive buyer perception comes from what encapsulation represents: a seller who identified a potential problem, addressed it professionally, and has documentation proving it was done correctly. This is categorically different from an unaddressed crawl space problem, which triggers uncertainty, negotiation, and sometimes deal termination. A documented encapsulation with transferable warranty removes crawl space from the inspection negotiation entirely — buyers see it as a solved, documented issue rather than an unknown liability.

    In markets where crawl space encapsulation is less common knowledge (dry western markets, markets with predominantly slab-on-grade construction), buyers may not specifically seek it as a feature but will recognize it as a positive during inspection. The absence of musty odor, high humidity, and mold in the crawl space — confirmed during the home inspection — is itself a positive signal that reduces buyer anxiety during due diligence.

    How Appraisers Treat Crawl Space Encapsulation

    Residential real estate appraisers value homes primarily through comparable sales analysis — what similar homes in the area have sold for recently. Crawl space encapsulation presents a challenge for appraisers because it is a below-grade improvement that does not appear in the publicly observable features (square footage, bedroom count, bathroom count, garage) that drive comparable sale selection.

    The appraisal impact of crawl space encapsulation depends on:

    • Whether the appraiser can find comparable encapsulated homes: If comparable sales in the area frequently include encapsulation, the appraiser can adjust for its presence. In markets where encapsulation is rare, finding encapsulated comparables is difficult and the improvement may receive limited credit.
    • Whether unencapsulated crawl space problems would cause a negative adjustment: An appraiser who notes active mold, structural deterioration, or significant moisture problems in the crawl space of comparable homes (or the subject home without encapsulation) would apply a negative adjustment for those deficiencies. Encapsulation that prevents these negative adjustments is valuable even if it doesn’t generate a line-item positive adjustment.
    • Whether the appraiser is experienced with crawl space improvements: Residential appraisers in regions where crawl space encapsulation is common are more likely to recognize and value it appropriately than appraisers in markets where it is rare.

    The Real Value Proposition: Preventing Discounts, Not Adding Premiums

    The strongest ROI case for crawl space encapsulation at resale is not that it adds a premium — it is that it prevents the discounts and negotiation concessions that crawl space problems generate. Research on real estate inspection outcomes shows:

    • Homes with undisclosed or unresolved crawl space moisture problems discovered at inspection negotiate price reductions or repair credits averaging 1–3% of purchase price
    • Homes where buyers terminate due to crawl space issues (in markets where buyers have contingencies) face re-listing costs, days on market, and the stigma of a failed deal
    • Homes with documented encapsulation and clean post-installation testing close with fewer inspection contingency negotiations, reducing seller concession risk

    On a $350,000 home, a 2% inspection concession due to crawl space problems is $7,000 — enough to cover a mid-range encapsulation project. A seller who invested $8,000 in pre-listing encapsulation avoided a $7,000 concession, net cost of the encapsulation: $1,000. The energy savings, structural protection, and reduced maintenance costs over the ownership period are additional return on the original investment.

    Documentation That Maximizes Value at Resale

    The documentation package significantly affects how buyers, agents, and appraisers value a crawl space encapsulation. A seller with complete documentation can tell the story of the improvement clearly; a seller with no documentation is simply claiming an improvement that cannot be verified.

    Documentation that matters:

    • Pre-installation assessment report: The contractor’s or inspector’s findings before the project — what conditions prompted the encapsulation
    • Installation contractor information: Contractor name, license/certification number, installation date, system specification (barrier mil, brand, vent sealing method, dehumidifier model)
    • Post-installation radon test results (if radon was a concern or if ASMD was installed)
    • Post-installation humidity readings: Documentation that relative humidity in the sealed crawl space is below 60% (or ideally below 50%)
    • Manufacturer warranty documents for the barrier and dehumidifier
    • Contractor workmanship warranty: Is the warranty transferable to the new buyer? Transferable warranties significantly increase buyer confidence.
    • Annual inspection records: Evidence of ongoing monitoring — biennial humidity checks, wood moisture measurements — demonstrates a maintained system

    Frequently Asked Questions

    Does crawl space encapsulation increase home value?

    It more reliably prevents value discounts than it generates value premiums. A documented encapsulation removes crawl space from inspection negotiation risk — preventing the 1–3% price concessions that crawl space problems typically generate at inspection. On a $350,000 home, avoiding a $7,000 concession from an $8,000 encapsulation investment represents a near-dollar-for-dollar return at resale, plus ownership benefits (energy savings, air quality, structural protection) during the time the seller occupies the home.

    Do I have to disclose crawl space encapsulation when selling?

    Generally, yes — if you received a contractor report or had professional work done, that documentation is typically disclosable as a material fact about the property. The more relevant disclosure question is whether you must disclose the pre-encapsulation conditions (elevated humidity, mold, moisture problems) that prompted the encapsulation. In most states, known material defects — including conditions that existed before remediation — must be disclosed. Consult a real estate attorney in your state for specific disclosure requirements.

    Is a crawl space warranty transferable to the new owner?

    It depends on the contractor and the specific warranty terms. Ask your encapsulation contractor at installation time whether the workmanship warranty is transferable to subsequent owners — and get the answer in writing in the contract. Transferable warranties are a meaningful selling point; non-transferable warranties provide limited value to buyers who are then unprotected if problems develop after closing.

  • Claude Context Window Explained: From 200K to 1M Tokens

    Claude AI · Fitted Claude
    Updated April 2026: Claude Sonnet 4.6 and Opus 4.6 now support a 1 million token context window at standard pricing. Haiku 4.5 supports 200,000 tokens. The information below has been updated to reflect current specs.

    Claude’s context window is one of its most practically important technical specifications — and one of the least well understood. This guide explains tokens and context windows, how Claude’s compare to competitors, and strategies for working effectively within context limits.

    What Is a Context Window?

    A context window is the total amount of text a model can process in a single session — everything it can “see” and reason about at once. Context is measured in tokens. As a practical rule: 1,000 tokens ≈ 750 words.

    Claude’s Context Windows

    Access Method Context Window Approx. Words
    Standard Claude (all plans) 1,000,000 tokens (Sonnet/Opus), 200,000 (Haiku) ~750,000 words (Sonnet/Opus)
    Enterprise Claude 500,000 tokens ~375,000 words
    Claude Code 1,000,000 tokens ~750,000 words

    What Fits in 200K Tokens?

    • A full-length novel (~100,000 words)
    • 100-200 typical business emails
    • 10-15 long research papers
    • An entire small codebase (5,000-10,000 lines)
    • A year’s worth of meeting notes from a small team

    PDF and Document Token Costs

    • PDFs: 1,500-3,000 tokens per page
    • Plain text: ~1 token per 4 characters
    • Images: 1,000-4,000 tokens per image
    • Code files: 500-2,000 tokens per file

    Strategies for Long Contexts

    • Extract before uploading: Only upload relevant PDF sections, not full documents
    • Use Projects for reference material: Store knowledge base docs in Projects rather than re-uploading every session
    • Auto compaction (Claude Code beta): When coding sessions approach limits, Claude automatically summarizes history to continue

    Frequently Asked Questions

    How many pages can Claude read at once?

    With 200K tokens and ~1,500-3,000 tokens per PDF page, roughly 65-130 pages while leaving room for conversation.

    Does Claude forget things in long conversations?

    Not within the context window. In very long conversations approaching the limit, older content may be truncated.


    Need this set up for your team?
    Talk to Will →

  • Anthropic IPO 2026: Timeline, Valuation, and What Investors Need to Know

    Claude AI · Fitted Claude

    Anthropic’s IPO is one of the most anticipated public offerings in technology history. The company behind Claude AI — valued at over $61 billion in its most recent private round — is widely expected to go public in 2026 at a valuation that could rank among the largest technology IPOs ever. This guide covers the timeline, valuation analysis, and investment options available to retail and accredited investors.

    IPO Timeline: What We Know

    No official IPO date has been announced as of April 2026. Multiple reports point to a target of late 2026, with Goldman Sachs and JPMorgan Chase as lead underwriters. Anthropic reportedly surpassed $30B annualized revenue run rate in early 2026 — a strong foundation for a premium valuation multiple.

    Valuation: What the Numbers Suggest

    Anthropic’s last private valuation exceeded $61 billion. Analysts and bankers model an IPO range of $400-500 billion — a 6-8x step-up from the most recent private round, based on revenue growth trajectory and market position. This would place Anthropic among the top 20 most valuable public companies at listing.

    Pre-IPO Investment Options

    Secondary Market Platforms (Accredited Investors Only)

    • Hiive — Anthropic shares listed at approximately $849/share as of early 2026
    • EquityZen — Pre-IPO share access for accredited investors
    • Forge Global — Another secondary market platform for private company shares

    Important: Secondary market access requires accredited investor status (typically $1M+ net worth or $200K+ annual income). Shares may be illiquid until IPO and carry meaningful risk.

    Indirect Exposure

    Amazon (AMZN) has committed up to $4 billion in Anthropic investment. Google/Alphabet (GOOGL) invested $2 billion. These provide indirect exposure, though Anthropic represents a small fraction of either company’s total value.

    What to Watch

    • Revenue growth rate and enterprise customer count
    • Claude Code developer adoption metrics
    • Official S-1 filing (IPO prospectus)
    • Lead underwriter announcements and roadshow schedule

    Frequently Asked Questions

    When is the Anthropic IPO?

    No official date announced. Reports target late 2026, subject to market conditions.

    Can retail investors buy Anthropic stock before the IPO?

    Accredited investors can access pre-IPO shares through Hiive, EquityZen, or Forge Global. Retail investors without accredited status must wait for the public offering.


    Need this set up for your team?
    Talk to Will →

  • The Complete History of Anthropic: From OpenAI Split to $380B Valuation

    Claude AI · Fitted Claude

    Anthropic’s founding story is one of the most consequential in the history of artificial intelligence. Seven researchers who helped build the most powerful AI systems in the world walked away because they were worried about what those systems might become. This is the complete history.

    The OpenAI Origins

    By 2020, OpenAI had produced GPT-3 — a 175-billion-parameter language model demonstrating qualitatively new capabilities. Dario Amodei, VP of Research, and several colleagues were growing increasingly concerned: what happens when these systems become significantly more capable? The company’s “capped-profit” structure and commercial partnerships with Microsoft were creating tensions with pure safety research.

    The Precita Park Meetings

    In spring 2021, senior OpenAI researchers began meeting in Precita Park, a neighborhood park in San Francisco’s Bernal Heights. These conversations crystallized around a founding team: Dario Amodei (CEO), Daniela Amodei (President), Jared Kaplan (CSO), Chris Olah, Tom Brown, Sam McCandlish (CTO), and Jack Clark. All seven had been at OpenAI. All seven left within a compressed time period in mid-2021.

    The Founding

    Anthropic was incorporated in 2021 as a Public Benefit Corporation (PBC) — a legal structure that formally embeds a social mission alongside profit objectives. The name “Anthropic” (relating to human existence) reflects the mission: building AI safe and beneficial for humanity. Early funding: $124 million seed from Spark Capital.

    Constitutional AI

    Anthropic’s most significant research contribution: Constitutional AI — training models to follow written principles rather than relying solely on human feedback at every step. The “constitution” is a list of principles Claude upholds: honesty, avoiding harm, respecting user autonomy. This creates more consistent safety behavior across a wider range of situations.

    Growth and Current Status

    Major investments from Google ($2B) and Amazon (up to $4B) validated Anthropic’s trajectory. By 2026, Anthropic is valued at over $61 billion. Claude competes directly with GPT-4o and Gemini as one of the three most capable AI assistants in the world. An IPO targeting late 2026 at $400-500B is widely expected.

    Frequently Asked Questions

    Who founded Anthropic?

    Seven former OpenAI researchers: Dario Amodei (CEO), Daniela Amodei (President), Jared Kaplan (CSO), Chris Olah, Tom Brown, Sam McCandlish (CTO), and Jack Clark.

    Why did the Anthropic founders leave OpenAI?

    Growing concerns about AI safety practices and tensions between commercial pressures and rigorous safety research.


    Need this set up for your team?
    Talk to Will →

  • Claude AI Alternatives: 10 Tools for When Claude Isn’t Enough

    Claude AI · Fitted Claude

    Claude is one of the best AI assistants available — but it’s not the right tool for every job. It can’t generate images, doesn’t have default real-time web access, and lacks deep Google Workspace integration. Here are the 10 best Claude alternatives, each matched to where it genuinely wins.

    1. ChatGPT — Best All-Around Alternative

    Use when: You need image generation (DALL-E), broader plugin ecosystem, or voice mode. Price: Free / $20/month Plus / $200/month Pro.

    2. Perplexity — Best for Real-Time Research

    Use when: You need current information with source citations. Searches the live web in real time. Price: Free / $20/month Pro.

    3. Gemini — Best for Google Workspace

    Use when: You live in Gmail, Docs, Sheets, or Drive. Native integration across all Google Workspace apps. Price: Free / $20/month Advanced.

    4. Midjourney — Best for AI Image Generation

    Use when: You need high-quality AI-generated images. Claude cannot generate images at all. Price: $10-120/month.

    5. GitHub Copilot — Best IDE-Native Coding

    Use when: You want AI coding assistance embedded in VS Code or JetBrains with persistent autocomplete. Price: $10/month individual.

    6. Otter.ai — Best for Audio Transcription

    Use when: You need to transcribe meetings or audio files. Claude cannot process audio directly. Price: Free / from $10/month.

    7. Jasper — Best for Marketing Content at Volume

    Use when: You’re a marketing team producing high volumes of structured content with brand voice memory and SurferSEO integration. Price: From $49/month.

    8. Microsoft Copilot — Best for Office 365

    Use when: Your work lives in Word, Excel, PowerPoint, Teams, and Outlook. Native M365 suite integration. Price: $30/user/month.

    9. Notion AI — Best for Workspace-Embedded Writing

    Use when: You want AI assistance directly inside Notion — summarizing pages, drafting within documents, auto-filling databases. Price: $8-10/month add-on.

    10. DeepSeek — Best for Cost-Sensitive API Use

    Use when: Building API applications where per-token cost is the primary constraint and you’re not handling sensitive data. DeepSeek API is 10-20x cheaper. Note data sovereignty considerations. Price: Free consumer / very cheap API.

    Frequently Asked Questions

    What is the best free alternative to Claude AI?

    Gemini has the most generous free tier with capable model access. Perplexity free includes limited Pro searches. ChatGPT free uses GPT-4o-mini.


    Need this set up for your team?
    Talk to Will →

  • Claude Max Plan: Who Actually Needs $100/Month

    Claude AI · Fitted Claude

    The jump from Claude Pro to Max is a 5x price increase — $20/month to $100/month. Whether it’s worth it depends entirely on how you use Claude and where your current plan fails you. Here’s the data to make that decision.

    What’s Actually Different

    Feature Pro ($20/mo) Max 5x ($100/mo) Max 20x ($200/mo)
    Usage volume Baseline 5x Pro 20x Pro
    Heavy prompts/day ~12 ~60 ~240
    Claude Code No Yes Yes
    Extended thinking Limited Full Full
    Model access Sonnet + Opus Sonnet + Opus Sonnet + Opus

    Key insight: you don’t get different models at Max — you get more of them. The difference is usage capacity and Claude Code access.

    Who Should Stay on Pro

    • You use Claude regularly but not all day — a few substantive sessions per week
    • You’re hitting limits occasionally but not consistently
    • You don’t need Claude Code

    Who Needs Max 5x

    • You hit Pro limits daily and it disrupts your workflow
    • You want Claude Code — only available at Max tiers
    • Claude is your primary work tool, not supplementary

    Who Needs Max 20x

    • Heavy Claude Code user running multi-hour sessions daily
    • Processing massive document volumes — dozens of long PDFs per day
    • You’ve been hitting Max 5x limits regularly

    Frequently Asked Questions

    What does Claude Max include that Pro doesn’t?

    Claude Code access, higher usage limits (5x or 20x), full extended thinking, and higher priority during peak times.

    Is Claude Max worth $100 a month?

    For developers using Claude Code and professionals hitting Pro limits daily: yes. For moderate users: Pro at $20/month is sufficient.


    Need this set up for your team?
    Talk to Will →

  • Claude vs Perplexity: Research Engine vs Reasoning Partner

    Claude AI · Fitted Claude

    Comparing Claude to Perplexity is a category error — they’re not trying to do the same thing. Perplexity is a real-time research engine. Claude is a reasoning partner. Understanding the distinction helps you build the most effective research workflow.

    What Perplexity Does Best

    • Real-time information: Searches the live web, summarizes current events with source links
    • Source citation: Every claim has source links for verification
    • Quick research: Fast sourced answers for “what is X” and “what happened with Y”
    • Academic research: Academic mode searches peer-reviewed papers

    What Claude Does Best

    • Deep reasoning: Complex multi-step analysis and strategic thinking
    • Document synthesis: Upload a 200-page report and ask for analysis — Perplexity cannot do this
    • Writing quality: Significantly stronger long-form writing
    • Code: One of the best coding models. Perplexity is not a coding tool.
    • Private documents: Works with confidential content you upload

    The Hybrid Workflow (Best of Both)

    1. Perplexity first: Rapid research, current information, source discovery
    2. Claude second: Synthesis, analysis, writing. Take what Perplexity found and reason through the implications

    At $20/month each, running both costs $40/month — worth it for professionals who research and write regularly.

    Frequently Asked Questions

    Should I use Claude or Perplexity for research?

    Use Perplexity for finding current information with sources. Use Claude for analyzing, synthesizing, and writing. Ideally, use both — Perplexity first, Claude second.

    Does Claude have real-time web access?

    Not by default. Claude has a knowledge cutoff and doesn’t browse the web in real time unless connected via MCP or specific integrations.


    Need this set up for your team?
    Talk to Will →

  • Claude vs DeepSeek: Performance, Pricing, and Privacy

    Claude AI · Fitted Claude

    DeepSeek emerged as the most disruptive AI development since GPT-4 — a Chinese lab producing frontier-quality models at dramatically lower cost. In 2026, it’s a genuine competitor to Claude in several categories. But the comparison isn’t only about performance. Privacy and data sovereignty matter. This guide covers all three dimensions.

    Performance Comparison

    Benchmark Claude Opus 4.6 DeepSeek
    SWE-bench (coding) 80.8% ~49% (V3), higher for R1
    GPQA Diamond 91.3% Competitive
    Math reasoning Top tier R1 leads on pure math
    Context window 200K tokens 128K tokens

    Claude leads on real-world software engineering and long-document reasoning. DeepSeek R1 is competitive or superior on pure math. For most professional use cases, Claude holds the performance edge.

    Pricing Comparison

    DeepSeek’s API pricing is 10-20x cheaper than Claude’s — roughly $0.27-0.55 per million input tokens vs Claude’s $3-15. For high-volume API applications where cost is the primary constraint, DeepSeek is a serious consideration. The consumer interface is free vs Claude’s $20-200/month paid tiers.

    The Privacy Question

    DeepSeek is a Chinese company. Its data handling is subject to Chinese law, which includes requirements to provide user data to Chinese government authorities under certain circumstances. Multiple national governments have restricted DeepSeek on government systems. For professionals handling confidential client data or sensitive business information, the data sovereignty difference between Anthropic (US-incorporated) and DeepSeek (Chinese-incorporated) is material.

    Choose Claude If You…

    • Handle confidential professional, legal, or medical data
    • Need highest performance on software engineering tasks
    • Require long-document analysis (200K vs 128K context)
    • Need US-based data handling

    Frequently Asked Questions

    Is DeepSeek as good as Claude?

    Competitive on math and logic. Claude leads on SWE-bench software engineering, long documents, and writing quality.

    Is DeepSeek safe to use?

    For general consumer use, immediate risk is low. Professionals handling sensitive data should consider DeepSeek’s Chinese data jurisdiction carefully.


    Need this set up for your team?
    Talk to Will →

  • MCP Servers Explained: Model Context Protocol Tutorial

    Claude AI · Fitted Claude

    Model Context Protocol (MCP) is the most important infrastructure development in Claude’s ecosystem in 2026. It’s an open standard for connecting AI models to external tools, data sources, and services — replacing fragmented one-off integrations with a universal interface. This guide explains what MCP is and how to set up your first server.

    What Is MCP?

    MCP defines a universal interface: any tool that implements the MCP server specification can connect to any AI application implementing the MCP client specification. Build once, connect anywhere. Before MCP, connecting Claude to external systems required custom integration code for every integration — and none of it worked across different AI tools.

    MCP Architecture

    • MCP Host: The AI application (Claude desktop, Claude Code, your custom app)
    • MCP Client: Built into the host; manages connections to servers
    • MCP Server: Lightweight program exposing tools, resources, or prompts

    Setting Up MCP in Claude Desktop

    Go to Settings → Developer → Edit Config. Add your server configuration:

    {
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/directory"]
    }
  }
}

    Restart Claude Desktop. Claude can now read, write, and manage files in your specified directory.

    Popular MCP Servers

    Server What It Does
    Filesystem Read/write local files
    GitHub Manage repos, issues, PRs
    PostgreSQL Query databases
    Slack Read/send messages
    Brave Search Real-time web search
    Zapier Connect to 8,000+ apps

    Frequently Asked Questions

    Is MCP open source?

    Yes. Anthropic open-sourced the MCP specification and official server implementations.

    Do I need to code to use MCP?

    To install existing servers: basic command-line comfort is enough. To build custom servers: TypeScript or Python knowledge required.


    Need this set up for your team?
    Talk to Will →