Tygart Media Editorial - Tygart Media

Category: Tygart Media Editorial

Tygart Media’s core editorial publication — AI implementation, content strategy, SEO, agency operations, and case studies.

  • What Notion’s Claude Managed Agents Integration Actually Does

    What Notion’s Claude Managed Agents Integration Actually Does

    Tygart Media Strategy
    Volume Ⅰ · Issue 04Quarterly Position
    By Will Tygart
    Long-form Position
    Practitioner-grade

    When Anthropic launched Claude Managed Agents, Notion was one of four launch partners. That detail got buried in the announcement. Here’s what it actually means for people who use Notion for knowledge work, and why “Notion voice input desktop” keeps showing up as a query against a Managed Agents page.

    Short answer: Managed Agents in Notion is an ambient intelligence layer. It’s not a chatbot in a sidebar. It’s an agent that watches your workspace and acts — without you directing every step.

    What the Notion Integration Actually Does

    Notion’s Claude Managed Agents integration runs as a persistent background agent with access to your workspace. The practical capabilities, as documented at launch:

    • Autonomous page updates: The agent can read, summarize, and rewrite Notion pages without manual triggers. You set a task; it works through it.
    • Cross-database synthesis: Pull data from multiple Notion databases, synthesize it, and write outputs to a target page or database entry
    • Meeting note processing: Ingest raw meeting notes and produce structured summaries, action items, and task entries in your project database
    • Workflow automation: Trigger actions based on database property changes — a status update in one database can kick off agent work in another

    The key difference from Notion AI (which Notion has had for some time): Notion AI is request-response. You ask it something; it answers. Managed Agents in Notion can be configured to run autonomously on a schedule or on trigger, keep working through multi-step tasks, and report back when done. It’s closer to a background employee than an on-demand assistant.

    Why This Showed Up in Search as “Notion Voice Input Desktop”

    This is worth explaining, because that query cluster is real and mildly interesting. The Managed Agents announcement included voice input functionality — the ability to interact with agents via voice in some contexts. People searching “notion voice input desktop” and “notion ai voice input desktop” were looking for whether this voice capability existed in the desktop client for Notion specifically.

    The honest answer as of April 2026: voice input capabilities are in preview or context-dependent. Verify current availability in Notion’s desktop client against their current documentation — this is an area that may have evolved since launch.

    The “Decoupled Brain and Hands” Model Applied to Notion

    Anthropic describes their Managed Agents architecture as decoupling the brain (Claude, the reasoning layer) from the hands (the sandboxed containers where actions execute). In Notion’s context, this maps cleanly:

    • The brain reads your Notion workspace, understands context, makes decisions about what to do
    • The hands execute — writing to pages, updating database entries, moving content between sections

    The brain and hands operate independently. The agent can reason about what your project needs without being tightly coupled to the specific API calls that will implement it. This matters because it means the agent can handle ambiguity — “clean up the Q2 notes and create action items” is a goal, not a procedure, and the agent figures out the procedure.

    What You Actually Configure

    To run Claude Managed Agents in Notion, you’re defining:

    • Task definition: What the agent is supposed to accomplish (in natural language or structured format)
    • Tool access: Which Notion databases, pages, and capabilities the agent can read and write
    • Guardrails: What the agent cannot do — pages it can’t modify, actions it must confirm before taking
    • Trigger: When the agent runs — on schedule, on database trigger, or on demand

    You don’t write the orchestration logic. Anthropic’s infrastructure handles session management, state persistence, and error recovery. If the agent hits an error mid-task, it checkpoints and recovers — you don’t lose progress.

    The Practical Cost of Running Notion Agents

    Using Managed Agents in Notion triggers the same billing as any Managed Agents session: standard token rates plus $0.08/session-hour of active runtime. For typical knowledge work tasks:

    • A daily meeting summary agent running 15 minutes of active execution: ~$0.02/day in runtime (~$0.60/month), plus token costs for the volume of notes processed
    • A weekly database synthesis task running 45 minutes: ~$0.06/run

    For most knowledge workers, the session runtime cost is negligible — the token costs (driven by how much content the agent reads and writes) are the actual variable to model. See the complete pricing reference for worked examples.

    Asana and the Broader Pattern

    Asana was also a Managed Agents launch partner, and the integration pattern is similar: an agent that can read project data, update task statuses, move cards, and generate project summaries without constant human direction. The launch partner list (Notion, Asana, Rakuten, Sentry) suggests Anthropic targeted three categories: knowledge management (Notion), project management (Asana), enterprise operations (Rakuten), and developer tools (Sentry).

    That’s a deliberate wedge. If agents can handle the administrative layer of these four categories, the surface area for autonomous business work expands significantly.

    What This Means for How You Work

    The honest use case for most people reading this: you have a Notion workspace with databases that need regular synthesis, and you’re currently doing that manually. Managed Agents is the path to automating that synthesis without building and maintaining a custom integration.

    The constraint worth naming: you’re running your workspace data through Anthropic’s infrastructure. That’s the trade-off. For most knowledge work, the data sensitivity concern is low. For anything involving client data, legal documents, or proprietary strategy — read Anthropic’s data handling terms before configuring access.

    For the full Managed Agents setup and pricing context: Claude Managed Agents: Every Question Answered. For the enterprise deployment pattern: How Rakuten Deployed 5 Enterprise Agents in a Week.

  • Claude Managed Agents — Every Question Answered (Complete FAQ 2026)

    Claude Managed Agents — Every Question Answered (Complete FAQ 2026)

    Tygart Media Strategy
    Volume Ⅰ · Issue 04Quarterly Position
    By Will Tygart
    Long-form Position
    Practitioner-grade

    Everything people actually ask about Claude Managed Agents, answered straight. No preamble about “the exciting world of AI agents.” If you’re here, you already know why this matters — you just need answers.

    This page covers pricing, setup, capabilities, limits, comparisons, and the specific questions that don’t have obvious homes in Anthropic’s documentation. It updates as the beta evolves.

    Context

    Claude Managed Agents launched April 8, 2026 as a public beta. All answers reflect current documentation as of April 2026. Beta details change — verify specifics at platform.claude.com/docs.

    Pricing Questions

    What does Claude Managed Agents cost?

    Two charges: standard Claude API token rates (same as calling the Messages API directly) plus $0.08 per session-hour of active runtime. That’s the complete formula. See the complete pricing reference for worked examples by workload type.

    What exactly is a “session-hour” and when does it start billing?

    A session-hour is one hour of active session runtime — time when your session’s status is running. Billing is metered to the millisecond. It does not accrue during idle time, time waiting for your input, time waiting for tool confirmations, or after session termination.

    What’s included in the $0.08/session-hour charge?

    The session runtime charge covers Anthropic’s managed infrastructure: sandboxed code execution containers, state management, checkpointing, tool orchestration, error recovery, and scaling. You are not separately billed for container hours on top of session runtime.

    Does the $0.08/hr apply even if my agent is just waiting?

    No. Time spent waiting for your message, waiting for tool confirmations, or sitting idle does not accumulate runtime charges. Only active execution time counts.

    What does web search cost inside a Managed Agents session?

    $10 per 1,000 searches ($0.01 per search), billed separately from session runtime and token costs. This is the same rate as web search through the standard API.

    Are there volume discounts?

    Yes, negotiated case-by-case for high-volume users. Contact [email protected] or through the Claude Console.

    How does Managed Agents pricing compare to running my own agent infrastructure?

    The $0.08/session-hour is almost always cheaper than equivalent provisioned compute — but you trade infrastructure control and data locality for that simplicity. For a full comparison: Build vs. Buy: The Real Infrastructure Cost.

    What’s the real monthly cost if I run an agent 24/7?

    Maximum theoretical session runtime: 24 hrs × $0.08 × 30 days = $57.60/month. In practice, no production agent has zero idle time. Token costs become the dominant cost driver long before you hit the runtime ceiling. Detailed breakdown: The Real Monthly Cost of Running Claude Managed Agents 24/7.

    Setup and Access Questions

    How do I get access to Claude Managed Agents?

    Available to all Anthropic API accounts in public beta — no separate signup. You need the managed-agents-2026-04-01 beta header in your API requests. The Claude SDK adds this header automatically.

    Does it work with my existing API key?

    Yes. Same API key you’re already using for the Messages API. Same authentication. The beta header is the only new requirement.

    What three ways can I access Managed Agents?

    Via the Claude SDK (recommended — handles the beta header automatically), via direct API calls with the beta header, or via the Claude Console’s new Managed Agents section for no-code agent configuration and session tracing.

    Can I use Managed Agents through AWS Bedrock or Google Vertex AI?

    Managed Agents runs on Anthropic-managed infrastructure. This is distinct from Bedrock and Vertex AI deployments. Check Anthropic’s current documentation for multi-cloud availability status — this is an area of active development.

    Capability Questions

    What can Claude Managed Agents actually do?

    Run long autonomous sessions with persistent state, execute code in sandboxed Linux containers, use tools including web search and MCP servers, coordinate multiple Claude instances via Agent Teams, and maintain checkpoints for crash recovery. The session can last minutes or hours without you staying in the loop.

    What’s the difference between Agent Teams and subagents?

    Agent Teams coordinate multiple Claude instances with independent contexts, direct agent-to-agent communication, and a shared task list — suited for complex parallel tasks. Subagents operate within the same session as the main agent and only report results upward — more economical for sequential targeted tasks but less capable of true parallelism.

    Does it support MCP servers?

    Yes. MCP servers can be integrated as tool sources in Managed Agents sessions, extending what the agent can access and act on.

    How long can a session run?

    Anthropic’s documentation currently references session durations of minutes to hours. Claude Code’s longest autonomous sessions have reached 45 minutes. Managed Agents is architected for longer-running work. Check current documentation for specific session duration limits as the beta matures.

    What happened to Claude Code — is it the same as Managed Agents?

    No. Claude Code is a separate local coding workflow product. Anthropic’s docs explicitly note partners should not conflate the two. Managed Agents is a hosted API runtime service. Claude Code is a developer tool. Different products, different use cases, different billing.

    Rate Limit Questions

    What are the rate limits for Managed Agents?

    60 requests per minute for create endpoints; 600 requests per minute for read endpoints. Organization-level API limits still apply on top of these. For higher limits, contact Anthropic enterprise sales. Detailed breakdown: Claude Managed Agents Rate Limits Explained.

    Do standard Claude API rate limits still apply inside a session?

    Organization-level limits apply. The session runtime and create/read endpoint limits are Managed Agents-specific. If you’re running many parallel Agent Teams, model token throughput limits will become relevant.

    Comparison Questions

    How does Managed Agents compare to OpenAI’s Agents API?

    Both offer hosted agent infrastructure. Key differences: Managed Agents is Claude-native (no multi-model flexibility), sessions bill on runtime + tokens vs. OpenAI’s different pricing model, and lock-in dynamics differ. Full comparison: Claude Managed Agents vs. OpenAI Agents API.

    Should I use Managed Agents or the Claude Agent SDK?

    Use Managed Agents when you want Anthropic to host the runtime — less infrastructure work, faster to production. Use the SDK when you need tighter loop control, on-premise execution, or multi-cloud flexibility. Anthropic’s own migration docs draw this line clearly: SDK runs in your environment; Managed Agents runs in theirs.

    What companies are already using Managed Agents in production?

    Notion, Asana, Rakuten, Sentry, and Vibecode were launch partners. Rakuten deployed five enterprise agents within a week. Allianz is using Claude for insurance agent workflows. Anthropic’s run-rate from the agent developer segment exceeds $2.5 billion. How Rakuten did it in a week →

    Data and Security Questions

    Where does my data go when running in Managed Agents?

    Execution runs on Anthropic’s infrastructure. This is the explicit trade-off: you get managed infrastructure; they manage the compute. For companies with strict data sovereignty requirements, this is the key constraint to evaluate. On-premise or native multi-cloud deployment is not currently available.

    What are the sandboxing guarantees?

    Anthropic uses disposable Linux containers — “decoupled hands” in their terminology. Each container is a fresh sandboxed environment for code execution. State persistence is managed separately from the execution environment.

    Strategic Questions

    Is this a bet worth making?

    That depends on your switching cost tolerance. Lock-in is real: once your agents run on Anthropic’s infrastructure with their tools, session format, and sandboxing, switching providers isn’t trivial. The counter-argument: the infrastructure you’d otherwise build to match this is months of engineering. One developer’s reaction at launch was blunt: “there goes a whole YC batch.” That captures both the opportunity and the risk. Our take on why we’re staying our course →

    What does this mean for AI citation and visibility?

    Agents running on Anthropic’s infrastructure make decisions about what content to surface, cite, and synthesize. As agent workloads grow, being present in the knowledge sources agents draw from becomes a search strategy question in itself. What AI citation monitoring looks like →

  • Claude Managed Agents — Complete Pricing Reference + Dreaming Update (May 2026)

    Claude Managed Agents — Complete Pricing Reference + Dreaming Update (May 2026)

    Last refreshed: May 15, 2026

    May 2026 Update — Dreaming Feature + Beta Status

    Anthropic introduced Dreaming at Code w/ Claude (May 6, 2026) — a new Managed Agents capability where agents review their own session history overnight to improve future performance. Harvey (legal AI) reported a roughly 6× task completion rate increase after implementing it. Dreaming is developer-access preview only. Multiagent Orchestration and Outcomes are now in public beta. See the new Dreaming section below.

    What Is Claude Managed Agents? (Current Status, May 2026)

    Claude Managed Agents is Anthropic’s framework for long-running, stateful AI agents — agents that can maintain context across sessions, hand off between sub-agents, and now, improve themselves by reviewing their own work history. Here’s the current status of each component:

    Component Status Who Has Access
    Multiagent Orchestration Public Beta All API developers
    Outcomes Public Beta All API developers
    Dreaming Developer Preview Selected developers only

    Dreaming: The Feature the Press Mostly Missed

    Announced at Code w/ Claude on May 6, 2026, Dreaming is a Managed Agents capability that lets agents review and reorganize their own memory between sessions. The mechanism:

    1. After a session ends, the agent reads its existing memory store alongside the session transcripts
    2. It produces a new, reorganized memory store: duplicates merged, stale entries replaced, new patterns surfaced
    3. The next session starts with a higher-quality knowledge base — capturing insights no single session could hold

    This is meaningfully different from simply persisting conversation history. The agent isn’t just remembering what happened — it’s synthesizing what it learned. Think of it as the difference between taking notes and actually reviewing and reorganizing your notes the next morning.

    The Harvey Result

    Harvey, the legal AI company, reported approximately a 6× task completion rate increase after implementing Dreaming in their Managed Agents workflow. Harvey’s use case — complex legal research that spans multiple sessions with evolving context — is exactly the kind of work Dreaming was designed for. Sessions build on each other rather than starting fresh each time.

    Dreaming is developer-access preview as of May 2026. Docs: platform.claude.com/docs/en/managed-agents/dreams.

    What Dreaming Is Not

    A few clarifications worth making explicit:

    • Dreaming is not available to end users — it’s a developer-layer capability requiring implementation
    • It’s not persistent memory in the claude.ai chat interface
    • It’s not available to free or standard Pro subscribers through any interface
    • It’s a developer preview, not GA — expect it to evolve before full release

    Our Take: Why This Architecture Matters

    We run Managed Agents in our own Cowork workflows. The Dreaming announcement is the first time Anthropic has shipped something that resembles how expert human knowledge actually compounds over time — not by accumulating raw notes, but by periodically synthesizing and reorganizing what’s been learned into a cleaner structure.

    The Harvey 6× result is a real-world data point from a production legal AI workflow. That’s not a benchmark number — it’s a deployed system showing measurable improvement from session-to-session memory refinement. Whether that 6× figure holds across different use cases is unknown, but the direction of the effect is the signal: agents that learn from their own history outperform agents that don’t.

    For non-developer users watching this space: Dreaming is the preview of what agentic AI will look like when it becomes mainstream. The groundwork being laid now in developer preview will eventually surface in subscription-tier products.

    Model Accuracy Note — Updated May 2026

    Current flagship: Claude Opus 4.7 (claude-opus-4-7). Current models: Opus 4.7 · Sonnet 4.6 · Haiku 4.5. Claude Opus 4.7 (claude-opus-4-7) is the current flagship as of April 16, 2026. Where this article references Opus 4.6 or earlier models, those references are historical. See current model tracker →. See current model tracker →

    Tygart Media Strategy
    Volume Ⅰ · Issue 04Quarterly Position
    By Will Tygart
    Long-form Position
    Practitioner-grade

    You opened this tab because you need a number you can actually use. Not a vibe, not “it depends.” A real pricing breakdown you can put in a spreadsheet, a budget request, or a Slack message to your CTO.

    This is that page. Every pricing variable for Claude Managed Agents in one place, verified against Anthropic’s current documentation as of April 2026. Bookmark it. The beta will update; so will this.

    Quick Reference: The Formula

    Total Cost = Token Costs + Session Runtime ($0.08/hr) + Optional Tools
    Session runtime only accrues while status = running. Idle time is free.

    The Two Cost Dimensions

    Claude Managed Agents bills on exactly two dimensions: tokens and session runtime. Every pricing question you have collapses into one of these two buckets.

    Dimension 1: Token Costs

    These are identical to standard Claude API pricing. You pay the same rates you’d pay calling the Messages API directly. No Managed Agents markup on tokens. Current rates for the models most commonly used in agent work:

    • Claude Sonnet 4.6: ~$3/million input tokens, ~$15/million output tokens
    • Claude Opus 4.7: higher rates apply — check platform.claude.com/docs/en/about-claude/pricing for current figures
    • Prompt caching: same multipliers as standard API — cache hits dramatically reduce input token costs on long sessions with stable system prompts

    The implication: a token-heavy agent with a large system prompt that runs the same context repeatedly benefits significantly from prompt caching, and that benefit carries over unchanged into Managed Agents.

    Dimension 2: Session Runtime — $0.08/Session-Hour

    This is the Managed Agents-specific charge. You pay $0.08 per hour of active session runtime, metered to the millisecond.

    The critical word is active. Runtime only accrues while your session’s status is running. The following do not count toward your bill:

    • Time spent waiting for your next message
    • Time waiting for a tool confirmation
    • Idle time between tasks
    • Rescheduling delays
    • Terminated session time

    This is not how you’d bill a virtual machine. It’s closer to how AWS Lambda bills — you pay for execution, not reservation. An agent that “runs” for 8 hours but spends 6 of those hours waiting on human input has a very different bill than one running continuous autonomous loops.

    Optional Tool Costs

    Web Search: $10 per 1,000 Searches

    If your agent uses web search, each search costs $10/1,000 — that’s $0.01 per search. For most agents, this is negligible. For a research agent running hundreds of searches per session, it becomes a line item worth modeling separately.

    Code Execution: Included in Session Runtime

    Code execution containers are included in your $0.08/session-hour charge. You’re not separately billed for container hours on top of session runtime. This is explicitly stated in Anthropic’s docs and represents meaningful savings versus provisioning your own compute.

    Worked Cost Examples

    Example 1: Daily Research Agent

    Runs once per day. 30 minutes of active execution. Processes 10 documents, outputs a summary report. Moderate token volume.

    • Session runtime: 0.5 hrs × $0.08 = $0.04/day (~$1.20/month)
    • Tokens (estimate): 50K input + 5K output with Sonnet 4.6 = ~$0.23/run (~$7/month)
    • Total: ~$8–10/month

    Example 2: Weekly Batch Content Pipeline

    Runs 3x/week. 2-hour active sessions. Processes multiple documents, generates structured outputs.

    • Session runtime: 2 hrs × $0.08 × 12 sessions/month = $1.92/month
    • Tokens: depends on content volume — typically $10–40/month
    • Total: ~$12–42/month

    Example 3: Customer Support Agent (Business Hours)

    Active during business hours, handling tickets. 8 hours/day active, 5 days/week.

    • Session runtime: 8 hrs × $0.08 × 22 days = $14.08/month in runtime
    • Tokens: highly variable by ticket volume — the dominant cost driver at scale
    • Runtime cost alone: ~$14/month — tokens are likely 5–20x this depending on volume

    Example 4: 24/7 Always-On Agent

    The maximum theoretical runtime exposure. Continuous operation, no idle time.

    • Session runtime: 24 hrs × $0.08 × 30 days = $57.60/month
    • In practice, no agent has zero idle time — real cost will be lower
    • Token costs at this scale become the dominant factor by a wide margin

    Anthropic’s Official Example (from their docs)

    A one-hour coding session using Claude Opus 4.7 consuming 50,000 input tokens and 15,000 output tokens: session runtime = $0.08. With prompt caching active and 40,000 of those tokens as cache reads, the token costs drop significantly. The runtime charge stays flat at $0.08 regardless of caching.

    What’s Not Billed in Managed Agents

    A few things that might seem like costs but aren’t:

    • Infrastructure provisioning: Anthropic handles hosting, scaling, and monitoring at no additional charge
    • Container hours: Explicitly not separately billed on top of session runtime
    • State management and checkpointing: Included in the session runtime charge
    • Error recovery and retry logic: Anthropic’s infrastructure problem, not yours

    Rate Limits

    Managed Agents has specific rate limits separate from standard API limits:

    • Create endpoints: 60 requests/minute
    • Read endpoints: 600 requests/minute
    • Organization-level limits still apply
    • For higher limits, contact Anthropic enterprise sales

    How to Access Managed Agents Pricing

    Managed Agents is available to all Anthropic API accounts in public beta. No separate signup, no premium tier gate. You need the managed-agents-2026-04-01 beta header in your API requests — the Claude SDK adds this automatically.

    For high-volume agent applications, Anthropic’s enterprise sales team negotiates custom pricing arrangements. Contact them at [email protected] or through the Claude Console.

    The Pricing Signals Worth Noting

    Anthropic recently ended Claude subscription access (Pro/Max) for third-party agent frameworks, requiring those users to switch to pay-as-you-go API pricing. This signals a deliberate strategy: consumer subscriptions are for human-paced interactions; agent workloads route through the API. The $0.08/session-hour rate exists in that context — it’s infrastructure pricing for compute that runs beyond human attention spans.

    The session-hour model also signals something about Anthropic’s infrastructure cost structure. They’re pricing on active execution time because that’s what actually taxes their systems. Idle sessions don’t cost them much; active agents do. The billing model follows the actual resource consumption pattern.

    Frequently Asked Questions

    Is the $0.08/session-hour charge in addition to token costs, or does it replace them?

    In addition to. You pay both: standard token rates for all input and output tokens, plus $0.08 per hour of active session runtime. They’re separate line items.

    Does prompt caching work in Managed Agents sessions?

    Yes. Prompt caching multipliers apply identically to Managed Agents sessions as they do to standard API calls. If your agent has a large, stable system prompt, caching it can significantly reduce input token costs.

    What happens if my session crashes? Am I billed for the crashed time?

    Runtime accrues only while status is running. Terminated sessions stop accruing. Anthropic’s infrastructure handles checkpointing and crash recovery — the session state is preserved even if the session terminates unexpectedly.

    Can I use Managed Agents on the free API tier?

    Managed Agents is available to all Anthropic API accounts in public beta, but standard tier access and rate limits apply. Free API tier users receive a small credit for testing.

    How does this compare to running agents on my own infrastructure?

    See our full breakdown: Build vs. Buy: The Real Infrastructure Cost of Claude Managed Agents. Short version: the $0.08/hour is almost certainly cheaper than provisioning and maintaining equivalent compute, but you trade control and data locality for that simplicity.

    Are there volume discounts?

    Volume discounts are available for high-volume users but negotiated case-by-case. Contact Anthropic enterprise sales.

    Does web search billing count against the $10/1,000 rate if the search returns no results?

    Anthropic’s current docs don’t explicitly address failed searches. Treat any triggered search as billable until confirmed otherwise.

    For the full session-hour math worked out by workload type, see: Claude Managed Agents Pricing, Decoded: What a Session-Hour Actually Costs You. For the build-vs-buy infrastructure comparison: Build vs. Buy: The Real Infrastructure Cost. For enterprise deployment patterns: Rakuten Stood Up 5 Enterprise Agents in a Week.

  • The Delta Is the Asset: Why Only What Changes Knowledge Actually Compounds

    The Delta Is the Asset: Why Only What Changes Knowledge Actually Compounds

    The Distillery
    — Brew № — · Distillery

    There is one thing that justifies the existence of any piece of information — whether it is a questionnaire answer, a blog post, a research paper, or a conversation. That thing is the delta.

    The delta is the gap between what was known before and what is known after. It is the only unit of measurement that matters in a knowledge economy. Everything else — word count, publication frequency, keyword coverage, contributor count — is a proxy metric. The delta is the real one.

    What the Delta Actually Measures

    Most information does not create a delta. It moves existing knowledge from one container to another. An article that summarizes three other articles, a questionnaire response that confirms what the system already knows, a report that restates findings from prior reports — none of these change the state of knowledge. They change the location of knowledge. That is a logistics operation, not a knowledge operation.

    A delta event is different. Something enters the system that was not there before. A practitioner documents a process that existed only in their head. A contributor surfaces an edge case that the general model did not account for. A writer names a pattern that everyone in an industry recognizes but no one has articulated. After the contribution, the knowledge base is genuinely different. The world knows something it did not know before. That difference is the delta. That is the asset.

    Why the Delta Compounds

    A piece of content that contains a genuine delta does not depreciate the way a paraphrase does. It becomes a reference point. Other content cites it, links to it, builds on it. AI systems trained on it carry it forward. People who read it share what they learned from it because they actually learned something. The delta propagates.

    A paraphrase, by contrast, is immediately superseded by the next paraphrase. It has no anchor in the knowledge base because it did not change the knowledge base. It cannot be built upon because it introduced nothing to build upon. It ages and falls away.

    This is why high-delta content from years ago still ranks, still gets cited, still drives traffic. It earned its place in the knowledge base by changing what the knowledge base contained. Low-delta content from last week is already invisible because it never earned that place.

    The Knowledge Token System as a Delta Detector

    The reason knowledge token systems score contributions on novelty, specificity, and density is that those three variables are proxies for delta magnitude. A novel answer changed the state of what is known. A specific answer created a precise, actionable change rather than a vague one. A dense answer created a large change relative to the effort of processing it.

    The token grant is not payment for time spent filling out a form. It is compensation for delta generated. A contributor who spends five minutes giving a genuinely novel, specific, dense answer earns more tokens than a contributor who spends an hour giving generic, vague, low-density answers. The system is not rewarding effort. It is rewarding contribution to the actual state of knowledge.

    This inverts the typical incentive structure of content production and knowledge collection, where volume is rewarded because volume is easy to measure. Delta is harder to measure — but it is the right thing to measure, and the systems that measure it correctly end up with knowledge bases that are actually valuable rather than merely large.

    The Delta Test for Content

    Every piece of content can be evaluated with a single question: what does the collective knowledge base contain after this piece exists that it did not contain before?

    If the answer is “the same information, arranged slightly differently” — the delta is zero. The piece is a redistribution event, not a knowledge event. It may serve a purpose — reaching a new audience, establishing a presence on a keyword — but it should not be confused with a knowledge contribution. It will not compound. It will not be cited. It will not earn its place in the knowledge base because it did not change the knowledge base.

    If the answer is “a named framework that did not previously exist,” or “a documented process that only existed in one practitioner’s head,” or “a specific finding that contradicts the prevailing assumption” — the delta is real. The piece has a reason to exist beyond its publication date. It becomes the reference, not one of many paraphrases pointing at a reference that does not exist.

    Building Toward Delta

    The practical implication is that delta-generating content requires something to say before the writing begins. Not a topic. Not a keyword. Something to say — a specific insight, a documented process, a named pattern, a genuine finding. The writing is the vehicle for the delta, not the source of it.

    This is why the Human Distillery model works. It does not start with a content calendar. It starts with people who know things that have not been written down. The extraction process — the interview, the questionnaire, the structured conversation — pulls the delta out of a practitioner’s head and into a form the knowledge base can absorb. The writing that follows is the articulation of something real. That is why it compounds.

    The knowledge token economy operationalizes the same logic. Contributors who have genuine deltas to offer — real expertise, specific processes, novel findings — earn meaningful access. Contributors who are redistributing existing knowledge earn little. The system is a delta detector, and it rewards accordingly.

    The Only Metric That Matters

    Publication frequency does not compound. Word count does not compound. Keyword coverage does not compound. Contributor volume does not compound.

    Delta compounds.

    A knowledge base built on genuine deltas — whether those deltas come from structured interviews, scored questionnaires, or pieces of content that actually changed what readers know — becomes more valuable over time in a way that a knowledge base built on redistributed information never will. The compounding is not metaphorical. It is structural. Each delta makes the base more complete, which makes each subsequent delta easier to identify because you can see exactly what is missing.

    The businesses, content operations, and API systems that understand this will build knowledge bases that are genuinely defensible. Not because they published more, but because they published things that changed the state of what is known. The delta is the asset. Everything else is overhead.

  • Your Content Is a Knowledge Contribution — Score It Like One

    Your Content Is a Knowledge Contribution — Score It Like One

    The Distillery
    — Brew № — · Distillery

    The same three variables that determine whether a knowledge contribution earns API tokens — novelty, specificity, and density — are the same three variables that determine whether a piece of content compounds or evaporates.

    This is not a coincidence. It is the same underlying problem: how do you measure whether a unit of information actually adds something to what already exists?

    Most content fails the test. Not because it is badly written, but because it does not clear the delta threshold. It confirms what readers already know, it gestures at specifics without landing them, and it spreads thin across a lot of words. By the metrics of a knowledge contribution scoring system, it would earn near-zero tokens. By the metrics of search and AI systems, it performs accordingly.

    Novelty: The Content Delta Problem

    In a knowledge token system, novelty is measured as the gap between what the knowledge base contained before a submission and what it contains after. The same logic applies to content. The question is not whether your article covers a topic — it is whether it moves the conversation forward on that topic.

    Most content on any given subject is paraphrase. Someone reads the top three ranking articles, recombines the information in a slightly different order, and publishes. The delta is near zero. The knowledge base — the collective of what is publicly known about this topic — does not change. Neither does the reader’s understanding.

    High-novelty content introduces a framework that did not exist before, surfaces a counterintuitive finding, documents a process that has never been written down, or names a pattern that practitioners recognize but no one has articulated. It changes what a reader knows, not just what they have read. That is the delta. That is what scores.

    Specificity: The Precision Test

    In the knowledge token system, specificity separates high-scoring from low-scoring contributions. A vague answer — “we usually handle it within a few days” — scores low. A precise answer with named processes, real numbers, and identified edge cases scores high.

    Content works the same way. “Restoration contractors should document damage thoroughly” is a zero-specificity statement. Every reader already knows this and leaves no smarter than they arrived. “Restoration contractors should photograph structural damage at minimum three angles — wide, mid, and close — and timestamp each image before touching anything, because public adjusters use photo metadata to establish pre-mitigation condition in supplement disputes” is a specific statement. It contains a named process, a reason, and a downstream consequence. A reader learns something they can act on.

    Specificity is also the primary differentiator between content that gets cited by AI systems and content that does not. Language models are not looking for topic coverage — they are looking for the most precise, actionable answer to a question. Vague content does not get cited. Specific content does. The knowledge token scoring model and the AI citation model are measuring the same thing.

    Density: Signal Per Word

    The third variable in knowledge contribution scoring is density — how much usable signal per word. A two-sentence answer that contains a genuinely novel, specific insight outscores a three-paragraph answer full of generalities.

    Most content has low density by design. The SEO paradigm of the last decade rewarded length, and writers learned to stretch. Introductory paragraphs that restate the headline. Transitions that summarize what was just said. Conclusions that recap the article. None of this adds signal. It adds word count.

    High-density content treats the reader’s attention as the scarce resource it is. Every sentence either introduces new information, sharpens a previous point, or provides a concrete example that makes an abstraction actionable. Nothing restates. Nothing pads. The piece ends when the information ends, not when a word count target is hit.

    This is increasingly what AI systems reward as well. Google’s helpful content guidance, AI Overview citation behavior, and Perplexity’s source selection all trend toward density over volume. The piece that says the most useful thing in the fewest words wins. Not the piece that covers the topic most thoroughly in the most words.

    Building Content Like a Knowledge Contributor

    If you applied knowledge contribution scoring to your content before publishing, what would change?

    The pre-publish question becomes: what does a reader know after finishing this that they did not know before? If the answer is “roughly the same things, expressed slightly differently,” the piece fails the novelty test and should not publish in its current form. If the answer is “they now understand specifically how X works, with a concrete example they can apply,” it passes.

    The editorial discipline this creates is uncomfortable. It eliminates a lot of content that feels productive to write. Topic coverage for its own sake. Articles that establish presence on a keyword without earning it through actual insight. Content that fills a calendar slot without filling a knowledge gap.

    What it produces instead is a smaller body of work with significantly higher per-piece value. Each article functions like a high-scoring contribution: it adds to the collective knowledge base in a measurable way, earns citations from AI systems that are looking for exactly this kind of precise, novel information, and compounds over time because it contains something that was not available before it was written.

    The Practical Application

    Before writing any piece, run it through the three-variable test:

    Novelty check: Search the topic. Read the top five results. Write down one thing your piece will contain that none of them do. If you cannot identify one thing, stop. You do not have a piece yet — you have a summary of existing pieces.

    Specificity check: Find every general statement in your outline and ask what the specific version of that statement is. “Contractors should document damage” becomes “contractors should document damage with timestamped photos from three angles before touching anything.” If you cannot make it specific, you do not know it specifically enough to write about it yet.

    Density check: After drafting, read every sentence and ask whether it adds new information or restates existing information. Delete everything that restates. If the piece collapses without the restatements, the underlying structure is held together by padding rather than by ideas.

    A piece that passes all three tests earns its place. It would score high in a knowledge token system. It will perform accordingly in search, in AI citation, and in the minds of readers who finish it knowing something they did not know before.

    That is the only metric that compounds.

  • The Knowledge Token Economy: Earning API Access Through What You Know

    The Knowledge Token Economy: Earning API Access Through What You Know

    The Distillery
    — Brew № — · Distillery

    What if access to an API wasn’t purchased — it was earned? Not through a subscription, not through a credit card, but through the value of what you know.

    That is the premise of the knowledge token economy: a system where people fill out forms, answer questionnaires, and complete structured interviews, and the depth and novelty of what they contribute determines how much API access they receive in return. Knowledge in, capability out.

    How the Contribution Loop Works

    The mechanic is straightforward. A person enters the system through a form — static, dynamic, or choose-your-own-adventure style. Their responses are ingested, scored against the existing knowledge base, and a token grant is issued proportional to the contribution’s value. Those tokens translate directly into API calls, rate limit increases, or access to higher-capability endpoints.

    The scoring event is the critical moment. It is not the act of submitting answers that generates tokens — it is the delta. The gap between what the system knew before the submission and what it knows after. A generic answer to a common question scores near zero. A 30-year restoration adjuster explaining exactly how Xactimate line items get disputed in hurricane-affected markets — that scores high. The system gets smarter; the contributor gets access.

    Form Types and Knowledge Depth

    Not all forms extract knowledge equally. The format determines the depth ceiling.

    Static forms establish baseline data: industry, credentials, years of experience, geography. They orient the system but rarely produce high-scoring contributions on their own. Their value is in establishing contributor identity and seeding the dynamic layer.

    Dynamic forms branch based on answers. When a contributor demonstrates domain knowledge in one area, the form follows them deeper into that area rather than moving on to the next generic question. A plumber who mentions slab leak detection gets routed into a sequence that extracts everything they know about that specific problem. Someone without that knowledge gets routed elsewhere. The form adapts to the contributor’s actual knowledge surface.

    Choose-your-own-adventure forms give contributors agency over which knowledge threads they follow. This produces the highest-quality contributions because people naturally move toward the areas where they have the most to say. It also produces the most honest signal — a contributor who keeps choosing the shallow path is telling you something about the limits of their expertise.

    The Grading Model

    Three variables determine a contribution’s score:

    Novelty. Does this add something the knowledge base does not already contain? A response that confirms existing knowledge scores low. A response that contradicts, nuances, or extends existing knowledge scores high. The system is not looking for agreement — it is looking for new signal.

    Specificity. Vague answers have low information density. Specific answers — with named processes, real numbers, identified edge cases, and concrete examples — have high information density. “We usually do it within a few days” scores low. “Florida public adjusters typically file the supplemental within 14 days of the initial estimate to stay inside the appraisal demand window” scores high.

    Density. How much usable signal per word? Long answers are not automatically high-scoring. A contributor who gives a two-sentence answer that contains a genuinely novel, specific insight outscores someone who writes three paragraphs of generalities. The system is measuring information content, not volume.

    Token Economics

    Tokens can be structured in multiple ways depending on what the API operator wants to incentivize.

    The simplest model maps tokens directly to API calls: one token, one call. A contributor who scores in the top tier earns enough tokens for meaningful API usage. A contributor who submits low-value responses earns modest access — enough to see the system work, not enough to build on it seriously.

    A tiered model unlocks capability rather than just volume. Low-score contributors get basic endpoint access. Mid-score contributors get higher rate limits and richer data. Top-score contributors get access to premium endpoints, bulk query capabilities, or priority processing. This creates a self-sorting system where domain experts naturally end up with the most powerful access.

    A reputation model layers on top of either approach. Each contributor builds a score over time. Early submissions carry full novelty weight. As a contributor’s personal knowledge surface gets exhausted — as the system learns everything they know about their specialty — their marginal contribution value decreases. This prevents gaming through repetition and rewards contributors who keep bringing genuinely new knowledge to the system.

    The Anti-Gaming Layer

    Any token economy will be gamed. People will submit the same high-scoring answer repeatedly, pattern-match to questions they have seen before, or collaborate to flood the system with synthetic responses. The anti-gaming architecture needs to be built in from the start, not retrofitted after the first abuse case.

    Novelty detection penalizes answers that match previous submissions semantically, not just literally. A reworded version of a prior high-scoring answer should score significantly lower. Contributor fingerprinting tracks the knowledge surface each individual has already covered and reduces scoring weight for re-covered ground. Anomaly detection flags contributors whose scoring patterns are statistically improbable — consistently perfect scores across unrelated domains are a signal worth investigating.

    The Strategic Frame

    What makes this model different from a survey with a gift card is the compounding dynamic. Each contribution makes the knowledge base more valuable, which makes the API more valuable, which increases the value of token access, which increases the incentive to contribute high-quality knowledge. The system gets smarter and more valuable over time through the contributions of the people who use it.

    The contributors who understand their own knowledge — who can articulate what they know specifically and precisely — end up with the most API access. The system rewards epistemic clarity. That is not a design quirk. It is the point.

  • The Knowledge Exchange Economy: What Businesses Can Trade for Expert Insights

    The Knowledge Exchange Economy: What Businesses Can Trade for Expert Insights

    The Distillery
    — Brew № — · Distillery

    Every business has a waiting room problem. Customers sit idle, phones in hand, burning time that nobody captures. The knowledge exchange model flips that equation: offer something tangible — a free oil change, a coffee, a service credit — in return for a structured voice interview with an AI. The conversation gets transcribed, processed, and converted into industry intelligence that compounds over time.

    This is not a survey. It is a transaction — one where both sides walk away with something real.

    The Businesses That Make This Work

    Not every venue is equal. The model performs best where three conditions align: captive time, domain knowledge, and a credible exchange offer.

    Automotive Dealerships and Service Centers

    A customer waiting 90 minutes for a service appointment on a $40,000 vehicle is one of the highest-value interview subjects available. The demographic skews toward homeowners, business operators, and tradespeople — people with active relationships with contractors, insurance companies, and service vendors. A free oil change ($40–$60 value) is a natural, frictionless exchange that fits the existing service relationship.

    The knowledge collected here is high-signal: home maintenance decisions, contractor vetting behavior, brand loyalty drivers, insurance claim experience. And because automotive service is habitual — the same customer returns every 3–6 months — topic rotation allows the same individual to be interviewed on entirely different subjects across visits without fatigue.

    Specialty Trade and Supply Shops

    A person browsing a plumbing supply house has already self-selected as a domain expert. You are not screening for knowledge — it arrives pre-filtered. The same applies to HVAC supply stores, electrical wholesalers, restoration equipment rental shops, and flooring distributors. The knowledge depth available in these environments is exceptional, and the foot traffic, while lower than consumer retail, is densely qualified.

    A discount on next purchase, a free product sample, or a referral credit aligns with the transactional context better than a gift card. The goal is to make the offer feel like a natural extension of the existing vendor relationship, not a detour from it.

    Contractor and Home Service Appointment Queues

    When a restoration contractor, HVAC technician, or roofing company sends a team out for an estimate, there is often a 15–30 minute window before the conversation starts. That window is currently dead time. A tablet-based voice interview with a homeowner — optional, in exchange for a service discount — turns dead time into structured knowledge.

    For restoration networks, this is the highest-priority deployment target. The homeowner knowledge collected here — property condition, vendor relationships, insurance claim navigation, decision-making around major repairs — directly feeds contractor content networks that produce compounding SEO value.

    Coffee Shops and Cafés

    The latte exchange is the cheapest attention buy available. A $6 drink buys 5–8 minutes from a broad demographic cross-section. The problem is variability. Without venue-specific targeting, knowledge quality is unpredictable. A café near a hospital skews toward healthcare workers. One near a job site skews toward tradespeople. Location selection is the quality filter. This model works best as a campaign sprint, not a permanent fixture.

    Waiting Rooms: Medical, Legal, Insurance, Government

    Captive time is abundant in institutional waiting rooms. The problem is emotional state. Someone waiting for a medical appointment or legal consultation is often stressed and guarded. This context produces experiential knowledge — how people navigate complex systems — but it is poorly suited to deep technical intelligence gathering. The exchange offer matters more here than anywhere else.

    The Diminishing Returns Problem

    Every knowledge exchange model eventually hits a ceiling. Three variables determine the return curve:

    Time cost versus knowledge depth. A 3-minute coffee shop interview produces surface awareness. A 15-minute dealership interview produces actionable depth. The exchange value must scale proportionally. The ask and the offer must be in the same weight class.

    Knowledge specificity versus content utility. General consumer sentiment is cheap to collect and cheap to use. Vertical expertise — how a 30-year HVAC technician thinks about refrigerant transitions, or how a jewelry appraiser evaluates estate pieces — is rare and highly monetizable. The exchange reward should reflect the scarcity of the knowledge, not just the time spent.

    Repeat exposure decay. The same person in the same context produces diminishing returns after one or two interviews. Topic rotation is the primary lever for extending the value of a returning interviewee. A homeowner interviewed about contractor relationships in spring can be interviewed about insurance claim history in fall. The person is the same; the knowledge surface is entirely different.

    The Autonomous Pipeline

    For the model to scale beyond a manual operation, the interview-to-content pipeline must run without human intervention at each step. A voice AI handles the interview on a tablet mounted at the venue, following a structured question protocol designed around the specific knowledge domain of that venue type. Transcription happens in real time. The transcript is routed to Claude, which extracts structured knowledge, formats it as a knowledge node, and pushes it to a content pipeline. High-value nodes get flagged for article production. Standard nodes are logged for future use.

    Consent is captured at interview start — a single tap-to-accept screen that clearly states the knowledge is being collected for content purposes. This covers legal exposure without creating friction that kills compliance rates.

    The Strategic Frame

    What makes this different from a survey or focus group is the output format. Traditional knowledge collection produces reports that sit on drives. This model produces structured, AI-ready knowledge nodes that slot directly into a content production pipeline. Every conversation becomes an asset. Every asset compounds.

    The goal is not to conduct interviews. The goal is to build a system where knowledge flows continuously from the people who have it to the platforms that need it — and everyone involved gets something real in return.

  • The Distillery: Hand-Crafted Batches of Distilled Knowledge, Available as API Feeds

    The Distillery: Hand-Crafted Batches of Distilled Knowledge, Available as API Feeds

    The Distillery — Brew № — · Distillery

    Most content on the internet is noise. It exists to rank, to fill space, to signal presence. It is not dense enough to be useful to the people who actually need to know the thing it claims to cover. And it is certainly not dense enough to be valuable as a feed that an AI system pulls from to answer real questions.

    The Distillery is different. It is a named section of Tygart Media where we produce small batches of genuinely high-density knowledge on specific topics — researched from real search demand data, written to a standard where every sentence earns its place, and published in structured form that both humans and AI systems can use.

    Each batch is available as a category API feed. Subscribers get authenticated access to the full batch as structured JSON — updated as new knowledge is added, versioned so auditors and AI systems can cite the exact vintage they’re drawing from.

    What a Batch Is

    A batch is a curated body of knowledge on a specific topic, built from three ingredients: real demand data (what people are actually searching for and what advertisers are paying to reach), primary research (direct engagement with the subject matter, not summarizing what others have written), and editorial discipline (the $5 filter — would someone pay $5 a month to pipe this feed into their AI? if not, it doesn’t ship).

    Each batch has a name, a number, and a version. Batch 001 is the Restoration Carbon Protocol — the only published Scope 3 emissions calculation standard for property restoration work. Batch 005 is the Restoration Industry Knowledge Base — a structured body of operational knowledge for restoration contractors who want to build AI-native systems without starting from scratch.

    Batches are not blog posts. They are not opinion columns. They are not rephrased Wikipedia entries. They are the kind of specific, accurate, hard-earned knowledge that takes real work to produce and that AI systems actively need but largely cannot find in their training data.

    How the API Works

    Every Distillery batch is accessible through the Tygart Content Network API. Subscribers receive an API key at signup. The key unlocks authenticated access to the batch endpoints they’ve subscribed to. Each endpoint returns structured JSON — articles by category, filterable by date and topic, with consistent metadata that AI agents can process directly.

    The response format is designed for machine consumption: clean plain text content, explicit categorization, publication timestamps for recency evaluation, and topic tags that allow agents to assess relevance before processing. The same feed that powers a human reader’s understanding of a topic powers an AI agent’s ability to answer questions about it accurately.

    Rate limits are generous at the $5 community tier — 100 requests per day, sufficient for an AI assistant pulling daily updates. Professional tiers at $50/month offer higher limits, webhook push when new content publishes, and bulk historical pulls for training and fine-tuning use cases.

    Why Information Density Is the Moat

    The content that survives in an AI-mediated information environment is the content that contains something worth extracting. Not something that sounds authoritative — something that actually is. The difference is information density: the ratio of useful, specific, actionable knowledge to total words published.

    Every Distillery batch is held to the same standard: if an AI system pulled from this feed to answer a question in this domain, would the answer be more accurate and more specific than if the AI had relied on its training data alone? If yes, the batch has value. If no, we haven’t done enough work yet.

    This standard is harder to meet than it sounds. It eliminates most of what gets published under the banner of “thought leadership” and “content marketing.” It requires knowing the subject well enough to say things that couldn’t be said by someone who spent an afternoon with a search engine. It is the reason The Distillery produces small batches rather than high volumes.

    Current Batches

    Batch 001 — Restoration Carbon Protocol (RCP)
    The only published Scope 3 ESG emissions calculation standard for property restoration work. Covers all five core restoration job types with actual emission factor tables, complete worked examples, and the 12-point data capture standard. Designed for restoration contractors serving commercial clients with 2027 SB 253 Scope 3 reporting obligations. 23 articles. Updated monthly.

    Batch 002 — The Knowledge Economy API Layer
    The conceptual and practical framework for turning human expertise into machine-consumable, API-distributable knowledge products. For anyone with domain expertise considering how to package and monetize it in an AI-native information environment. 8 articles. Updated as the landscape develops.

    Batch 003 — Mason County Minute
    Current, structured, consistently maintained coverage of Mason County, Washington — local government, business, community, real estate, and public affairs. The only machine-readable hyperlocal intelligence feed for this geography. Updated weekly.

    Batch 004 — Belfair Bugle
    Hyperlocal coverage of Belfair, WA and the North Mason community. Current events, local government, community intelligence. The only structured feed for this geography. Updated weekly.

    Batch 005 — Restoration Industry Knowledge Base (coming)
    Operational knowledge infrastructure for restoration contractors — the 50 knowledge nodes every restoration company should have documented, the AI-native knowledge architecture that replaces manual training, and the integration patterns connecting job management systems to knowledge delivery. In development.

    Batch 006 — AI Agency Playbook (coming)
    The operating methodology behind Tygart Media — how a single operator runs 27+ client sites, deploys AI-native content at scale, and builds knowledge infrastructure rather than content volume. For agency owners and solo operators building AI-native practices. In development.

    Who This Is For

    The Distillery API is for three kinds of subscribers:

    Developers building AI tools who need reliable, current, domain-specific knowledge feeds to ground their applications in accurate information. The Restoration Carbon Protocol feed, for example, gives any AI assistant building tool accurate restoration-specific ESG data without the developer having to research and curate it themselves.

    Businesses who want AI systems that actually know their industry. A restoration company whose AI assistant draws from the RCP feed knows more about Scope 3 emissions calculation for their job types than any general-purpose AI. A commercial property manager whose AI assistant pulls from the RCP feed can answer contractor ESG questions accurately instead of hallucinating plausible-sounding nonsense.

    Content teams and agencies who want structured, current, reliable source material for their own content production — not to copy, but to ensure accuracy and specificity in their coverage of these domains.

    The Standard We Hold Ourselves To

    Every article in every batch passes one test before it ships: would someone pay $5 a month to pipe this feed into their AI? Not to read it themselves — to have their AI draw from it continuously as a trusted source in this domain.

    If the answer is no — if the content is too generic, too thin, or too derivative to justify a subscription — it doesn’t ship. The batch waits until the knowledge is actually there.

    This makes The Distillery slow. It makes it small. And it makes it worth subscribing to.

  • RCP Proxy Estimation Guide: How to Calculate When Primary Data Is Missing

    RCP Proxy Estimation Guide: How to Calculate When Primary Data Is Missing

    The Agency Playbook
    TYGART MEDIA · PRACTITIONER SERIES
    Will Tygart
    · Senior Advisory
    · Operator-grade intelligence

    The RCP requires 12 data points per job. In practice, some of those data points will be unavailable — particularly for historical jobs being calculated retrospectively, or for field situations where documentation wasn’t captured as completely as the standard requires. The proxy estimation methodology provides documented substitution methods that produce defensible, auditor-acceptable estimates when primary data is missing.

    Key principle: A documented estimate with a stated assumption is always preferable to a blank field in an RCP report. ESG auditors understand that emissions calculation involves uncertainty — what they require is transparency about where estimation was used and what the basis of that estimation was. Undocumented guesses are not acceptable. Documented proxies are.

    Data Quality Tiers

    The RCP uses three data quality tiers, consistent with GHG Protocol Scope 3 guidance:

    Tier Description Audit Acceptability
    Tier 1 — Primary measured data Actual measurements from job records: GPS mileage, disposal facility receipts with weights, materials purchase orders by job Highest — preferred for all data points
    Tier 2 — Primary estimated data Calculated from documented job parameters using RCP proxy methods: affected area × consumption rate, crew size × duration × unit rate Acceptable — must document calculation method and basis
    Tier 3 — Spend-based / invoice-based proxy Dollar amount × industry average emission factor — the fallback of last resort Lowest — use only when no job-specific data is available; flag prominently in data quality notes

    Proxy Methods by Data Point

    Data Point 1 — Vehicle Mileage (Transportation)

    Primary source: GPS fleet tracking data, dispatch records, driver logs.

    Proxy method: Use Google Maps or equivalent mapping tool to calculate round-trip distance from your facility (or prior job address for multi-stop days) to the job site. Multiply by the number of crew trips documented in time records or invoices. This is a Tier 2 estimate.

    Default proxy (Tier 3, last resort): Industry average mobilization distance for restoration contractors is 22 miles one-way (44 miles round trip). Apply this default only when no address or routing information is available. Note as Tier 3 estimate in data quality section.

    Data Point 2 — Waste Transport Mileage

    Primary source: Waste manifests and hauler receipts (these typically include origin and destination).

    Proxy method: Use the distance from the job site to the nearest licensed disposal facility of the appropriate type (standard C&D landfill, licensed ACM facility, medical waste facility). Use online waste facility directories (EPA RCRA Info for hazmat, state environmental agency databases for C&D landfills) to identify the nearest appropriate facility.

    Default proxies by facility type (Tier 3): Standard C&D landfill: 18 miles. Licensed ACM facility: 60 miles. Licensed PCB incineration: 150 miles. Medical waste facility: 55 miles.

    Data Point 3 — Equipment Power Source

    Primary source: Job documentation noting whether equipment ran on building power or contractor generator; generator fuel logs.

    Proxy method: Default assumption is building electrical supply unless your company policy or the job type (remote location, building power unavailable) indicates otherwise. Note the assumption explicitly. If generator use is suspected but not documented, use the following generator fuel proxy: standard drying equipment setup (3 dehumidifiers + 6 air movers) consuming approximately 2.5 gallons of diesel per 8-hour shift × number of drying days × 10.21 kg CO2e per gallon diesel.

    Data Points 4–5 — Chemical Treatments and PPE Consumption

    Application rate proxies by job type and surface type:

    Job Type / Surface Antimicrobial Rate Tyvek Suits per Tech per Day Glove Pairs per Tech per Day N95/P100 per Tech per Day
    Cat 1 water — porous surfaces 0.008 L/sq ft 0.5 2 0.5
    Cat 2 water — porous surfaces 0.015 L/sq ft 1.0 3 1.0
    Cat 3 water — porous surfaces 0.025 L/sq ft (×2 applications) 2.0 5 2.0
    Mold Condition 3 — first application 0.020 L/sq ft 2.0 4 1.5
    Mold Condition 3 — second application 0.015 L/sq ft 2.0 4 1.5
    Fire — smoke cleaning (chemical sponge + cleaner) 1 sponge per 50 sq ft + 0.010 L/sq ft cleaner 1.5 4 1.5
    Hazmat abatement (Level C, standard exit protocol) N/A (wetting agent: 0.003 L/sq ft ACM) 3.0 (full replacement each exit) 6 2 pairs OV/P100
    Biohazard Level C 0.025 L/sq ft × 2 applications 3.0 (full replacement each exit) 6 2 pairs OV/P100
    Biohazard Level B (decomposition) 0.025 L/sq ft × 2 applications 3.0 Level B full-suit (replace each exit) 6 Supplied air — 0 disposable

    Data Point 6 — Containment Materials

    Proxy method: Standard containment for a single affected room (standard ceiling height 8–10 ft): perimeter of affected area (linear feet) × ceiling height × 1.2 (overlap factor) = m² of poly sheeting. For compartmentalized commercial spaces, add 20 m² per additional doorway or penetration point.

    Zipper doors: 1 per entry/exit point, typically 2 per contained area (entry + equipment pass-through).

    Data Points 7–8 — Waste Volume and Disposal

    Volume proxy: Use weight estimation proxies from the RCP Emission Factor Reference Table (drywall at 2.5 lbs/sq ft, carpet at 3.0 lbs/sq ft, etc.) applied to the demolished area documented in job scope records.

    Disposal method proxy: If disposal facility type is unknown, apply default based on material type: standard C&D for non-contaminated demolition debris, regulated C&D or hazmat for contaminated materials (see Table 3 in the Emission Factor Reference).

    Data Points 9–10 — Demolished and Installed Materials

    Proxy method: Calculate from demolition scope records (affected area by room, material type documented in scope of work or Xactimate/Symbility estimate). Weight estimation proxies apply as above. For installed materials in reconstruction phase, use square footage from scope-of-work documentation and apply standard weight proxies.

    Documenting Proxy Use in Your RCP Report

    Every proxy estimate must be documented in the data quality section of the per-job carbon report. The format for documenting a proxy is: [Data point name]: [Tier 2 or 3 estimate]. [Brief description of proxy method]. [Source of proxy rate or assumption].

    Example: “Vehicle mileage: Tier 2 estimate. Round-trip distance calculated using Google Maps from company facility to job site address (44 miles RT × 4 crew trips). Crew trip count from job invoices. Source: RCP proxy method P-4-1.”

    Example: “PPE consumption: Tier 2 estimate. Cat 3 water damage standard consumption rate applied (2.0 Tyvek/tech/day, 5 glove pairs/tech/day) per RCP Table A-5. Actual PPE not tracked separately on this job.”

    Can a per-job carbon report with all Tier 2 estimates be used in GRESB reporting?

    Yes. GRESB accepts primary data at various quality levels, including documented estimates. A Tier 2 estimate is primary data (not spend-based estimation) and is acceptable. The data quality notation in the RCP report demonstrates that you have applied documented methodology rather than guessing, which is what auditors need to see.

    What is the margin of error typical for Tier 2 proxy estimates?

    Typical uncertainty range for Tier 2 RCP estimates is ±20–35% relative to primary measured data. This compares favorably to spend-based estimation (Tier 3), which typically has ±50–100% uncertainty for restoration work due to the high variability of job type, scope, and emission profile at equivalent invoice amounts.

    Should you disclose the uncertainty range in the per-job carbon report?

    The RCP does not require quantified uncertainty ranges in the per-job report, but noting that Tier 2 estimates were used in the data quality section effectively communicates to auditors that the figure carries inherent estimation uncertainty. For clients whose ESG consultants or auditors specifically request uncertainty ranges, use the guidance values above (±20–35% for Tier 2).


  • RCP Emission Factor Reference Table: All Values in One Place

    RCP Emission Factor Reference Table: All Values in One Place

    The Agency Playbook
    TYGART MEDIA · PRACTITIONER SERIES
    Will Tygart
    · Senior Advisory
    · Operator-grade intelligence

    This reference table consolidates all emission factors used in Restoration Carbon Protocol calculations. It is the lookup document you use when completing a per-job carbon report — every factor needed for Categories 1, 4, 5, and 12 across all five job types is in this table, with source citations for audit purposes.

    Version: RCP v1.0 | Factor vintage: EPA 2024, DEFRA 2024, EPA WARM v16 | Units: All values in kg CO2e unless noted as tCO2e

    Table 1: Category 4 — Vehicle Transportation

    Vehicle Type Fuel kg CO2e per mile Source
    Passenger car Gasoline 0.355 EPA Table 2, Mobile Combustion 2024
    Light-duty truck / work van (under 8,500 lbs GVWR) Gasoline 0.503 EPA Table 2, Mobile Combustion 2024
    Light-duty truck / cargo van Diesel 0.523 EPA Table 2, Mobile Combustion 2024
    Medium-duty truck / equipment trailer (8,500–26,000 lbs GVWR) Diesel 1.084 EPA Table 2, Mobile Combustion 2024
    Heavy-duty truck — unloaded (26,000+ lbs GVWR) Diesel 1.612 EPA Table 2, Mobile Combustion 2024
    Heavy-duty truck — loaded (waste hauling, C&D) Diesel 2.25 EPA Table 2 + load factor adjustment
    Licensed hazmat waste hauler (ACM, lead, general hazmat) Diesel 3.20 EPA Table 2 + hazmat vehicle premium
    Licensed hazmat hauler (PCB, high-hazard specialty) Diesel 3.80 EPA Table 2 + specialty vehicle premium
    Medical waste hauler (biohazard) Diesel 2.80 EPA Table 2 + medical waste vehicle
    Pack-out truck (contents restoration) — loaded Diesel 2.25 EPA Table 2 + load factor
    Pack-out truck — empty (return trip) Diesel 1.612 EPA Table 2 — unloaded heavy

    Table 2: Category 1 — Materials

    Chemical Treatments

    Material Unit kg CO2e per unit Source
    Quaternary ammonium antimicrobial / biocide (liquid) Liter 2.8 EPA EEIO — Chemical manufacturing sector
    Hydrogen peroxide-based antimicrobial/biocide Liter 1.9 EPA EEIO — Chemical manufacturing sector
    Borax-based mold treatment kg 1.1 EPA EEIO — Inorganic chemical manufacturing
    Hospital-grade disinfectant (EPA-registered) Liter 2.8 EPA EEIO — Chemical manufacturing sector
    Enzyme biological digester / deodorizer Liter 1.6 EPA EEIO — Specialty chemical manufacturing
    Encapsulant / smoke-blocking primer Gallon 4.2 EPA EEIO — Paint and coatings manufacturing
    Thermal fogging agent Liter 2.1 EPA EEIO — Chemical manufacturing sector
    Desiccant drying agent (silica gel) kg 1.4 EPA EEIO — Chemical manufacturing sector
    Wetting agent / amended water (surfactant for ACM) Liter 1.4 EPA EEIO — Chemical manufacturing sector
    Dry ice (CO2 pellets for blast cleaning) kg 0.85 EPA EEIO — Industrial gas manufacturing

    Personal Protective Equipment

    PPE Item Unit kg CO2e per unit Source
    Disposable Tyvek suit (Level C) Each 1.2 EPA EEIO — Apparel manufacturing
    Level B full encapsulating suit Each 3.0 EPA EEIO — Apparel/specialty manufacturing
    Level C PPE full kit (Tyvek + gloves + goggles + boot covers) Kit 1.8 Composite of individual items
    Level B PPE full kit (encapsulating suit + supplied air + gloves) Kit 4.2 Composite of individual items
    Nitrile gloves (pair) Pair 0.3 EPA EEIO — Rubber and plastics manufacturing
    N95 respirator (disposable) Each 0.4 EPA EEIO — Medical equipment manufacturing
    Half-face respirator, P100 cartridges (pair) Pair 0.8 EPA EEIO — Medical equipment manufacturing
    Full-face respirator cartridges (pair) Pair 1.2 EPA EEIO — Medical equipment manufacturing
    Boot covers (pair) Pair 0.15 EPA EEIO — Rubber and plastics

    Containment and Filtration

    Material Unit kg CO2e per unit Source
    6-mil polyethylene sheeting 0.55 EPA EEIO — Plastics product manufacturing
    4-mil polyethylene sheeting 0.37 EPA EEIO — Plastics product manufacturing
    Double-layer 6-mil containment (hazmat/biohazard) 1.10 2× single-layer factor
    Zipper door — disposable Each 1.8 EPA EEIO — Plastics/hardware
    Zipper door — reusable (amortized over 20 uses) Use 0.09 1.8 ÷ 20 uses
    HEPA filter — air scrubber (standard) Each 3.2 EPA EEIO — Industrial machinery manufacturing
    HEPA vacuum bag (commercial grade) Each 0.4 EPA EEIO — Paper/plastics manufacturing
    Biohazard bag — 33-gallon red (medical waste) Each 0.65 EPA EEIO — Medical plastics manufacturing
    ACM disposal bag — 6-mil labeled (33-gallon) Each 0.55 EPA EEIO — Plastics product manufacturing
    Sharps disposal container (1-gallon) Each 0.35 EPA EEIO — Plastics/medical equipment
    Glove bag (pipe insulation removal) Each 0.85 EPA EEIO — Plastics product manufacturing

    Table 3: Category 5 — Waste Disposal

    Waste Type Disposal Method tCO2e per ton Source
    Standard C&D debris (non-hazardous mixed) Landfill 0.16 EPA WARM v16
    Cat 2 water-contaminated porous materials Standard landfill 0.18 EPA WARM + contamination premium
    Cat 3 sewage-contaminated materials Regulated C&D landfill 0.22 EPA WARM + regulated disposal
    Smoke-contaminated C&D debris (standard) Standard landfill 0.16 EPA WARM v16
    Smoke-contaminated C&D (regulated facility) Licensed C&D landfill 0.20 EPA WARM + transport premium
    Mold-contaminated porous materials Standard landfill (most jurisdictions) 0.18 EPA WARM + contamination premium
    Friable ACM (pipe insulation, spray fireproofing) Licensed hazmat landfill 0.42 EPA WARM + licensed facility + transport
    Non-friable ACM (floor tiles, roofing, joint compound) Licensed C&D with ACM cell 0.28 EPA WARM + regulated C&D transport
    Lead paint debris (TCLP-classified hazardous) Licensed hazmat landfill 0.38 EPA WARM + hazmat transport
    PCB-containing materials ≥50 ppm Licensed PCB incineration 1.85 EPA hazardous waste incineration factors
    PCB-containing materials <50 ppm Licensed landfill 0.22 EPA WARM + transport premium
    Mercury-containing lamps/thermostats Mercury recycler 0.15 EPA WARM — recycling credit offset
    Regulated medical/biohazard waste (standard) Autoclave + licensed landfill 0.55 EPA medical waste treatment factors
    High-pathogen biohazard waste High-temperature incineration 0.85 EPA hazardous waste incineration factors
    Sharps waste Sharps autoclave or incineration 0.65 EPA medical waste — sharps category
    Contaminated water (Cat 3, to wastewater treatment) Municipal wastewater treatment 0.000272 per liter EPA WARM v16 — wastewater treatment
    Disposable PPE — standard Standard landfill 0.25 EPA WARM — mixed plastics
    Disposable PPE — hazmat-contaminated Licensed hazmat or medical waste landfill 0.30–0.55 Apply appropriate hazmat or medical waste factor

    Table 4: Category 12 — Demolished Building Materials

    Material tCO2e per ton (landfill) tCO2e per ton (recycled) Source
    Gypsum drywall (1/2″) 0.16 0.02 EPA WARM v16
    Dimensional lumber / wood framing -0.07 -0.15 EPA WARM v16 — carbon storage credit
    OSB sheathing -0.05 -0.12 EPA WARM v16 — carbon storage credit
    Carpet + pad (standard residential/commercial) 0.33 0.05 EPA WARM v16
    Hardwood flooring -0.12 -0.18 EPA WARM v16 — carbon storage credit
    Vinyl / LVP flooring 0.28 0.08 EPA WARM v16 — plastics category
    Ceramic / porcelain tile 0.04 0.01 EPA WARM v16 — inert material
    Fiberglass batt insulation 0.33 0.05 EPA WARM v16
    Cellulose insulation (spray or loose-fill) 0.06 -0.02 EPA WARM v16
    Spray polyurethane foam insulation (SPF) 0.72 N/A EPA WARM v16 — plastics category
    Acoustic ceiling tiles (standard) 0.12 0.03 EPA WARM v16 — ceiling tile category
    Structural steel (demolished) -0.85 -0.95 EPA WARM v16 — steel recycling credit
    Copper pipe / wiring -0.45 -0.60 EPA WARM v16 — copper recycling credit
    Aluminum (ductwork, framing) -1.20 -1.45 EPA WARM v16 — aluminum recycling credit (high value)

    Weight Estimation Proxies

    When disposal receipts are not available, use these weight proxies to estimate demolished material tonnage:

    Material Weight per sq ft (installed, dry) Notes
    1/2″ gypsum drywall 2.5 lbs Use dry weight, not post-water-damage wet weight
    5/8″ gypsum drywall (Type X) 3.1 lbs Common in commercial construction
    Carpet + pad (residential) 3.0 lbs Including pad and tack strips
    Carpet + pad (commercial, glue-down) 2.2 lbs Heavier carpet, no pad
    LVP / vinyl plank flooring 2.8 lbs Including underlayment
    Ceramic tile (floor, 3/8″) 4.5 lbs Including thin-set mortar
    Acoustic ceiling tiles (2’×2′ standard) 1.8 lbs Mineral fiber type
    Fiberglass batt insulation (3.5″ R-13) 0.5 lbs Per sq ft of coverage area
    Dimensional lumber 2×4 wall framing (per linear foot of wall) 4.0 lbs Assumes 16″ OC framing in 8-ft walls
    Non-friable ACM floor tile (9″×9″) 4.0 lbs Including mastic adhesive

    How often will this reference table be updated?

    The RCP emission factor reference table will be updated annually following the release of updated EPA WARM, EPA Mobile Combustion, and DEFRA databases. Version numbers are included in the table header — always cite the version used in your per-job carbon report data quality notes.

    What if I need an emission factor for a material not in this table?

    First check EPA WARM v16 directly (available free at epa.gov/warm). Second, check the EPA EEIO database for the relevant industry sector. Third, check DEFRA’s Conversion Factors for Company Reporting. If none of these sources contain the specific material, use the closest proxy category and document the substitution in your data quality notes.

    Are these factors suitable for use in EU CSRD reporting?

    EPA and EPA WARM factors are US-specific but are accepted in most international ESG frameworks when accompanied by clear source citation. For EU CSRD reporting specifically, DEFRA factors (UK) or OECD emission factors may be preferred by auditors for non-US operations. The RCP will publish a DEFRA-specific factor table in a future supplement for EU-applicable reporting contexts.


    Table 6: Refrigerant GWP Values — IPCC AR6 Update

    The Global Warming Potential values for refrigerants used in restoration drying equipment have been updated under IPCC Sixth Assessment Report (AR6, 2021). AR6 GWP-100 values are 14–18% higher than AR5 for the HFCs commonly found in LGR dehumidifiers. RCP v1.0 uses AR6 values for refrigerant-related calculations. The EPA AIM Act continues to use AR4 values for regulatory compliance; UNFCCC/Paris reporting uses AR5. When delivering data to clients, disclose which GWP vintage was used.

    Refrigerant Common use in restoration AR5 GWP-100 AR6 GWP-100 Change
    R-410A (HFC-32/125 blend) Most current LGR dehumidifiers ~1,924 ~2,256 +17.3%
    R-32 (HFC-32) Dri-Eaz LGR 6000i; newer units 677 771 +13.9%
    R-454B (HFC-32/HFO-1234yf blend) Next-gen low-GWP units ~467 ~530 +13.5%
    HFC-134a (R-134a) Older residential dehumidifiers 1,300 1,530 +17.7%

    Source: IPCC AR6 WG1, Chapter 7, Table 7.SM.7 (2021). EPA Technology Transitions GWP Reference Table.


    Table 7: EPA eGRID 2023 — Subregional Emission Factors for Major Restoration Markets

    The national average grid factor (0.3497 kg CO₂e/kWh, eGRID 2023) used as the RCP default understates or overstates electricity emissions significantly depending on where equipment is operated. Using location-specific subregion factors improves data quality for clients in GRESB, SBTi, and CSRD reporting contexts.

    Use the subregion factor for the state/metro where the job was performed, not where the contractor’s facility is located.

    eGRID Subregion Primary coverage kg CO₂e/kWh vs. RCP default (0.3499)
    NYUP Upstate New York 0.1101 -68.5%
    CAMX California / Western US 0.1950 -44.3%
    NEWE New England 0.2464 -29.6%
    ERCT Texas (ERCOT) 0.3341 -4.5%
    US Average National default (RCP v1.0) 0.3497 Baseline
    FRCC Florida 0.3560 +1.7%
    SRSO Southeast (excluding FL) 0.3837 +9.7%
    NYCW NYC and Westchester 0.3927 +12.2%

    Source: EPA eGRID2023 Summary Tables Rev 2 (published March 2025). Full subregion table available at epa.gov/egrid. A California restoration contractor using the national average overstates electricity emissions by 44%; a Florida contractor understates by 1.7%. The difference is largest for multi-week jobs with sustained equipment energy consumption.


    Table 8: PPE and Consumables — LCA-Sourced Per-Unit Emission Factors

    The EPA EEIO proxies in Table 2 are sector-level estimates. The following values are sourced from published lifecycle assessments and Environmental Product Declarations for specific product types. Use these in place of the EEIO values where the product type matches.

    Item Unit kg CO₂e Source vs. EEIO proxy
    Nitrile glove (3.5g, size M) Each 0.0277 Top Glove LCA 2024, SATRA-verified -82% vs. EEIO pair proxy
    Nitrile glove pair Pair 0.0554 Top Glove LCA 2024 -82% vs. current 0.3 EEIO
    N95 respirator (disposable) Each 0.05 Springer Env. Chem. Letters 2022 -88% vs. current 0.4 EEIO
    DuPont Tyvek 400 coverall (180g HDPE) Each 0.40–0.63 Estimated: 180g × 2.2–3.5 kg CO₂e/kg HDPE -47–65% vs. current 1.2 EEIO
    LVP/LVT flooring (Shaw EcoWorx) 5.2 Shaw Contract EcoWorx Resilient EPD 2023 Consistent with WARM v16 plastics
    Ceramic tile (standard) kg 0.78 ICE Database v3.0 (University of Bath) More granular than WARM v16 inert
    Ready-mix concrete (30 MPa) kg 0.13 ICE Database v3.0 132 kg CO₂e/m³
    Polyethylene LDPE sheeting kg 1.793 DEFRA 2024 (closed-loop recycling scenario) Use as proxy for virgin LDPE sheeting
    H₂O₂ antimicrobial (active ingredient) kg active 1.33 ACS Omega 2025 (anthraquinone process) Lower than EEIO chemical proxy

    Note on Tyvek: DuPont has not published an independent lifecycle assessment for standard Tyvek 400 coveralls. The value above is estimated from HDPE production emission factors. DuPont has commissioned an LCA for Tyvek 500 Xpert BioCircle (a recycled-content variant) claiming 58% reduction versus standard Tyvek, which implies a quantified baseline exists internally. The RCP will update this value if DuPont publishes the underlying LCA data.

    Note on nylon carpet (DEFRA 2024): The DEFRA 2024 value of 5.40 kg CO₂e/kg for nylon carpet should be verified against the actual DEFRA 2024 full spreadsheet to confirm whether this represents virgin nylon production or a closed-loop recycling scenario. DEFRA 2024 uses AR5 GWP values throughout.


    Factor Vintage and GWP Basis: Version Disclosure

    RCP v1.0 uses the following factor vintages:

    • Electricity: EPA eGRID 2023 (published March 2025)
    • Mobile combustion / vehicle fuels: EPA 2025 Emission Factors Hub
    • Waste disposal: EPA WARM v16
    • Refrigerant GWPs: IPCC AR6 (2021)
    • Materials (non-EEIO): ICE Database v3.0, EPD-sourced, DEFRA 2024
    • Materials (EEIO proxy): EPA USEEIO v2.0
    • GWP basis: AR6 GWP-100 for refrigerants; AR5 GWP-100 for all other gases (consistent with EPA GHG Inventory basis)

    When factors are updated in patch releases, the factor vintage table updates accordingly. All RCP Job Carbon Reports should reference the schema_version field (RCP-JCR-1.0) which implicitly references the factor table version used at calculation time. For year-over-year comparisons, use the same factor vintage across both years unless a major correction justifies restating prior-year figures.