Blog

  • How to Track When ChatGPT or Perplexity Cites Your Content

    How to Track When ChatGPT or Perplexity Cites Your Content

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

    ChatGPT cited a competitor’s blog post instead of yours. Perplexity summarized the wrong article. An AI answer engine described your service category without mentioning you. You’d like to know when this happens — and whether it’s improving over time.

    The problem: no one has built a clean, turnkey tool for this yet. Here’s what actually exists, what we’ve pieced together, and what a real tracking setup looks like.

    Why This Is Hard

    Web search citation tracking is solved: rank trackers like Ahrefs and SEMrush show you who’s linking to what. AI citation tracking has no equivalent infrastructure. Here’s why:

    • Non-deterministic outputs: Ask ChatGPT the same question twice; you may get different sources cited, or no sources at all. There’s no persistent ranking to track.
    • No public citation index: Google’s index is crawlable. There’s no equivalent for “content that AI systems have cited in responses.” You can’t pull a report.
    • Variable source disclosure: Perplexity shows sources. ChatGPT’s web-enabled mode shows sources sometimes. Gemini shows sources. Claude generally doesn’t show sources in the same way. Tracking works where sources are disclosed; it breaks where they aren’t.
    • Query sensitivity: Your content might get cited for one phrasing and completely missed for a near-synonym. There’s no search volume data to tell you which phrasings matter.

    What Actually Exists Today

    Manual Query Sampling

    The only fully reliable method: run queries yourself and check the sources cited. For a content monitoring program this might look like:

    • Define 20–50 queries where you want to appear (covering your core topics)
    • Run each query in Perplexity, ChatGPT (web-enabled), and Gemini weekly or biweekly
    • Log whether your domain appears in cited sources
    • Track citation rate (appearances / total queries run) over time

    This is tedious but gives you ground truth. It’s what a real monitoring program looks like before you automate it.

    Perplexity Source Tracking

    Perplexity consistently displays its sources, making it the most tractable platform for systematic citation tracking. A simple automated approach:

    • Use Perplexity’s API to query your target questions programmatically
    • Parse the citations field in the response
    • Check whether your domain appears
    • Log and aggregate over time

    Perplexity’s API is available with a subscription. The citations field returns the URLs Perplexity used to generate its answer. You can run this as a scheduled Cloud Run job and dump results to BigQuery for trend analysis.

    ChatGPT Web Search Mode

    When ChatGPT uses web search (either via the browsing tool or search-enabled API), it returns source citations. The search-enabled ChatGPT API (available with OpenAI API access) gives you programmatic access to these citations. Same approach: define queries, run them, parse citations, track your domain.

    Limitation: not all ChatGPT responses use web search. For queries it answers from training data, no source is cited and you have no visibility into whether your content influenced the answer.

    Google AI Overviews

    Google AI Overviews (formerly SGE) shows cited sources inline in search results. You can track these through Google Search Console for your own content — if Google’s AI Overview cites your page, that page gets an impression and potentially a click recorded in GSC under that query. This is the only AI citation signal with first-party tracking infrastructure.

    Emerging Tools

    As of April 2026, several tools are building toward AI citation tracking as a category: mention monitoring services that have added AI search coverage, SEO platforms adding “AI visibility” metrics, and purpose-built tools targeting this specific problem. The category is forming but not mature. Verify current capabilities — this space has changed significantly in the past six months.

    What a Real Monitoring Setup Looks Like

    Here’s the practical stack we’ve assembled for tracking citation presence across AI platforms:

    1. Define your query set: 30–50 queries across your core topic clusters. Weight toward queries where you have existing content and where you’re trying to establish authority.
    2. Perplexity API integration: Scheduled weekly run. Parse citations. Log domain appearances to a tracking spreadsheet or BigQuery table.
    3. ChatGPT web search sampling: Less systematic — manual sampling weekly for highest-priority queries. The API approach works but requires more engineering to handle variability in when web search activates.
    4. Google Search Console: Monitor AI Overview impressions. This is your strongest signal because it’s Google’s own data, not sampled queries.
    5. Baseline and trend: After 4–6 weeks of tracking, you have a baseline citation rate. Changes correlate (imperfectly) with content quality improvements, new publications, and competitor activity.

    What Citation Rate Actually Tells You

    Citation rate — your domain appearances divided by total queries sampled — is a proxy metric, not a direct ranking signal. What drives it:

    • Content freshness: AI systems prefer recently indexed, recently updated content for queries about current information
    • Structural clarity: Content with explicit Q&A structure, defined terms, and direct factual claims gets cited more reliably than narrative content
    • Domain authority signals: The same signals that help SEO rankings help AI citation rates — but the weighting may differ by platform
    • Entity specificity: Content that clearly establishes your brand as an entity with defined characteristics gets cited more consistently than generic content

    For the content optimization angle: AI Citation Monitoring Guide. For the broader GEO picture: What Managed Agents means for content visibility.

    For the hosted agent infrastructure context: Claude Managed Agents Pricing Reference — how the billing works for agents that could automate citation monitoring workflows.

  • The Real Monthly Cost of Running Claude Managed Agents 24/7

    The Real Monthly Cost of Running Claude Managed Agents 24/7

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

    If you’re considering running Claude Managed Agents around the clock, you want a number. Not “it depends.” An actual number you can put in a budget. Here’s the math, worked out by scenario, with the honest caveats about where the real costs are.

    The Formula

    Total monthly cost = (Active session hours × $0.08) + token costs + optional tool costs

    The $0.08/session-hour charge only applies during active execution. Idle time — waiting for input, tool confirmations, external API responses — doesn’t count. This matters significantly for 24/7 workloads, because very few agents are active 100% of the time even when “running around the clock.”

    The Maximum Theoretical Cost

    Scenario: Agent running continuously, zero idle time, 24 hours a day, 30 days a month.

    • Session runtime: 24 hrs × $0.08 × 30 days = $57.60/month
    • Token costs: separate, highly variable (see below)

    $57.60/month is the ceiling on session runtime charges. You cannot pay more than this in session fees under any 24/7 scenario. But here’s the reality: that ceiling assumes zero idle time across the entire month, which doesn’t describe any real production agent.

    Realistic 24/7 Scenarios

    Monitoring Agent (High Idle Ratio)

    Runs continuously watching for triggers — error alerts, specific data patterns, incoming requests. Activates on trigger, processes, returns to monitoring state.

    • Assumption: 5% active execution time (watching 95% of the time, executing 5%)
    • Active hours: 24 × 30 × 0.05 = 36 hours/month
    • Session runtime: 36 × $0.08 = $2.88/month
    • Token costs: low — moderate bursts on trigger events
    • Realistic total: $5–15/month

    Customer Support Agent (Business Hours Active)

    “24/7” in the sense of always-available, but actual request volume concentrates in business hours. Waits for tickets, processes them, waits again.

    • Assumption: 8 hours/day active execution, 16 hours waiting
    • Active hours: 8 × 30 = 240 hours/month
    • Session runtime: 240 × $0.08 = $19.20/month
    • Token costs: depends heavily on ticket volume and average length
    • At 100 tickets/day with moderate length: likely $30–80/month in tokens
    • Realistic total: $50–100/month

    Continuous Autonomous Pipeline

    Batch processing agent that runs continuously through a queue with minimal waiting — the closest to true 24/7 active execution.

    • Assumption: 20 hours/day truly active (4 hours queue exhaustion/maintenance)
    • Active hours: 20 × 30 = 600 hours/month
    • Session runtime: 600 × $0.08 = $48/month
    • Token costs: high — continuous processing means continuous token consumption
    • This is where tokens become the dominant cost driver by a significant margin
    • Realistic total: $200–500+/month (tokens dominate)

    The Real Variable: Token Costs

    For any 24/7 workload that’s genuinely busy, token costs will substantially exceed session runtime costs. The math:

    A moderately active agent processing 10,000 input tokens and 2,000 output tokens per hour with Claude Sonnet 4.6:

    • Input: 10,000 tokens × $3/million = $0.03/hour
    • Output: 2,000 tokens × $15/million = $0.03/hour
    • Token cost: $0.06/hour vs. session runtime of $0.08/hour — roughly equal at this volume

    Scale to 100,000 input tokens and 20,000 output tokens per hour (a busy processing agent):

    • Input: $0.30/hour; Output: $0.30/hour
    • Token cost: $0.60/hour vs. session runtime of $0.08/hour — tokens are 7.5× the runtime charge

    The session runtime fee is flat and bounded. Token costs scale with workload volume. For high-volume 24/7 agents, optimize token efficiency (prompt caching, context management, output brevity) before worrying about the session runtime charge.

    Prompt Caching Changes the Token Math

    If your agent has a large, stable system prompt — common in agents with extensive tool definitions or knowledge bases — prompt caching dramatically reduces input token costs. Cache hits cost a fraction of base input rates. For a 24/7 agent with a 20,000-token system prompt hitting the same context repeatedly, caching that prompt can cut input costs by 80–90%. The session runtime charge is unchanged, but the total cost picture improves significantly.

    The Budget Summary

    Agent Type Runtime/mo Typical Total
    Monitoring / low activity ~$3 $5–15
    Support agent (business hours volume) ~$19 $50–100
    Continuous processing pipeline ~$48 $200–500+
    Theoretical maximum (zero idle) $57.60 Unbounded (tokens)

    Complete pricing reference: Claude Managed Agents Pricing Guide. How idle time affects billing: Idle Time and Billing Explained. All questions: FAQ Hub.

    What to do next

    Now that you have the cost math — here’s how to choose and implement

    You now know what Managed Agents costs at scale. The next decision is whether it’s the right architecture vs. OpenAI’s equivalent — and what the implementation actually looks like in practice.

  • Claude Managed Agents vs. OpenAI Agents API — A Direct Comparison

    Claude Managed Agents vs. OpenAI Agents API — A Direct Comparison

    TL;DR — Pick one in 30 seconds

    Choose Claude Managed Agents for zero-infra, fast production deployment. Choose OpenAI Agents API if you need multi-model flexibility or already run on OpenAI infrastructure.

    Feature Claude Managed Agents OpenAI Agents API
    Model lock-in Claude only GPT-4o, o3 — OAI only
    Setup complexity Zero infra — fully managed SDK — you build the harness
    Memory Built-in (public beta, May 2026) Manual via vector DB
    Multiagent Native (lead + specialists) Swarm/SDK patterns
    Pricing $0.08/session-hr + tokens Token-only (no session fee)
    Best for Fast production, Claude-native Multi-model, existing OAI infra

    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 4.6 referenced in this article has been superseded. See current model tracker →

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

    You’re evaluating hosted agent infrastructure. Both Anthropic and OpenAI have one. Before you commit to either, here’s what’s actually different — not the marketing version, the architectural and pricing version.

    Bottom Line Up Front

    If your stack is Claude-native and you want to get to production fast without building orchestration infrastructure, Managed Agents is hard to beat. If you need multi-model flexibility or have OpenAI deeply embedded in your stack, the calculus changes. Lock-in is real on both sides.

    Still Deciding?

    I’ve run both. Email me your use case and I’ll tell you which one fits.

    No pitch. If Claude isn’t the right call for what you’re building, I’ll tell you that too.

    Email Will → will@tygartmedia.com

    What Each Product Is

    Claude Managed Agents

    Anthropic’s hosted runtime for long-running Claude agent work. You define an agent (model, system prompt, tools, guardrails), configure a cloud environment, and launch sessions. Anthropic handles sandboxing, state management, checkpointing, tool orchestration, and error recovery. Launched April 8, 2026 in public beta.

    OpenAI Agents API

    OpenAI’s hosted agent infrastructure layer, launched earlier in 2026. Provides similar capabilities: hosted execution, tool integration, multi-agent coordination. Supports multiple OpenAI models (GPT-4o, o1, o3, etc.).

    Model Flexibility

    Managed Agents: Claude models only. Sonnet 4.6 and Opus 4.6 are the primary options for agent work. No multi-model mixing within the managed infrastructure.

    OpenAI Agents API: OpenAI models only, but a wider current model lineup (GPT-4o, o1, o3-mini depending on task). Also Claude-only within its own ecosystem — not multi-model in the cross-provider sense.

    The practical implication: If your evaluation is “I want the best model for this specific task regardless of provider,” neither hosted solution gives you that. Both lock you to their provider’s models. The multi-model comparison matters for self-hosted frameworks (LangChain, etc.), not for managed hosted solutions.

    Pricing Structure

    Claude Managed Agents: Standard Claude token rates + $0.08/session-hour of active runtime. Idle time doesn’t bill. Code execution containers included in session runtime — not separately billed.

    OpenAI Agents API: Standard OpenAI token rates + usage-based tooling costs. Pricing structure varies by tool and model tier. Verify current rates at OpenAI’s pricing page — rates have changed multiple times as their agent products have evolved.

    Direct comparison difficulty: Without modeling the same specific workload against both providers’ current rates, headline comparisons mislead. Token rates differ by model, model capabilities differ, and “session runtime” isn’t a category OpenAI uses. Model the workload, not the headline number.

    Infrastructure and Lock-In

    Both solutions create meaningful lock-in. This isn’t a criticism — it’s an honest description of the trade-off you’re making:

    Claude Managed Agents lock-in: Your agents run on Anthropic’s infrastructure with their tools, session format, sandboxing model, and checkpointing. Migrating to OpenAI’s Agents API or self-hosted infrastructure requires rearchitecting session management, tool integrations, and guardrail logic. One developer’s reaction at launch: “Once your agents run on their infra, switching cost goes through the roof.”

    OpenAI Agents API lock-in: Symmetric. Same dynamic in reverse. OpenAI’s session format, tool integration patterns, and infrastructure assumptions create equivalent switching costs to move to Anthropic’s platform.

    The honest framing: You’re not choosing “open” vs. “locked.” You’re choosing which provider’s lock-in you’re more comfortable with, given your existing infrastructure, model preferences, and vendor relationship.

    Data Sovereignty

    Both solutions run your data on provider-managed infrastructure. Neither currently offers native on-premise or multi-cloud deployment for the managed hosted layer. For companies with strict data sovereignty requirements, this is a parallel constraint on both platforms — not a differentiator.

    Production Track Record

    Claude Managed Agents: Launched April 8, 2026. Production users at launch: Notion, Asana, Rakuten (5 agents in one week), Sentry, Vibecode, Allianz. Anthropic’s agent developer segment run-rate exceeds $2.5 billion.

    OpenAI Agents API: Earlier launch gives more time in production, but the product has been revised significantly since initial release. Longer production history, but also more legacy architectural assumptions baked in.

    When to Choose Claude Managed Agents

    • Your stack is already Claude-native (you’re using Sonnet or Opus for most model calls)
    • You want to reach production without building orchestration infrastructure
    • Your tasks are long-running and asynchronous — the session-hour model fits naturally
    • The Notion, Asana, or Sentry integrations are relevant to your workflow
    • You want Anthropic’s specific safety and reliability guarantees

    When to Consider OpenAI’s Agents API Instead

    • Your stack is already heavily OpenAI-integrated (GPT-4o for primary model work, existing tool integrations)
    • You need access to reasoning models (o1, o3) for specific task types — Anthropic’s equivalent is Claude’s extended thinking, which has different characteristics
    • The specific tool integrations in OpenAI’s ecosystem are better matched to your stack
    • You want more production time at scale before committing to a platform

    When to Use Neither (Self-Hosted Frameworks)

    LangChain, LlamaIndex, and similar self-hosted frameworks remain viable — and better — when you genuinely need multi-model flexibility, on-premise execution, or tighter loop control than either hosted solution provides. The trade-off is engineering effort: months of infrastructure work that Managed Agents or OpenAI’s API eliminates.

    Complete pricing breakdown: Claude Managed Agents Pricing Reference. All Managed Agents questions: FAQ Hub. Enterprise deployment example: Rakuten: 5 Agents in One Week.

  • How Claude Managed Agents Handles Idle Time (And Why It Matters for Your Bill)

    How Claude Managed Agents Handles Idle Time (And Why It Matters for Your Bill)

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

    The most counterintuitive thing about Claude Managed Agents pricing is what you don’t pay for. Most people, when they hear “$0.08 per session-hour,” mentally model a virtual machine running continuously. That’s the wrong mental model. Here’s the right one, and why it matters for your bill.

    The Core Distinction: Active vs. Idle

    Managed Agents session runtime only accrues while your session’s status is running. The session can exist — open, initialized, capable of continuing — without accumulating runtime charges when it’s not actively executing.

    The specific states that do not count toward your $0.08/hr charge:

    • Time spent waiting for your next message
    • Time waiting for a tool confirmation
    • Time waiting on an external API response your tool is calling
    • Rescheduling delays
    • Terminated session time

    This is a meaningful architectural decision by Anthropic. They’re billing on what actually taxes their compute — active execution — not on session existence or wall-clock time.

    Why This Is Different From How You Might Expect Billing to Work

    Compare three billing models:

    Virtual machine billing (what this is not): You pay for every hour the instance exists, whether it’s idle or saturated. A VM running 24/7 with 10% actual utilization still costs 24 hours/day.

    Lambda/function billing (closer analogy): AWS Lambda bills on execution duration and invocation count — you pay when code actually runs, not when a function is “available.” Idle Lambda functions cost nothing.

    Managed Agents billing (what this actually is): Closer to Lambda than VM. You pay $0.08 per hour of active execution. A session that runs for 2 hours of wall-clock time but has 90 minutes of waiting costs $0.08 × 1.5 hours = $0.12, not $0.08 × 2 hours = $0.16.

    A Real Scenario: The Human-in-the-Loop Agent

    Consider an agent that processes your inbox for action items and waits for your approval before sending replies. Wall-clock time: 4 hours open during your workday. Actual active execution: 20 minutes of processing across that 4-hour window, with the rest spent waiting for your review decisions.

    • VM billing equivalent: 4 hours × rate = significant charge
    • Managed Agents billing: 20 minutes × $0.08/hr = $0.027

    The difference is real. For interaction-heavy agents where the agent frequently waits for human decisions, the idle-time exclusion significantly reduces costs versus a naive per-hour model.

    A Real Scenario: The Autonomous Batch Agent

    Now consider an agent running a fully autonomous content pipeline — no human checkpoints, just continuous execution through a queue. Wall-clock time and active execution time are nearly identical because the agent never waits.

    • A 2-hour autonomous batch: 2 hours × $0.08 = $0.16

    Here, the idle-time model provides no benefit — the agent has no idle time. The billing is effectively equivalent to per-hour pricing because execution is continuous.

    Code Execution Containers Are Included

    One more billing nuance worth knowing: when your agent runs code, the execution happens in sandboxed Linux containers. These containers are not separately billed on top of session runtime. The $0.08/hr covers both the session runtime and the container execution. This is explicitly documented by Anthropic and represents meaningful savings if your agent is doing significant code execution work — you’re not paying twice.

    What This Means for Workload Design

    If you’re designing agent workflows and have the choice between architectures, the billing model creates a useful signal:

    • Agents that wait on humans: Metered billing is favorable — you only pay for the actual reasoning and execution time, not the human decision time
    • Fully autonomous agents: Billing approaches equivalent to per-hour rates — optimize these on token efficiency, not idle reduction
    • Scheduled batch agents: Natural fit — run when needed, terminate when done, no idle accumulation

    The 24/7 Agent Math

    For anyone doing the 24/7 always-on calculation: the maximum theoretical runtime exposure is 24 hrs × $0.08 × 30 days = $57.60/month in session fees. But a 24/7 agent with zero idle time is rare in practice. Agents that sleep between triggers, wait on external data, or hold for human decisions have meaningful idle windows that reduce the actual charge below the theoretical ceiling.

    Full monthly cost analysis: The Real Monthly Cost of Running Claude Managed Agents 24/7. Pricing reference: Complete Pricing Guide. All questions: FAQ Hub.

  • Claude Managed Agents Rate Limits — What 60 Requests Per Minute Means in Practice

    Claude Managed Agents Rate Limits — What 60 Requests Per Minute Means in Practice

    The Lab · Tygart Media
    Experiment Nº 561 · Methodology Notes
    METHODS · OBSERVATIONS · RESULTS

    You’re planning to run Claude Managed Agents at scale. You’ve modeled the token costs, the session-hour charge, the workload cadence. Then you hit the actual constraint: rate limits. Here’s what 60 requests per minute actually means in practice, and whether it’s going to be your ceiling.

    The Two Limits You Need to Know

    Managed Agents has two endpoint-specific rate limits, separate from your standard Claude API limits:

    • Create endpoints: 60 requests per minute
    • Read endpoints: 600 requests per minute

    Your organization-level API limits apply on top of these. If your org is on a tier with a lower requests-per-minute ceiling, that’s the actual binding constraint.

    What “60 Create Requests Per Minute” Actually Means

    A create request, in Managed Agents context, is typically a session creation call — starting a new agent session. 60/minute means you can start 60 sessions per minute maximum. For almost all real workloads, this is not the binding constraint. Here’s why:

    Think about what generates create requests. If you’re running a batch pipeline that starts one new agent session per content item, processing 60 items per minute would saturate the limit. But a 60-item-per-minute content pipeline is running 3,600 items per hour — a genuinely high-volume operation. Most production agent workloads don’t look like this. They look like one session that runs for minutes or hours, processes multiple tasks within that session, and terminates when done.

    The create limit matters most for architectures where you’re spinning up a new session per task rather than running tasks within a persistent session. If that’s your pattern, 60/minute is a hard ceiling you’ll need to design around.

    What “600 Read Requests Per Minute” Actually Means

    Read requests include polling session status, reading agent output, checking checkpoints, and retrieving session state. 600/minute is a relatively generous limit — that’s 10 reads per second. For a monitoring dashboard polling 10 active sessions every second, you’d hit this. For most production monitoring patterns (checking status every 5-30 seconds per session), you’re well under the ceiling.

    The read limit becomes relevant in high-concurrency architectures where many sessions are running in parallel and all being polled aggressively. If you’re running 50 concurrent agents and checking each one every 2 seconds, that’s 25 reads/second — still within the 10 reads/second limit per second, but compressing toward it.

    The Limit That’s More Likely to Actually Stop You

    For most agent workloads, token throughput limits hit before request rate limits do. The reasoning: a long-running agent session processing significant context generates a lot of tokens. If you’re running many such sessions in parallel, you’ll hit your organization’s token-per-minute limit before you hit 60 sessions created per minute.

    Token limits depend on your API tier. Higher tiers have higher token throughput limits. Rate limit increases and custom limits for high-volume enterprise customers are negotiated with Anthropic’s sales team.

    Designing Around the 60 Create Limit

    If your architecture genuinely needs more than 60 new sessions per minute, the primary design pattern is batching more work within each session rather than creating more sessions. A single Managed Agents session can handle sequential tasks — you don’t need a new session per task if your tasks can be queued and processed within one session’s lifecycle.

    The tradeoff: longer-running sessions accumulate more runtime charge ($0.08/hr active). For most workloads, the efficiency gains from batching outweigh the marginal runtime cost.

    The Agent Teams Implication

    Agent Teams — Managed Agents’ multi-agent coordination feature — coordinate multiple Claude instances with independent contexts. Each instance in an Agent Team is a separate entity from a context standpoint. How Agent Team member sessions count against the create rate limit is worth verifying against current documentation if you’re architecting a high-concurrency Agent Teams deployment.

    For Enterprise Workloads

    If you’re evaluating Managed Agents for enterprise-scale deployment and the published limits don’t fit your volume requirements, contact Anthropic’s enterprise sales team. Rate limit increases for high-volume applications are a documented option — they’re negotiated, not self-serve.

    Contact: [email protected] or through the Claude Console.

    Frequently Asked Questions

    Does the 60 requests/minute limit apply to all API calls or just session creation?

    The 60/minute limit applies to create endpoints — session creation being the primary one. Read operations have a separate 600/minute limit. Standard Messages API calls are governed by your organization’s standard tier limits, not these Managed Agents-specific limits.

    Do subagents count against the create rate limit separately from the parent session?

    Subagents operate within the parent session’s context and report results upward — they’re architecturally different from new sessions. Verify current documentation for precise billing treatment of subagent creation calls vs. Agent Team session creation.

    What happens when I hit the rate limit?

    Standard API rate limit behavior applies — requests over the limit receive a 429 response. Implement exponential backoff in your session creation logic for any high-volume pattern that approaches the 60/minute ceiling.

    How does this compare to OpenAI’s Agents API limits?

    Rate limit structures differ by product and tier. Direct comparison requires checking both providers’ current documentation for your specific tier. The full comparison: Claude Managed Agents vs. OpenAI Agents API.

    Full pricing context including rate limits: Claude Managed Agents Complete Pricing Reference. All questions: Claude Managed Agents FAQ.

  • Radon Mitigation System Installation in New Construction

    Radon Mitigation System Installation in New Construction

    The Distillery
    — Brew № 1 · Radon Mitigation

    The lowest-cost and most effective time to address radon in a home is during construction — before the slab is poured, before walls are framed, before any remediation work is necessary. New construction radon mitigation installs a passive system (pipe, no fan) that can be activated with a fan at any future point for roughly $200–$400. Doing this same work after construction costs $800–$2,500 and requires drilling through finished concrete and routing pipe through finished walls.

    What Is Radon-Resistant New Construction (RRNC)?

    Radon-Resistant New Construction (RRNC) is a set of EPA-recommended building practices that minimize radon entry into new homes and create infrastructure for easy mitigation activation if post-construction testing reveals elevated levels. The EPA first published RRNC guidance in the 1990s; AARST-ANSI standard RRNC-2022 provides the current comprehensive technical requirements.

    RRNC is not a complete radon mitigation system. It is a passive infrastructure that makes active mitigation fast and inexpensive if needed. Think of it as a pre-wired electrical box: the capacity is built in, but you turn on power when you confirm you need it.

    Is RRNC Required by Building Code?

    RRNC requirements vary by state and municipality:

    • States with mandatory RRNC: Several states in EPA Radon Zone 1 (highest risk) require RRNC for all new residential construction. These include portions of Colorado, Iowa, Montana, North Dakota, South Dakota, and others.
    • States with voluntary or conditional RRNC: Many states adopt the International Residential Code (IRC) which includes RRNC provisions as a recommended (not mandatory) section. Some counties and municipalities within these states mandate RRNC independently.
    • States with no RRNC requirement: Builders in these areas may or may not include RRNC voluntarily.

    Regardless of legal requirement, the EPA recommends RRNC for all new construction — the incremental cost during construction is $350–$700 versus $800–$2,500+ for post-construction installation.

    The Four Core RRNC Components

    Per EPA RRNC guidance and AARST-ANSI RRNC-2022, a complete passive RRNC system consists of four elements.

    1. Gas-Permeable Layer

    A 4-inch layer of clean 3/4″ gravel (or equivalent gas-permeable material) placed beneath the slab across the entire footprint. This aggregate layer allows soil gases — including radon — to move freely beneath the slab toward the suction point rather than being forced through the concrete itself.

    Some jurisdictions allow alternative gas-permeable materials (certain drainage mats, for example) in lieu of gravel. The gravel layer also serves as drainage and supports the slab from below, so it has structural benefit regardless of radon.

    2. Plastic Sheeting (Vapor Barrier)

    A continuous layer of minimum 6-mil polyethylene sheeting placed over the gas-permeable gravel layer, beneath the concrete slab. The vapor barrier:

    • Prevents soil moisture from wicking up into the slab
    • Serves as a secondary barrier reducing radon and other soil gas migration through the slab
    • Laps up the interior foundation walls and seals at all penetrations

    The sheeting must be continuous — seams lapped a minimum of 12 inches and taped, penetrations sealed — before the concrete pour. Any gap becomes a permanent bypass that undermines both moisture and radon control.

    3. Vent Pipe

    A 3-inch or 4-inch PVC schedule 40 vent pipe is installed through the vapor barrier and slab during construction, routed through the building to terminate above the roof. This is the passive vent pipe that:

    • Runs from the sub-slab gravel layer up through the home’s interior (often inside the wall system or through a designated chase)
    • Connects to the exterior atmosphere above the roofline, providing passive thermal-draft ventilation of soil gases
    • Terminates with a cap that prevents precipitation and pest entry while allowing airflow

    The passive pipe alone — without a fan — can reduce radon by 30–50% in homes with favorable conditions (strong thermal draft, good aggregate, well-sealed slab). But it is not reliable as a sole mitigation strategy. Its primary value is as fan-ready infrastructure.

    4. Electrical Outlet in Attic or Near Fan Location

    An electrical junction box or outlet is installed in the attic (or wherever the future fan will be mounted) during initial construction. This ensures that activating the system with a radon fan requires only connecting the fan — no electrical work, no running new circuits through finished walls.

    This electrical prep step is frequently skipped by builders who are unfamiliar with RRNC or trying to minimize cost. When skipped, future fan activation requires an electrician to run a new circuit to the attic — adding $150–$400 to the activation cost.

    Passive-to-Active Conversion: Activating the System

    When post-construction radon testing shows levels at or above 4.0 pCi/L (EPA action level), or when a homeowner wants to reduce levels proactively, the passive RRNC system is activated by adding a radon fan. This is the simplest radon mitigation work available:

    • The existing passive pipe is already routed from sub-slab to above roofline
    • A radon fan is installed in the pipe run — typically in the attic between the riser and the discharge — and connected to the pre-installed electrical outlet
    • The installation takes 1–2 hours and costs $200–$500 in labor plus the fan ($100–$300)
    • A system performance indicator (manometer) is installed on the visible portion of the pipe inside the home
    • Post-activation radon testing confirms results

    Compare this to a full post-construction installation ($800–$2,500, 4–8 hours of labor) to understand why RRNC is consistently recommended by EPA, AARST, and every state radon program.

    RRNC in Crawl Space Homes

    For new construction homes with crawl spaces, RRNC provisions differ from slab/basement applications:

    • Vapor barrier: A 6-mil (minimum) polyethylene barrier is installed over the crawl space floor during construction, lapped up foundation walls and sealed at all penetrations
    • Vent pipe: A 3″–4″ PVC pipe penetrates the vapor barrier and routes through the home to above the roof — same passive vent function as the slab installation
    • Crawl space vents: AARST RRNC-2022 allows either vented or encapsulated crawl space design — the RRNC vent pipe infrastructure accommodates both

    Testing After Construction

    AARST and EPA recommend testing a new home for radon after occupancy, even if RRNC was implemented during construction. Reasons:

    • RRNC reduces radon entry but does not guarantee levels below 4.0 pCi/L — soil conditions and construction variations affect results
    • Passive-only systems may not achieve sufficient reduction in high-radon-zone homes without fan activation
    • Post-construction testing establishes a baseline for comparison if the home is later modified (addition, basement finish)

    The EPA recommends testing new homes after at least 60 days of occupancy under normal living conditions (closed house not required for initial new construction testing, as 60 days of normal occupancy provides sufficient averaging).

    Working with Builders: What to Specify

    If you are purchasing or building a new home and want to ensure RRNC is included:

    • Add RRNC to the contract as a line item — “Installation of passive radon vent system per EPA RRNC guidance and AARST-ANSI RRNC-2022”
    • Specify 10-mil or 20-mil vapor barrier (beyond the 6-mil minimum)
    • Confirm the electrical outlet in the attic is included
    • Request documentation at closing: vent pipe location, where it terminates, and outlet location
    • Ask whether the jurisdiction requires a permit for the RRNC installation and confirm the builder will obtain it

    Builders who have not done RRNC before may resist or underestimate the requirement. Having the AARST-ANSI RRNC-2022 standard number in the contract gives you a reference document that defines exactly what is required.

    Frequently Asked Questions

    What does RRNC stand for in radon mitigation?

    RRNC stands for Radon-Resistant New Construction. It refers to a set of EPA-recommended building practices that install passive radon vent infrastructure during home construction — before the slab is poured — making future radon fan activation fast and low-cost if post-construction testing shows elevated levels.

    How much does RRNC cost during new construction?

    RRNC during construction typically costs $350–$700 as a builder add-on. This includes the gas-permeable gravel layer (often already planned for structural reasons), vapor barrier (often already in the plans), vent pipe installation, and electrical outlet in the attic. Compare this to $800–$2,500 for post-construction installation.

    Does a passive RRNC system reduce radon by itself?

    Passive systems (no fan) can reduce radon 30–50% through thermal draft — warm air rising through the pipe creates natural suction. But passive systems are not reliable as sole mitigation — the thermal draft effect varies with outdoor temperature, wind, and internal building pressure. If post-construction testing shows levels above 4.0 pCi/L, fan activation is recommended.

    If I buy a new home with RRNC, do I need to test for radon?

    Yes. RRNC reduces radon entry probability but does not guarantee levels below the EPA action level of 4.0 pCi/L. Test after at least 60 days of occupancy under normal living conditions. If levels are at or above 4.0 pCi/L, activate the system by adding a fan — a 1–2 hour installation that costs $300–$800 total.

    Can RRNC be added to a home after construction has started?

    Partially. If the slab has not yet been poured, the gravel layer, vapor barrier, and pipe penetration through the slab can still be completed. If the slab is poured but walls are not yet framed, the vent pipe can still be routed through wall framing before drywall. Once walls are finished, full RRNC infrastructure cannot be added — the installation becomes a standard post-construction retrofit.

  • 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.

  • Does Homeowners Insurance Cover Radon Mitigation?

    Does Homeowners Insurance Cover Radon Mitigation?

    The Distillery
    — Brew № 1 · Radon Mitigation
    Standard homeowners insurance policies do not cover radon mitigation. State Farm, Allstate, USAA, Liberty Mutual, and every other major carrier exclude it because radon is classified as a gradual environmental condition rather than a sudden event. However, alternative paths exist to reduce the cost, including state assistance programs, HSA and FSA eligibility with medical documentation, real estate transaction negotiation, and contractor financing.

    The short answer is no. Homeowners insurance does not cover radon mitigation. Not State Farm, not Allstate, not USAA, not Liberty Mutual, not Progressive, not Farmers. Not any of the major carriers and not any of the minor ones. Standard homeowners insurance policies in 2026 exclude radon mitigation as a category of expense, and they have for decades.

    But “no” isn’t actually the complete answer, because there are a handful of narrow situations where insurance can partially offset radon-related costs, and there are several alternative paths to reducing the financial burden that people routinely overlook. This is the honest breakdown: why insurance won’t cover the main cost, what exceptions might apply to you, and what realistic options exist instead.

    Why homeowners insurance doesn’t cover radon mitigation

    The reason is structural to how homeowners insurance is designed, not arbitrary. Standard policies cover losses from sudden and accidental events — fires, storms, theft, vandalism, covered water damage, liability claims when someone is injured on your property. They explicitly exclude losses from gradual conditions that develop over time — foundation settling, wear and tear, mold from chronic moisture, soil movement, and yes, radon accumulation.

    Radon sits firmly in the “gradual condition” category. Uranium has been decaying in the soil beneath your home for billions of years. Radon has been seeping up toward your foundation for the entire time the home has existed. It isn’t an event, it’s a steady-state condition. Insurance companies classify it the same way they classify foundation settling, soil subsidence, and long-term moisture damage — as a maintenance issue the homeowner is responsible for addressing.

    Every major insurance carrier’s position on radon, as of 2026:
    – State Farm: excluded from standard policies
    – Allstate: excluded from standard policies
    – USAA: excluded from standard policies
    – Liberty Mutual: excluded from standard policies
    – Progressive: excluded from standard policies
    – Farmers: excluded from standard policies
    – Nationwide: excluded from standard policies
    – Travelers: excluded from standard policies

    Some of these carriers offer add-on endorsements or riders for environmental hazards that might include limited radon coverage — typically for $25 to $100 per year in additional premium — but the coverage is usually capped at low amounts (often $500 to $1,500) and requires specific triggering events. None of them cover routine radon mitigation as a standard inclusion.

    The exclusion isn’t hidden in the fine print; it’s a standard feature of how homeowners insurance works across the industry. Radon is not insurable under conventional policies for the same reason chronic roof wear isn’t insurable — it’s a foreseeable ongoing condition, not an unexpected loss.

    The narrow exceptions where insurance might help

    There are a few specific situations where homeowners insurance can partially cover radon-adjacent costs. None of them cover routine mitigation, but they’re worth understanding because they occasionally apply.

    1. Storm damage to an existing mitigation system

    If a severe storm damages the exterior portion of your radon mitigation system — for example, high winds rip the vent pipe off the exterior wall, or hail damages the rooftop vent flashing — your homeowners insurance may cover the repair cost as storm damage. The key is that the damage was caused by a covered peril (the storm), not by the radon itself. The radon system is treated as part of the home’s physical infrastructure for the purpose of storm damage claims.

    What this covers: Physical repair or replacement of damaged mitigation system components after a covered weather event.

    What this does not cover: Any reduction in system effectiveness, any increase in indoor radon levels during the repair period, or the original installation cost.

    Realistic claim value: $300 to $1,200 for typical storm damage to a mitigation system.

    2. Covered water damage from a failed sump integration

    If your mitigation system includes sump pit integration and a component failure causes the sump pump to malfunction, resulting in basement flooding, your homeowners insurance may cover the water damage itself — even though the radon system repair is not covered. The covered peril is the water damage, not the radon system.

    What this covers: Water extraction, drying, damaged flooring and drywall replacement, damaged contents.

    What this does not cover: Repair of the sump pump, the mitigation system, or any ongoing radon-related costs.

    This is a fairly rare scenario because sump integration in well-installed mitigation systems rarely causes pump failures, but it’s worth knowing the distinction.

    3. Liability coverage in disclosure-related lawsuits

    If you sell a home, the buyer later discovers elevated radon levels, and the buyer can prove you knew about the problem and failed to disclose it, your homeowners insurance liability coverage might apply to any resulting lawsuit. Whether coverage applies depends on your policy language and your state’s disclosure laws.

    This is a complex legal scenario and not a reliable safety net. Most states require disclosure of known material defects including radon, and most disclosure-related lawsuits are settled outside of insurance coverage because they involve allegations of intentional concealment rather than accidents.

    Realistic use case: Rare. Consult a real estate attorney if this situation applies to you.

    4. Future health claims linked to radon exposure

    Homeowners insurance does not cover medical claims for illness allegedly caused by radon exposure. Health insurance might, if a doctor diagnoses a condition and documents the causal link to radon, but this is uncommon and highly fact-specific. Most radon-related lung cancer cases are not pursued as insurance claims because the latency period (typically 5 to 25 years between exposure and cancer diagnosis) makes causation difficult to establish definitively.

    This category is effectively a non-option for most homeowners.

    What homeowners insurance actually does when radon is detected

    In most cases, the interaction between a homeowner and their insurance company around radon is limited to the following:

    1. Nothing. The homeowner discovers elevated radon, pays for mitigation out of pocket, and never contacts the insurance company. This is the most common outcome.
    2. A disclosure question at renewal. Some insurance companies ask about known environmental conditions at policy renewal. Disclosing that you had elevated radon and mitigated it is honest and typically does not affect your rate — mitigation is viewed as responsible maintenance.
    3. A denied claim. If a homeowner attempts to file a radon mitigation claim anyway, it will be denied citing the policy exclusion for gradual environmental conditions.

    There is no meaningful benefit to involving your insurance company in routine radon mitigation. The outcome of the call is almost always a polite “that’s not covered.”

    Alternative paths to reducing the cost

    Insurance isn’t the answer, but there are several legitimate ways to reduce or offset the cost of radon mitigation that most homeowners don’t know about.

    1. State-level grants and assistance programs

    Several states offer grants, loans, or financial assistance for radon mitigation to qualifying homeowners. Program details and eligibility change year to year, and availability is usually limited to specific income brackets or high-risk geographic areas, but real money is available in the right situations.

    States with active radon mitigation assistance programs (as of 2026):
    Pennsylvania Department of Environmental Protection: limited grants for low-income homeowners in high-radon counties
    Illinois Emergency Management Agency: Illinois Radon Mitigation Program for qualifying households
    Iowa Department of Public Health: Iowa Radon Program mitigation assistance
    Minnesota Department of Health: financial assistance programs through the state radon office
    Colorado Department of Public Health and Environment: grants in some counties through the state radon program
    Wisconsin Department of Health Services: limited assistance through regional radon information centers

    Grant amounts typically range from $500 to $1,500 per qualifying household when awarded. Applications usually require income verification, proof of an elevated radon test, and a quote from a certified mitigator.

    How to check if your state has a program:
    – Contact your state health department’s radon section
    – Search for “[your state] radon mitigation grant”
    – Check the EPA’s state radon contacts page at epa.gov/radon/find-your-states-radon-contact-information

    2. HSA and FSA eligibility

    Radon mitigation can sometimes qualify as a medical expense for Health Savings Account (HSA) or Flexible Spending Account (FSA) purposes when a physician has documented a health condition affected by radon exposure. This is most commonly applicable when a household member has been diagnosed with lung cancer, chronic respiratory disease, or another condition where continued radon exposure is medically contraindicated.

    How HSA/FSA eligibility works for radon mitigation:

    When eligible, the mitigation cost can be paid with pre-tax HSA or FSA dollars, effectively reducing the cost by the user’s marginal tax rate. For a household in the 22% federal tax bracket plus a 5% state tax, a $2,000 mitigation paid with HSA dollars has an effective cost of roughly $1,460 — a savings of about $540.

    Requirements:
    – A licensed physician’s letter documenting the medical necessity of radon mitigation for a specific diagnosis
    – The mitigation must be installed in a primary residence (not a rental property)
    – The expense must be documented according to IRS Publication 502 guidelines
    – A Letter of Medical Necessity (LMN) is required for FSA reimbursement

    This is not a routine use of HSA/FSA funds. Most radon mitigations do not qualify because no medical diagnosis is driving the work. Consult a tax professional before relying on this approach, and keep all documentation for at least seven years in case of audit.

    3. Federal and state tax benefits

    Direct tax deductions for radon mitigation are uncommon for owner-occupied homes but possible in a few specific scenarios:

    Rental property owners: If you install radon mitigation on a rental property you own, the cost can typically be deducted as either a repair (deducted fully in the year incurred) or a capital improvement (depreciated over the property’s useful life). Classification depends on the specific circumstances. Consult a tax professional.

    Medical expense deduction: As described under HSA/FSA above, radon mitigation can occasionally qualify as a deductible medical expense when a physician documents medical necessity. The deduction only applies to the portion of total medical expenses exceeding 7.5% of adjusted gross income, which is a high threshold for most taxpayers.

    State-level credits: A few states have offered limited tax credits for residential radon mitigation at various times. Check with your state department of revenue for current availability.

    Energy efficiency credits: Radon mitigation does not qualify for the federal energy efficiency tax credits that cover HVAC, insulation, and similar improvements. Those credits are specifically for energy-saving measures.

    Tax rules change frequently. Consult a qualified tax professional before claiming any deduction related to radon mitigation.

    4. Home warranty add-on coverage

    Some home warranty companies offer optional coverage for radon fan replacement as an add-on to their standard plans. This does not cover the initial installation, but it can cover the cost of replacing a failed fan motor years after installation — typically a $300 to $600 expense that would otherwise come out of pocket.

    How home warranty radon coverage typically works:
    – Monthly premium increase of $5 to $15 for the radon add-on
    – Coverage triggers when the fan fails and requires replacement
    – Service fee of $75 to $125 per claim
    – Limits vary; typical cap is $500 to $1,000 per claim

    For homeowners with aging mitigation systems who expect fan replacement within a few years, the math can work out favorably. For homeowners with new systems still under manufacturer warranty, it’s usually unnecessary.

    5. Real estate transaction negotiation

    For homeowners buying a new home where a pre-purchase radon test comes back elevated, the most effective “cost savings” is often getting the seller to pay for mitigation as part of the sale. Depending on market conditions and negotiating leverage, sellers pay for mitigation in roughly 40 to 60 percent of cases where it becomes a contract contingency.

    Typical outcomes:
    Buyer’s market: Seller pays 70-100% of mitigation cost as a concession to close the deal
    Balanced market: Cost is often split 50/50 or the seller pays in full
    Seller’s market: Buyer often pays in full to keep the deal competitive, though sometimes splits the cost

    Sellers in high-radon states increasingly install mitigation systems proactively before listing to avoid the contingency negotiation altogether. A documented working mitigation system has become a mild selling point in regions where radon awareness is high.

    Standard contract language: Most real estate purchase contracts include a radon testing contingency that allows the buyer to request mitigation or walk away if levels exceed the EPA action level of 4.0 pCi/L. If your contract includes this contingency and your test comes back elevated, the negotiation path is well-established and usually results in some level of seller contribution.

    6. Manufacturer rebates and contractor financing

    Some radon mitigation contractors offer financing plans that spread the installation cost over 12 to 60 months, typically with low or zero interest for qualified buyers. This doesn’t reduce the total cost but makes it easier to absorb.

    Manufacturer rebates on radon fans are rare but occasionally appear — primarily from RadonAway on specific fan models during promotional periods. Savings when available are usually $25 to $100.

    Payment plan options to ask about:
    – In-house contractor financing (0% interest for 6-12 months is common)
    – Third-party home improvement financing through companies like Synchrony or Wells Fargo
    – Home equity line of credit (HELOC) for larger installations
    – Credit card payment with 0% introductory APR offers

    These don’t reduce the cost but can make it manageable for homeowners who can’t cover the full $1,500 to $2,500 installation in a single payment.

    What to do if you can’t afford mitigation

    If you’ve confirmed elevated radon levels and can’t afford the mitigation cost in the near term, several interim steps can reduce your exposure while you work out the financing.

    Short-term harm reduction:

    1. Increase ventilation in the lower level of the home. Opening windows and running ventilation fans temporarily reduces indoor radon concentrations. This is not a long-term solution and doesn’t work in cold climates where windows need to stay closed, but it can meaningfully lower exposure as a stopgap.

    2. Avoid spending time in the lowest level of the home. Radon concentrations are typically highest in basements and the ground floor. Reducing time spent in those areas proportionally reduces exposure. If your basement is where family members spend most of their waking hours, moving that activity to upper levels temporarily reduces risk.

    3. Seal obvious foundation cracks. Sealing cracks alone is not effective mitigation, per EPA and AARST, but it can marginally reduce radon entry as an interim measure while you save for a professional system.

    4. Run bathroom and kitchen exhaust fans more frequently. These fans create negative pressure in the home that actually increases radon entry rates in some cases, but when combined with open windows on upper floors they can create an air exchange pattern that dilutes indoor radon. Use with caution.

    Longer-term planning:

    • Check state grant programs and apply if eligible
    • Contact your state radon office to ask about low-income assistance
    • Discuss the installation with certified mitigators and ask about payment plans
    • Compare 2-3 quotes to find the lowest legitimate price for your specific home
    • Consider DIY passive approaches (floor sealing, increased ventilation) as temporary measures while saving

    What not to do:

    • Don’t attempt a DIY active radon mitigation system unless you have specific training. An incorrectly installed ASD system can create problems larger than the original radon issue, including fan-induced negative pressure that worsens radon entry in other parts of the home. EPA explicitly discourages DIY installation for this reason.
    • Don’t ignore the test result. Elevated radon levels are a cumulative health risk, and the cost of a professional mitigation system is a small fraction of the cost of lung cancer treatment.
    • Don’t use DIY test kits you don’t trust as a reason to conclude your home is fine. If you tested elevated once, retest before concluding anything, but don’t discount a confirmed elevated result.

    The bottom line on insurance

    Homeowners insurance does not cover radon mitigation, will not cover radon mitigation, and has never covered radon mitigation under standard policies. The exclusion is structural and industry-wide, not a gap you can negotiate around with your specific carrier.

    But the complete picture includes alternative paths that most homeowners don’t know exist: state grants, HSA/FSA eligibility with medical documentation, real estate transaction negotiation, home warranty add-ons, and contractor financing. These options don’t eliminate the cost but they can meaningfully reduce it or make it manageable for households that would otherwise struggle with a $1,500 to $2,500 out-of-pocket expense.

    The conversation that matters isn’t with your insurance company. It’s with certified mitigators about the actual installation, with your state radon program about assistance availability, with your tax professional about possible deductions, and — if you’re in a real estate transaction — with your agent about negotiating seller contribution. Those conversations produce results. The insurance call does not.

    Frequently asked questions

    Does any homeowners insurance cover radon mitigation?

    No standard homeowners insurance policy from any major carrier covers routine radon mitigation. The exclusion is structural — radon is classified as a gradual environmental condition rather than a sudden event — and applies across the industry. Some carriers offer environmental hazard riders that may provide limited coverage for radon-related costs, but these are capped at low amounts and do not cover typical mitigation installation. Routine mitigation is an out-of-pocket expense for homeowners in virtually every case.

    Will my insurance cover storm damage to my radon mitigation system?

    Yes, if the damage is caused by a covered peril like high winds, hail, or falling trees. The key is that the damage must come from an event your policy covers, not from the radon itself or from system wear. If a storm rips the exterior vent pipe off your home, the repair is typically covered as standard storm damage. The original installation cost and any ongoing radon-related costs remain the homeowner’s responsibility.

    Can I use my HSA to pay for radon mitigation?

    Only if a licensed physician documents the mitigation as medically necessary for a specific diagnosis affecting a household member. Most radon mitigations do not qualify because no medical condition is driving the work. When HSA or FSA payment is eligible, the effective cost is reduced by the homeowner’s marginal tax rate, which typically produces savings of $300 to $600 on a $2,000 mitigation. Consult a tax professional and keep medical documentation on file before relying on this approach.

    Is radon mitigation tax deductible?

    For primary residences, radon mitigation is generally not tax deductible unless it qualifies as a medical expense (requiring physician documentation and a diagnosis). For rental properties, the cost can typically be deducted as a repair or depreciated as a capital improvement, depending on how it’s classified. A few states have offered limited tax credits for residential radon mitigation in the past — check with your state department of revenue for current programs.

    What state has the best radon mitigation assistance program?

    Pennsylvania, Illinois, Iowa, and Minnesota have the most active state-level assistance programs as of 2026, typically offering grants of $500 to $1,500 for qualifying low-income households in high-radon areas. Program availability and funding change year to year. Contact your state health department’s radon section directly for current eligibility requirements and application procedures.

    If I’m buying a home, who should pay for radon mitigation?

    It depends on the market and the specific contract, but negotiation is normal. In buyer’s markets, sellers typically pay for 70-100% of mitigation cost as a contingency concession. In balanced markets, the cost is often split or paid entirely by the seller as a goodwill gesture. In seller’s markets, buyers more frequently pay to keep the deal together. Most purchase contracts include a radon testing contingency that establishes the negotiation framework. Work with your real estate agent to craft a contingency that protects your interests based on current market conditions.


    THE TYGART MEDIA DISTILLERY
    This is a knowledge node.
    Part of the Radon Mitigation knowledge base — a category being brewed openly, one node at a time. Every article passes through an eight-pass distillation pipeline before publication. Live organic value tracked publicly on the Distillery Live Value Meter.