Free scan · no signup · ~30 seconds

AI agents read your site before your customers do. Find out what they can actually use.

Start with the free readiness scan — what an agent can reach, read and act on, with the exact fixes. Then the evidence: whether a live assistant cites your domain, and how far a buying agent gets toward your checkout.

Free · no signup · See an example report

Sites running AgentSpeed · scored live, badge on the pageWebsiteDown.comPopulationTracker.ioSolarNaperville.comStatusDetector.comOur own properties, scored by the same public rubric as everyone else — including the scores we would rather were higher.
agentspeed.comlive report · scanned 2026-09-02 07:01 UTC · rubric 2026.11.0full report →
0100discoverability · API catalog / OpenAPI: passdiscoverability · Link response headers: passdiscoverability · MCP server card: passdiscoverability · OAuth authorization metadata: faildiscoverability · OAuth resource metadata: faildiscoverability · Web Bot Auth: faildiscoverability · llms.txt present: passdiscoverability · Canonical URL: passdiscoverability · Declared language: passdiscoverability · Meta description: passdiscoverability · Page title: passdiscoverability · robots.txt allows AI agents: passdiscoverability · Content-Signal directives: passdiscoverability · robots.txt present: passreadability · JSON-LD name appears on the page: passreadability · JSON-LD price matches the visible price: passreadability · Declared language matches the content: passreadability · Heading hierarchy: passreadability · Content without JavaScript: passreadability · Text-to-markup ratio: failreadability · Markdown negotiation: failstructured_data · JSON-LD present: passstructured_data · Schema type coverage: failstructured_data · Structured data validates: passactionability · Agent Skills manifest: passactionability · Commerce protocol manifest: failactionability · WebMCP actions: passactionability · Primary action reachable: passactionability · Filters reachable by URL: skipactionability · Primary action is clickable: passperformance · Full render time: skipperformance · Page weight: passperformance · Time to first byte: passother · Cookie wall blocks content: passother · Paywall / login wall: passother · Reachability: passother · Sitemap present: pass87/ 100 · B
  • 28 pass
  • 7 fail
  • 2 not measured
  • Crawler access100
  • Structured data88
  • Readable without JS100
  • Buy button in the HTML100
  • Performance90
Top fixes
  • failText-to-markup ratio

    If the weight is markup, the usual cause is deeply nested wrappers, repeated navigation and ad slots: flatten the structure and move presentation into stylesheets.

  • failSchema type coverage

    Align JSON-LD type to page purpose.

  • failCommerce protocol manifest

    If you sell to agents, publish the discovery manifest for the commerce protocol you support: /.well-known/x402.json (x402), /.well-known/ucp (UCP), or /.well-known/acp.json (ACP).

37 checks · 26 deterministic · 10 heuristic · 1 llm-assisted

Scored against the agents that fetch your pages to answer questions

  • ChatGPT-User
  • OAI-SearchBot
  • Claude-User
  • Claude-SearchBot
  • Perplexity-User
  • PerplexityBot
  • YouBot
  • Amazonbot
  • Applebot

We track 24 agents in all. These 9 move your score; the other 15 — 10 training crawlers and 5 regional engines — are reported to you and deliberately not charged against it. Blocking a training crawler is a licensing decision, not a readiness defect. Every agent, and which tier it is in →

After the AI finds you

Being mentioned is the easy half.

Visibility tools tell you an assistant said your name. They cannot tell you what happened when it arrived. These are real failures the free scan detects, and what each one costs.

  • Your structured data says $49. Your page says $59.

    The agent reads the machine-readable price and quotes a number you will not honour. The buyer finds out at checkout.

    coherence.jsonld_price_matches_visible
  • Your buy button is painted by JavaScript after load.

    An agent that reads the HTML your server sends never sees a button to press, so the purchase path ends on arrival.

    operability.primary_action_in_dom
  • Your product copy only appears once the page boots.

    The agent summarises an empty shell. Whatever it tells the buyer about you, it did not get from your page.

    content.js_required_for_primary_content
  • A consent or login wall stands in front of the content.

    The agent hits the wall instead of your offer, and reports back on the wall.

    auth.paywall_or_login_wall_on_landing
  • Your JSON-LD is present but does not validate.

    The one part of your page written for machines is the part they discard, so the agent falls back to guessing from marketing copy.

    structured_data.validates
  • Your filters and variants have no addressable URL.

    An agent asked for "the blue one in medium" cannot construct a link to it, so it cannot get the buyer to the thing they asked for.

    operability.filters_addressable
Three questions

The whole agent path, in the order it fails

1 · Discover

Do agents find and choose you?

The scan grades what discovery depends on: robots policy per agent, structured data, the well-known files agents pre-flight. Then, from your report, a live assistant is asked a real buying question — and you see whether it cited your domain, saw it and chose someone else, or never found it.

Scan my site →
2 · Transact

Can they buy from you?

Three gates — Find, Read, Buy — answered free from the same scan. The Deep Scan goes further: a read-only, five-step purchase walk from your homepage to checkout that shows the exact step a buying agent loses.

Check my store, free →
3 · Drift

Will you know the day it breaks?

Sites drift — a robots edit, a CDN default, a template swap — and nothing in your analytics fires. Watches re-run the same rubric on your schedule and alert you the week anything meaningful changes.

See plans →

The 0–100 readiness score under all three is the diagnosis layer: it tells you which fix moves which answer.

If you sell online

AI agents are shopping. Can they buy from you?

Three gates, in order. Most stores clear the first two and lose the sale at the third, and nothing in your analytics fires when it happens.

Check my store, free →

Research preview — inferred from your scan, labeled as such.

Three ordered gates stand between a shopping agent and a checkout: Find (robots + sitemap), blocked by a crawler blocked, then Read (price without JS), blocked by a price needs scripts, then Buy (reach the checkout), blocked by a login or consent wall. A store can clear the first two and still lose the sale at the third.
The same page, twice

Structure is a rendering choice. Agents get the other one.

This is our own homepage as a person reads it, and as an agent receives it with JavaScript switched off. Yours is one scan away.

agentspeed.comfetched as an agent would · JavaScript off
Human
AgentSpeed: can AI agents read and use your site?

Free 30-second scan of what AI agents can reach, read and act on — then the evidence: whether a live assistant cites you, how far a buying agent gets, and alerts the week anything breaks.

  • AI agents read your site before your customers do. Find out what they can actually use.
  • Being mentioned is the easy half.
  • The whole agent path, in the order it fails
  • Do agents find and choose you?
  • Can they buy from you?
Agent
agentspeed.Free scanCan agents buy?PricingDocsSign inScan my site →Free scan · no signup · ~30 secondsAI agents read your site before your customers do. Find out what they can actually use.Start with the free readiness scan — what an agent can reach, read and act on, with the exact fixes. Then the evidence: whether a live assistant cites your domain, and how far a buying agent gets toward your checkout.Scan my site →Free · no signup · See an example reportSites running AgentSpeed · scored live, badge on the pageWebsiteDown.comPopulationTracker.ioSolarNaperville.comStatusDetector.comOur own properties, scored by the same public rubric as everyone else — including the scores we would rather we…
192,932 bytes of HTML · 14 headings · 0 scripts run

Both readings from the scan of 2026-09-02 — re-taken daily.

Measured, not imagined

How agents actually fail on real sites

Detected on public scans of 828 domains in the last 30 days. Every one looks fine in a browser.

Schema type coverage
209 domains
Primary action reachable
59 domains
Time to first byte
56 domains
Heading hierarchy
53 domains
Best, median and worst of 845 ranked domains

See the domains behind these numbers →

What we measure

Five steps, and the five ways they break

Every check in the rubric attaches to one of these five steps, and every failure is one of them going wrong on a page that looks perfect to you.

An agent reads a site in five steps, and each has its own way of failing: Ask, which reads robots.txt and fails when a rule blocks it; Find, which reads sitemap + catalogs and fails when no sitemap exists; Fetch, which reads HTML, no browser and fails when a wall answers first; Read, which reads text + JSON-LD and fails when JSON-LD ≠ the page; Act, which reads links + protocols and fails when the action is an image. Every one of them looks fine in a browser.

Run any step on its own, free, or run all five in one scan.

The instrument: a published rubric, not a private opinion
36 scored checks across 5 categories. The bar is the whole score; each segment is one category’s share of it.
  • Actionability8 checks5 emerging28%
  • Discoverability11 checks6 emerging22%
  • Readability9 checks2 emerging22%
  • Performance3 checks15%
  • Structured data5 checks2 emerging13%

15 of the 36 test agent-native standards whose adoption is still emerging — every one scored, every one listed at /rubric.

The rubric scores 36 checks across 5 categories, and their weights sum to 100 percent of the score: Actionability at 28 percent over 8 checks, Discoverability at 22 percent over 11 checks, Readability at 22 percent over 9 checks, Performance at 15 percent over 3 checks, Structured data at 13 percent over 5 checks. 15 of the checks test agent-native standards whose adoption is still emerging, and every one of them carries weight in the score. They are listed individually at /rubric.

37 checks, 36 of them scored. The one we report without scoring is llms.txt, because Google says Search does not use it and a large domain study found no link to AI citations.

Rubric r2026.11.0: 70.6% of the weight is deterministic, enforced in CI.

PageSpeed measures humans. Keep it. It measures real things, just not these. See the comparison →

Vs the tools you already run

Same site, a different reader

Agent traffic is the fastest-growing source a site has: Adobe put AI-referred visits to US retail up 393% year over year in Q1 2026, across more than a trillion visits.

 PageSpeed, LighthouseAgentSpeed
What it measuresLoading speed, accessibility, SEOWhether an agent can read, navigate and transact
Who the user isA browser on a phoneGPTBot, ClaudeBot, PerplexityBot, autonomous agents
AI crawler policyNot measured24 agents tracked, verdict per agent
Cookie and login wallsNot measuredVendor fingerprinted, verdict per barrier
One workflow

Scan → Monitor → Investigate → Certify: the same rubric at every stage

Know whether AI agents can read you and buy from you — not just find you — and get told the day that changes. Every stage scores against the same published rubric, so upgrading never resets what you learned.

1 · Scan
Free scan Free

Paste a URL, get the graded report: what agents can reach, read and act on, with the exact fixes.

Scan my site
2 · Monitor
Watches From $19/mo

Scheduled re-checks with alerts on meaningful change. Sites drift — a robots edit, a CDN default, a template swap — and nothing in your analytics fires when it happens.

See plans
3 · Investigate
Evidence reports From $29 one-time

When something needs proof: the Deep Scan fix-list report, the agent Transaction Audit, the AI Market Report. One-time purchases, no subscription.

Order a Deep Scan
4 · Certify
Certification Per site, per year

A signed, machine-verifiable attestation with its own weekly monitoring — revoked if your site stops earning it, which is what makes it worth showing.

How certification works

Building agents rather than a site? The telemetry line — runs, cost, journey canaries, alerts, free for 10,000 events a month, metadata-only by design — lives at /observability, with a working demo.

How to buy

The first three stages, side by side

 1 · Scan Free2 · Monitor Popular3 · Investigate
PriceFreeFrom $19/mo$29 once
Fixes shownTop 6Every finding, plus diffsEvery finding, step by step
Speed~30 secondsHourly, daily or weekly~1 to 2 minutes
Alerts on regressionNoSlack, webhook, emailNo
Free
$0/mo
  • 1 scheduled watch · weekly
  • Competitor benchmarking on paid plans
  • AI visibility monitors on paid plans
  • AI crawler traffic analytics
  • 10,000 agent events/mo
  • 1 project · 3 agents
  • 1 journey canary · manual runs
  • Alert channels on paid plans
  • 1,000 evaluations/mo (API · beta)
  • 7-day retention
Starter
$19/mo
  • 3 scheduled watches
  • 3 competitors benchmarked
  • 1 AI visibility monitor · 300 prompt runs/mo across Claude
  • AI crawler traffic analytics
  • 100,000 agent events/mo
  • 3 projects · 10 agents
  • 10 journey canaries · scheduled + alerts
  • Slack / webhook / email alerts
  • 25,000 evaluations/mo (API · beta)
  • 30-day retention
RECOMMENDED
Growth
$79/mo
  • 10 scheduled watches
  • 10 competitors benchmarked
  • 3 AI visibility monitors · 3,000 prompt runs/mo across Claude
  • AI crawler traffic analytics
  • 1,000,000 agent events/mo
  • 10 projects · 50 agents
  • 50 journey canaries · scheduled + alerts
  • Slack / webhook / email alerts
  • 250,000 evaluations/mo (API · beta)
  • 90-day retention

One event = one ingested row. Full pricing and FAQ →

Scan it once. Watch it forever.

Free, 30 seconds, no signup.