AgentSpeed: See what AI agents see on your site — then monitor it agentspeed . Free check Live demo Pricing Tools Docs Sign in Start free → Free check · no signup · ~30 seconds AI agents are already reading your site. See what they see. Paste a URL and get a graded report: which AI crawlers you block, whether your llms.txt works, and what an agent can actually read — with the exact fixes. Scan my site → Building agents? Explore the live monitoring demo → The check Four things only machines see Crawler access Which AI crawlers your site allows, blocks, redirects, or challenges. Real fetches as GPTBot, ClaudeBot, Perplexity, and friends. run this check → llms.txt Present, valid, and actually useful to an agent? Graded on six axes, with a suggested replacement that closes every gap. run this check → Readability without JS Most agents never run your JavaScript. See what a bot reading raw HTML actually understands about your page. run this check → Structured data The JSON-LD machines rely on: which types you ship, what fails validation, and what is missing for your page type. run this check → The full scan grades your site against our public rubric. Powered by 11 free tools → Watches A check is a snapshot. A watch is monitoring. A stray robots rule or a new bot wall can cut agents off silently — nothing errors, nothing shows in analytics. Turn any check into a watch and find out the moment it changes. Re-runs on your schedule Hourly, daily, or weekly. The same check, the same URL, without you remembering to look. Diffs what changed A robots rule edited, a bot newly challenged, an llms.txt section dropped, a score that slid. Every snapshot is kept. Alerts on regression Slack, webhook, or email the moment a meaningful change lands. No alert storms; a 30-minute cooldown is built in. Start one from any tool result — look for “Watch this URL”. Watches are included on paid plans (from $ 19 /mo). Agent monitoring Building agents? Monitor those too. Agents don’t crash. They quietly get slower, pricier, and wrong. Trace every run down to the token and the dollar, and get paged the moment something breaks. Metadata-first · we never store your prompts or outputs Runs & spans Click a run and read it top to bottom: every LLM call, tool call, and retrieval with its own timing and tokens, plus live p50/p95 per agent. Cost & tokens Tokens and dollars by agent, by model, by run. One stuck retry loop can spend $40 before you finish your coffee. You will see it the same minute. Quality drift Send a quality score with each run, a number you already compute. Watch it per agent and per model, and catch the slide where success holds at 99% but answers quietly got worse. Journey canaries Describe a critical flow in plain steps. On a schedule we probe the live site and verify each step is still supported by what it actually serves — and page you when one breaks. Bot walls get reported, never bypassed. Alert rules Threshold on failure rate, latency, cost, quality, or silence. Every failure keeps its error type, so a creeping RateLimitError cannot hide behind a healthy average. Public status pages Hand customers a status page with 30-day uptime bars. One link, always current. Live render · this is the real product UI, not a screenshot Checkout assistant · sample data agentspeed . Projects Alerts Status pages Billing Settings Projects · production Checkout assistant sample data 24h 7d 30d Success rate 98.7% 1,301 succeeded Failure rate 1.3% 17 failed / timeout p95 latency 4.7s p50 2.9s Total runs 1,318 3 running Cost $211.84 1.9M tokens Runs per day last 14 days Recent runs Status Started Latency Model Tokens Cost Error running just now — claude-opus-4-8 — — succeeded 2m ago 3.1s claude-opus-4-8 1,540 $0.021 succeeded 4m ago 2.7s claude-sonnet-4-6 1,120 $0.009 failed 6m ago 9.0s gpt-4o 2,310 $0.038 RateLimitError succeeded 8m ago 3.4s claude-opus-4-8 1,705 $0.024 timeout 11m ago 30.0s claude-opus-4-8 980 $0.014 TimeoutError succeeded 13m ago 2.9s claude-sonnet-4-6 1,260 $0.010 Start monitoring free → Explore the live demo → Free for 10,000 events/month · No credit card · See how it all works → WORKS WITH THE STACK YOU ALREADY SHIP Python TypeScript cURL Anthropic OpenAI LangChain LlamaIndex CrewAI One HTTP endpoint, from any language or framework that can send JSON. No SDK required. Is this you? The agent shipped. The hard part started. You hear about outages from customers The agent started failing overnight. You found out from a support ticket the next morning, with a screenshot you can’t reproduce. The token bill keeps creeping up This month cost more than last, and nobody touched the pricing. Something is retrying in a loop and there’s no quick way to see which agent. A prompt tweak quietly tanked quality Success rate slid from 98% to 91% after a small wording change. It shipped last Tuesday. You’re finding out now. Your “monitoring” is a ping check A 200 from the endpoint means the server is awake. It says nothing about whether the agent actually did the job. If two of those landed, you’re who we built AgentSpeed for. Start watching → Setup One POST and you're live 01 Make a key Create a project and generate an API key. We hash it at rest, and the secret shows once. 02 POST a run Send one request from anything that speaks HTTP. Spans and events are optional. A new agent provisions itself the first time it reports. 03 Watch it Health appears right away. Set your thresholds, publish a status page, and get on with your day. No SDK to install. POST /api/v1/runs curl -X POST https://agentspeed.com/api/v1/runs \ -H "Authorization: Bearer $AGENTSPEED_API_KEY" \ -d '{ "agent": "checkout-assistant", "status": "succeeded", "model": "claude-opus-4-8", "inputTokens": 1200, "outputTokens": 340, "costUsd": 0.0185, "score": 0.92 }' Metadata only. Your prompts and outputs stay on your side. Full API docs → Pricing Flat tiers. No per-seat fees, no overage bills. Free $ 0 /mo ✓ 10,000 events/mo ✓ 1 project · 3 agents ✓ 7 -day retention ✓ 1 journey canary · manual runs — watches on paid plans — alert channels on paid plans Start free MOST POPULAR Starter $ 19 /mo ✓ 100,000 events/mo ✓ 3 projects · 10 agents ✓ 30 -day retention ✓ 10 journey canaries · scheduled + alerts ✓ Watches (scheduled site checks) ✓ Slack / webhook / email alerts Continue with Starter → Growth $ 79 /mo ✓ 1,000,000 events/mo ✓ 10 projects · 50 agents ✓ 90 -day retention ✓ 50 journey canaries · scheduled + alerts ✓ Watches (scheduled site checks) ✓ Slack / webhook / email alerts Continue with Growth → Pro $ 299 /mo ✓ 10,000,000 events/mo ✓ 50 projects · 250 agents ✓ 180 -day retention ✓ 200 journey canaries · scheduled + alerts ✓ Watches (scheduled site checks) ✓ Slack / webhook / email alerts Continue with Pro → One event = one ingested row: a run report is 1 + its spans + its log events. Full pricing details & FAQ → Check it once. Watch it forever. The scan is free and takes 30 seconds. Monitoring starts free for 10,000 events a month. Scan my site → Start monitoring free → agentspeed . Monitoring for AI agents: uptime, cost, and latency. Metadata-first, so we never store your prompts or model outputs. Product Observability Live demo Free tools AI-readiness scanner Pricing Why AgentSpeed Developers Docs API reference Embed badge Resources Scoring rubric Learn Leaderboard What's new Privacy agentspeed . © 2026 AgentSpeed Terms Privacy Policy Sub-processors DPA Ask AgentSpeed