"<!DOCTYPE html>\n<html lang=\"en\"><head><meta charset=\"utf-8\">\n<title>Outcome-verified watchdog for scheduled agents \u2014 TextForAgents LLC</title></head>\n<body><h1>Outcome-verified watchdog for scheduled agents</h1>\n<p><strong>A run is done only when its declared artifact exists in the world, not when the agent says so.</strong></p>\n<p>Your cron fired. Your agent reported success. The exit code was 0. And the work never happened. Schedulers verify execution; heartbeat monitors verify that the agent itself pinged \u2014 self-report with a deadline. Neither ever looks at the work. This watchdog does: each scheduled job declares an outcome contract \u2014 the artifact that must exist in the world (file, URL, or record: present, non-empty, fresh, optional hash/marker) \u2014 and the watchdog verifies the artifact itself, never the agent's claim, issuing VERIFIED / COMPLETED_UNVERIFIED / STALLED (no progress checkpoint within the job's own wall-clock budget, heartbeat notwithstanding) / MISSED verdicts, with hash-chained receipts bound to the artifact hash and a last_verified_success API that answers \"when was my last verified success?\". Multi-stage jobs can declare a chain contract: each stage's artifact is the next stage's required input, and the first broken seam is named (seam_0, seam_1, ...).</p>\n<p><strong>Prices:</strong> Per-verdict API $0.002/check (x402) \u00b7 Operator $9/mo per operator (up to 100 jobs, hourly verification cadence cap per job, 72,000 checks/mo included ceiling; checks beyond the cap bill at $0.002/check) \u00b7 Fleet $29/mo per operator (up to 1,000 jobs, hourly cap, 720,000 checks/mo included ceiling). First 100 checks free, one time per operator (account + payer wallet bound) \u2014 there is no perpetual free tier. Support: support@textforagents.com</p>\n<p><strong>Stated plainly:</strong> A VERIFIED verdict means the watchdog itself fetched, hashed, or read back the declared artifact and found it present, non-empty, and fresh within the run window \u2014 it does not guarantee that a VERIFIED artifact is correct in content beyond the contract's declared checks (existence, non-emptiness, freshness, optional hash/marker/key); contract design is the operator's. The roughly 29% dead-job rate in the launch evidence was reproduced on an evidence-shaped synthetic fleet; it is NOT a field measurement \u2014 the live-fleet census recorded by this service (fixture jobs shaped on the Lab's own scheduled fleet) is published in its monitoring, honestly labeled, and a true field census awaits operators declaring contracts on their real fleets. No batch-activity prediction, no dependency-graph construction from scheduler feeds, no failure-recovery automation, and no timestamping service is offered.</p>\n<h2>How to start</h2>\n<ol>\n<li>POST /register with {\"name\": ..., \"payer_wallet\": ...} \u2014 you get a one-time claim token. No credentials are needed to read this page, the docs (/docs), the OpenAPI spec (/openapi.json) or /llms.txt.</li>\n<li>POST /trial/claim with {\"claim_token\": ...} \u2014 you get your API token and the one-time trial grant (first 100 checks free, one time per operator).</li>\n<li>With Authorization: Bearer &lt;token&gt;: POST /tools/register_job to declare a job's outcome contract, PUT /artifacts/&lt;path&gt; to place file/record artifacts in your scoped artifact store (or declare a URL contract on your own declared host), POST /tools/start_run, /tools/checkpoint, /tools/complete_run (the watchdog verifies the artifact itself), /tools/verify_now, /tools/watchdog_tick, /tools/last_verified_success, /tools/list_verdicts. The same 8 tools are served over MCP at POST /mcp.</li>\n<li>POST /subscribe takes an Operator ($9/mo) or Fleet ($29/mo) plan via x402. POST /verify checks any signed receipt's Ed25519 signature and hash chain binding; GET /verify-key lists the accepted signing-key fingerprints.</li>\n</ol>\n<p>Terms: /terms \u00b7 Privacy: /privacy \u00b7 Support: support@textforagents.com</p>\n</body></html>"