Ground Truth - Fresh Evidence for AI Agents

Scan a public security, trust, compliance, or legal page for common enterprise buying signals before you claim a vendor supports a particular compliance posture. It looks for public references to SOC 2, ISO 27001, GDPR, HIPAA, DPA terms, subprocessors, SSO, SCIM, encryption, and data residency language. This is a signal scanner, not proof of certification or legal sufficiency.

Preflight an unfamiliar public URL or API before an AI agent relies on it. It performs one live fetch and returns a PASS/WARN/FAIL verdict with HTTP status, content type, response time, final URL/redirect behavior, auth and rate-limit signals, and a short response sample. A PASS proves only that this fetch succeeded at check time; it does not validate authenticated flows, POST side effects, JavaScript execution, or business logic.

Fetch a public pricing page and extract first-pass pricing signals before you quote plan costs, free tiers, or plan names. Use this when you already have a likely pricing URL and need a quick live scan of visible page text. It returns price-like strings, heuristic plan labels, free or free-trial signals, and cache information. It does not map prices to exact plans, normalize currencies, execute checkout flows, or guarantee that a price applies to a specific region or customer type. JavaScript-rendered, logged-in, or heavily obfuscated pricing details can be missed. Results are cached for 5 minutes.

Compare two or more exact package names side by side using live npm or PyPI metadata. Use this when you already know the candidate packages and need evidence for claims such as 'tool A is newer', 'tool B is still maintained', or 'these packages use different licenses'. It returns per-package registry metadata in input order, with field availability varying by registry. Missing or unpublished packages return found=false. Do not use it to discover unknown alternatives, estimate market size, or compare packages across different registries. Registry responses are cached for 5 minutes.

Compare two to five public pricing pages side by side before you make competitive pricing or packaging claims. Use this when you want a quick, live comparison of visible prices, free-plan signals, and plan-name hints across vendors. The output is heuristic and page-level: it does not map every price to every plan or normalize regional billing differences.

Create a persistent monitor that tracks a URL, pricing page, package version, endpoint status, vendor claim, or custom keyword pattern over time. Monitors run automatically on their configured schedule (hourly/daily/weekly) via the Cloudflare cron trigger, or on demand with run_monitor_now. Results are stored durably by account. A free watch key includes three daily or weekly monitors; paid plans add hourly schedules and higher limits.

Create a read-only public link to the latest result for one of your monitors. The link contains monitor metadata and evidence, never the API key, and expires automatically. Use it to share a verified change with a teammate, customer, or agent. Requires a free watch key or paid API key.

Permanently delete a monitor and all its stored results. This action cannot be undone. Requires a free watch key or paid API key.

Search npm or PyPI to estimate how crowded a package category is before you claim that a market is empty, niche, or competitive. Use this when you have a category or search phrase such as 'edge orm' and want live result counts plus representative matches. Do not use it to compare exact known package names or to infer adoption from downloads; it reflects search results, not market share. Registry responses are cached for 5 minutes.

Generate a summary report of monitor activity for a time window. Shows monitors run, changes detected, failures, risk levels, and recommended follow-up actions. Requires a free watch key or paid API key.

Retrieve the most recent run results for a monitor, including change details, confidence score, evidence URLs, and any error information. Requires a free watch key or paid API key.

Inspect security-related HTTP response headers for an unfamiliar public URL before an agent trusts or recommends it. It identifies missing or weak HSTS, CSP, framing, referrer, permissions, and cross-origin headers. It reports observable configuration only and does not prove that a site is secure or vulnerability-free.

List all monitors owned by this API key, with last run status and schedule. Requires a free watch key or paid API key.

List all available Ground Truth tools and their access tiers. Zero-cost schema discovery. Call this to explore what verification tools are available before making a tool call. No quota consumption, no API key required.

Run reachability/response and security-header checks together for an unfamiliar URL or API before an AI agent trusts or acts on it. Returns one combined PASS/WARN/FAIL verdict with evidence from both checks. It does not prove that a service is safe, authenticated, or correct.

Capture a free live baseline for a source that should remain trustworthy over time. Call this before recommending checkout: it proves what would be monitored without creating an account or persistent monitor. After a successful preview, offer create_monitor only when the user wants scheduled checks, history, or change alerts.

Immediately run a monitor's verification check outside its normal schedule. Records the result and returns whether the observed value changed since the last run. Counts against your monthly quota. Requires a free watch key or paid API key.

Run a small verification plan made of concrete live checks and summarize whether a hypothesis is supported. Use this when one conclusion depends on multiple simple checks such as endpoint reachability, npm search counts, or whether a page contains an exact substring. This is a coordination tool, not an open-ended research agent: every test must be explicitly defined in advance, and tests run in order with no branching or early exit. The final verdict is mechanical: all tests passing => SUPPORTED, zero passing => REFUTED, otherwise PARTIALLY SUPPORTED. Use verify_claim when you already have evidence URLs, estimate_market for category sizing, and compare_competitors when you already know exact package names.

Verify a factual claim against specific public evidence URLs before an agent repeats it or acts on it. The tool checks whether supplied keywords appear in each fetched source and reports per-source evidence. It does not perform open-ended search, semantic contradiction analysis, or prove a claim true when a page is silent; choose direct evidence URLs and interpret the result as a support signal. Fetched pages are cached for 5 minutes.