Always-on monitoring of OpenAI's live-search crawler. OAI-SearchBot indexes the pages ChatGPT cites when a user searches the web inside a chat. Independent of GPTBot — sites routinely block one and not the other. Sentry catches the misalignment. Cortex handles the fix.
Continuous audits of OAI-SearchBot's access to your site against the 8 things that decide whether ChatGPT can cite you in live search. OAI-SearchBot is independent of GPTBot; sites routinely block one and not the other. Sentry catches the mismatch. Cortex fixes it.
User-agent: OAI-SearchBot is not Disallowed. This is a separately controllable token from GPTBot. OpenAI honors the robots.txt rule strictly per their published bot policy.
Cloudflare's 'Block AI Scrapers' managed rule is off or has OAI-SearchBot in its allowlist. Bundled blocking with GPTBot is the #1 cause of missing ChatGPT citations on otherwise indexable sites.
Recent visitor IPs claiming the OAI-SearchBot UA match OpenAI's published searchbot.json range list. Separate range from GPTBot's gptbot.json.
Critical content appears in the initial HTML. OAI-SearchBot's Chrome/131 UA fingerprint suggests rendering capability but OpenAI does not publish a render commitment. SSR is the safe path.
No WAF rule returns 4xx/5xx to OAI-SearchBot's `Chrome/131.0.0.0` token. 'Outdated browser' rules sometimes catch it because the pinned Chrome version lags real Chrome by a couple of releases.
robots.txt directives for OAI-SearchBot do not bundle with GPTBot. Publishers wanting indexed-in-search-but-not-training should explicitly differentiate — the most common GEO config error is copy-pasting one bot's rule to the other.
Page-level JSON-LD parses cleanly. ChatGPT search frequently reads structured data to summarize who/what/when of a cited page, lifting citation quality and source-card completeness.
Server logs show an OAI-SearchBot fetch within the last 30 days, confirming the page remains in OpenAI's live-search index. OpenAI notes propagation can take roughly 24 hours after a robots.txt change.
Paste your homepage URL. Sentry verifies robots.txt allowance for the separate OAI-SearchBot token, Cloudflare AI Audit posture, OpenAI IP-range fidelity, SSR reachability, and last-fetch recency, then ships a per-rule report. No signup, instant results, always free.
Sentry fetches your site, runs every OAI-SEARCHBOT rule, and renders the full result page before your next sip of coffee.
Each failed rule ships with a prescription paragraph. Hand it to engineering and the gap is closed before lunch.
Add your site to the daily Sentry sweep with one click. New regressions get caught the next morning.
8 rules in the OAI-SEARCHBOT Sentry. Daily 3:30 AM ET sweep.
One brain. Thirty-six pairs of eyes. Sentries monitor every visibility signal that decides whether search engines, AI engines, and ad platforms show you. Cortex reads what they see, weighs it against a unified corpus of platform documentation, and acts. Every move follows a defined decision protocol: action stated, reason given, impact named.