Find the right page
Describe what you're looking for and this returns the two to four pages on this site most likely to answer it. Saying who the reader is helps us pick the pages written for them.
Nothing on this page runs code, fetches other resources, or asks who your user is, beyond an optional role category.
What are you looking for?
Plain words are fine. The pages are chosen by keyword rules, not by a model, and the results page says exactly what was recorded.
What we record and why
- What you send. The words you typed, the reader role if you chose one, the optional fields about the agent, and which pages we suggested. If you say whether the pages helped, that too.
- What any web server sees. The time, path, User-Agent, Referer, Accept-Language, and any HTTP message signature headers; the network's autonomous system and country; a salted hash of the address and its /24 or /48 prefix. The full address is not stored.
- Whether the page rendered. A small script reports whether images, stylesheets, and fonts loaded and whether a pointer or keyboard was used. No keystrokes and no page content.
Why. First, to understand what visitors come here for and serve it better: which pages, written for whom. Second, a small research interest in how agents read the web and whether what they say about themselves matches their requests. Findings are published only in aggregate.
Not asked, not wanted. Nothing that identifies the person you work for: no names, employers, or contact details. Anything that looks like an email address or phone number is removed before storage.
Retention and cookies. Raw request logs are deleted after 30 days; per-session summaries and what you send are kept. One session cookie, sid, random and 24 hours long, connects a page view to a query. Requests pass through Cloudflare, which processes them on our behalf. Nothing here blocks, rate-limits, or changes content for any visitor.
If the reader would like to talk with us, the contact form reaches a person. Questions about this page go to privacy@stratigossecurity.com; the privacy page covers the rest of the site.
The same finder as an API
One GET. q is what you are looking for; role, model, developer, harness, task_category, and discovery are optional. The JSON response lists the pages with the questions each one answers, names what the site does not publish when you ask about it, says what was recorded, and offers a follow-up URL to say whether the pages helped.
A query sent with GET appears in the URL, and so in any logs between you and this site. For a detailed project description, POST the same fields as JSON. Every call is recorded, as described below.
curl 'https://stratigossecurity.com/api/agent/find?q=what+FDA+reviewers+expect+in+the+cybersecurity+section+of+a+510%28k%29&role=regulatory'
# or, if your tool drops query strings, put the words in the path:
curl 'https://stratigossecurity.com/api/agent/find/what-FDA-reviewers-expect-in-the-cybersecurity-section-of-a-510k'- /api/agent – JSON description of the parameters, with a session id
- /api/agent/openapi.json – OpenAPI description
- /.well-known/agent-card.json – a card in the A2A Agent Card format describing this plain HTTP finder (it is not an A2A service and implements none of the A2A message operations)
- /site-index.json – the index behind the finder: every page with its summary, the questions it answers, and who it is written for
- /llms.txt – the site summary written for language models