Cognition is Sharp to agents.

Item: Cognition API
Rating: Sharp
Author: Discry

Discry independently scored how well an AI agent can discover and understand the Cognition API from what’s public — measuring discovery and comprehension separately, not a single blended number.

Familiarity 60% · what a model knew before reading the docs

Discry your API — free View the docs ↗

Discovery

68 / 100

OpenAPI spec218 endpointsPass

llms.txt17 described linksPass

llms-full.txt685123 tokensPass

AGENTS.mdnot found in repoFail

.well-known/mcp.jsonnot presentFail

MCP registrysmithery match for "devin"Pass

robots.txt AI directivesparsed AI-bot rulesPass

Sitemapnot presentFail

Comprehension

97 / 100

Factual recall2/2 passed

Absence honesty1/1 passed

See your own Discry result.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free