◎ Discry Score
aiception.com.com
ai · API
F
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #43 OF 43

aiception.com is Not Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the aiception.com API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 12/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Fail
llms.txtAn llms.txt index that points agents to the docs that matter.Fail
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Fail
llms-full.txtA full-text bundle agents can load in one request.Fail
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Fail
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Partial
SitemapA sitemap so agents can enumerate the docs surface.Partial

Comprehension

55% of score · 0/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Fail
Realistic examplesRunnable, real-world request/response examples.Fail
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Fail
Error-recovery guidanceDocumented failure modes and how to recover from them.Fail
Answer-first formatThe answer leads; preamble does not bury it.Fail
Capability boundariesClear limits — what the API can and cannot do.Fail
Naming consistencyConsistent, predictable naming across endpoints.Fail
Heading hierarchyClean heading structure agents can navigate.Fail
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Fail
Token efficiencyDocs are concise enough to fit an agent context window.Fail

What we found

  • AIception is no longer an API product. The domain now hosts a WordPress marketing site for an AI/ML consulting agency; an agent sent here to find the legacy AIception computer-vision API finds no endpoints, no docs, and no indication the API still exists.
  • The site sits behind an anti-bot challenge: a standard fetch of the homepage returns a 'Robot Challenge Screen' captcha page, so most AI agents are turned away before reading any content — a browser-grade stealth fetch was required to reach the real page.
  • Zero agent-discovery surface: llms.txt, llms-full.txt, .well-known/mcp.json, AGENTS.md, and any OpenAPI/Swagger spec are all absent, and no MCP registry (Glama, Smithery, PulseMCP) lists it.
  • The only positive signals are WordPress hygiene artifacts: a permissive robots.txt with no AI-bot blocks and an auto-generated sitemap — but the sitemap lists just 4 marketing pages and neither leads an agent to API documentation, because none exists.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Delist aiception.com from public API directories or publish a clear deprecation notice for the legacy computer-vision API — agents chasing stale directory references currently hit a captcha wall and a consulting brochure.
  2. 02If any programmatic offering still exists (e.g., the AI-as-a-Service referenced in the PubNub case study), publish developer documentation with an OpenAPI spec at a standard path such as /openapi.json.
  3. 03Exempt AI crawlers (GPTBot, ClaudeBot, CCBot, etc.) from the bot-challenge WAF so actual access matches the permissive robots.txt policy.
  4. 04Add an llms.txt describing current services and linking to the key pages, so agents that do get through can learn what the company now offers.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

✕ Error format documented✕ Rate limits documented✕ Pagination documented✕ Idempotency documented

No API documentation exists anywhere on the site. There is no auth, error-format, rate-limit, pagination, or idempotency documentation of any kind — aiception.com is a consulting-services marketing site with no developer surface.

See your own Discry Score.

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

Discry your API — free