The Agent Readability Standard

Your documentation has a new reader. It isn't human.

It doesn't skim, guess, or watch the walkthrough video. An AI agent fetches your page, parses the text, and either completes the task — or gives up. Prolectio scores how well agents can actually read and use your API docs, on a 0–100 scale.

https://
Public pages only · robots.txt respected · a report in minutes
prolectio · live scan
What a human sees

Create a payment

POST /v1/payments
Authorization: Bearer •••
{ "amount": 4200 }
What the agent receives
h1 "Create a payment"
auth [not on page]
endpoint POST /v1/payments
params [rendered by JS]
example partial
task cannot complete
Same page.
Two very different readers.
47
leading platforms scored in Index #1
79/100
median agent readability — most docs are only workable
3cat
structure, clarity & real task completion
1
scored in the red. Many more sit close behind.
The shift

The same page, read two completely different ways.

Documentation has been written for humans for thirty years. But a fast-growing share of the traffic hitting your docs is agents acting for a developer — and they read nothing like a person does.

Human reader

Forgiving. Resourceful. Patient.

Renders the whole page in a browser, skims, infers intent, and fills the gaps with a search, a forum post, or a support ticket.

  • Tolerates ambiguity and missing steps
  • Sees JavaScript-rendered content
  • Asks a colleague when stuck
Agent reader

Literal. Fast. Unforgiving.

Fetches the raw page, parses the tokens it receives, forms a plan, and calls the API — or abandons the task the moment the page can't answer it.

  • Needs auth, limits & a runnable request, stated plainly
  • Often sees only what loads without JavaScript
  • Doesn't guess — it stops
0READABLE SCORE
Red <50Amber 50–79Green 80+
The Agent Readability Score

One number an agent can trust — built from three.

Task completion is weighted over surface structure: you can't top the Index by dropping in an llms.txt and calling it done.

40%

Deterministic checks

Are the machine-checkable fundamentals present and valid — llms.txt, OpenAPI, auth examples, token budget?
35%

Clarity, graded by model

Can an agent finish the page's stated task from that page alone? Clarity, completeness, consistent terms.
25%

Real task probes

A live agent tries three standard jobs — find auth, find limits, build a first request — graded on substance.
The Agent Readability Index #1

We scored 47 platforms your agents already read.

An open, reproducible benchmark of public developer documentation. Here are the platforms that ship docs an agent can read cold.

How it works

Scan, score, and get the fix — reproducibly.

STEP 01

Scan

We crawl your public docs as an agent would — one request a second, robots-respecting, no logins. A snapshot is captured so every score is reproducible.

STEP 02

Score

Three categories, a pinned model, and full provenance — the exact prompt and output stored with every result. The methodology is published and versioned.

STEP 03

Fix

A specific, ranked list of what an agent couldn't read — the missing auth example, the JS-only reference, the rate limit buried in prose — with the transcript that proves it.

Earn your score

Make your docs the ones agents can actually use.

Scan your documentation, see exactly where an agent stalls, and ship the fixes. When you clear the green bar, show it.

Agent Readable92Prolectio