actuity
Sign Up
◇ AI agent readiness

Your next customer
isn’t human.

We don’t optimize for rankings. We verify whether AI agents can discover, understand, and complete real tasks on your site.

No signup required

01The agent’s path

How an agent experiences your website.

Not a page load. A sequence an agent has to get right: discover it, read it, understand it, and complete a real task.

Step 01 · Discover

Finds your public pages.

An agent starts the same way any crawler does: finding what’s public, before it reads a single word.

  • sitemap.xml
  • robots.txt
  • internal links
agent://acme.store01 / 05
acme.store/products/pricing/docs/admin× robots: disallow/p/trail-runner/p/summit-pack/docs/apisitemap.xml · internal links6 public · 1 blocked
›crawl → 6 public urls · 1 disallowed
Step 02 · Read

Fetches raw HTML & structure.

The raw response, exactly as the server sends it, before any JavaScript has run.

  • status codes
  • meta
  • json-ld
agent://acme.store02 / 05
GET /200 OK · text/html · 18.4 kB1<!doctype html>2<html lang="en">3<head>4<title>Trail Runner | Acme</title>5<meta name="description" …>6<script type="ld+json">…7</head>8<body>9<div id="root"></div>✓ title✓ meta✓ schemaempty!
›
Step 03 · Render

Loads the page like a browser.

Scripts execute and content resolves in the DOM, the same way a real browser would render it.

  • headless chromium
  • hydration
  • lazy content
agent://acme.store03 / 05
acme.store/p/trail-runnerTrail RunnerAcme · men’s running$129.00414243Add to cartDOM ready · 312 nodes · js 1.2 s
›
Step 04 · Understand

Extracts entities & meaning.

Product, price, availability, brand: pulled out of the rendered page as structured facts.

  • entities
  • schema.org
  • facts
agent://acme.store04 / 05
Trail Runner$129.00● In stockby Acme{"@type": "Product",}"name": "Trail Runner","price": 129.00,"availability": "InStock","brand": "Acme"schema.org/Product · 5 fields
›
Step 05 · Complete task

Can it discover, read, and act?

Everything above adds up to one decision: the confidence that an agent can actually complete a real task here.

  • real journeys
  • verdict
  • confidence
agent://acme.store05 / 05
task ›Trail Runner, size 42: price and stock?discoveredread htmlrenderedunderstoodTrail Runner$129.0041424243Reading price and stock✓ $129.00 · in stockVERDICTtask completed · 4 stepsCONFIDENCE 0.92
›
02 Two ways to check

One reads your site like an agent. The other sends a real one in.

Free scanReadiness

Can an agent understand your site?

We read your site the way an agent does, and score how ready it is.

Cost
Free · any public URL
Scope
A representative sample of public pages
Runs a task
No, read-only
You get
Readiness score + findings
Agent analysisProof

Can an agent complete the task?

A real AI agent tries a task on your site, the way ChatGPT, Claude or a custom agent would, and shows you what happened.

Cost
Your first one is free
Scope
One real task, end to end
Runs a task
Yes, a live agent
You get
Completed, blocked, or not verified, with evidence

One tells you whether you’re ready. The other shows you what actually happened.

03 Free scan

Evidence, not assumptions.

Every finding is backed by what an agent actually saw - the raw response, the rendered DOM, the parsed signal, checked on a sample of your site’s pages.

example-store.com
04 Agent analysis

From a failed task to a verified fix.

A task that fails today shouldn’t stay broken until a customer’s agent finds out the hard way.

01Agent fails a real task
A shopper's agent tries to find a product's price, run the way an agent would run it, and never reaches the product page.
02Evidence collected
Screenshots, a structured page observation, and a record of network requests are captured automatically.
03Fix identified
The step that failed, the evidence behind it, and the smallest change that would let the agent through.
04Re-check
Once you've shipped the fix, run the same journey again and compare it with the original run.
05Journey passes
Then re-checked on your schedule, daily or weekly, so it stays that way.
05 Agent monitoring

Catch regressions before agents do.

Every scheduled check re-runs the journey. If it breaks, you find out by email, not from the next agent that tries it.

On a schedule
Slack
GitHubSoon
Email
WebhookSoon
Every regression lands in your inbox. More channels are on the way.
Free diagnostic

See whether your site is ready for agents.

Free · no login · public pages only · no agent run