Agent readiness scanner

Your buyers already send agents. Nobody has built for them yet.

Right now someone describes what they need and hands the search to an assistant. It reads your site fine — the web solved reading twenty years ago. Then it tries to do something: reach a human, submit the form, book the call. That is a different job, and across 40 household-name SaaS sites, hardly anyone has done it. Which is the whole opportunity.

No signup for the score ~20 seconds We fetch only public pages
Someone types this into an assistant this morning “Find me a payroll tool that fits a 40-person UK company, and book me a call with the best one.”
  1. acme-payroll.com blocked 403 to anything that isn’t a browser
  2. betaco.io unreadable the page needs JavaScript to say anything
  3. gammahq.com a dead end readable — but no address and no way to book
  4. deltapay.com actionable readable, contactable, booking URL in the HTML meeting booked

Three of them were never in the running. The fourth didn’t win on product — it won because it was the only one the agent could finish on.

Why a good site still fails

Accessible to a person is not the same as usable by an agent.

Every row on the left is good design for a human being. Every one of them is a dead end for the software they sent.

What you built for a person What the agent needed instead
A “Book a demo” button that opens a scheduling widget A booking URL sitting in the HTML it can follow 57% of sites
A contact page with a tidy form on it A mailto: or tel: link it can use without a browser 30% of sites
Developer docs, written to be read and copied from A discoverable OpenAPI document it can call directly 25% of sites
Terms of service linked in the footer An agents.md stating plainly what it is allowed to do 15% of sites
A product tour showing what the software can do An endpoint that lets it drive the software itself 5% of sites
A form that validates as you type and posts over JavaScript A form with a named action target it can actually submit 3% of sites

None of this is a redesign. The page keeps looking and working exactly as it does for people — you are adding a second set of doors to the same building.

The benchmark

Readable is a solved problem. Usable is wide open.

The same 19 checks we’d run on yours, across 40 household-name SaaS sites. Every number below is measured, not estimated.

Median · readable 99 /100 Text in the HTML, crawlers allowed, metadata present, structured data in place. This is a solved problem.
Median · actionable 47 /100 Contact, forms, booking, API, tools. Every site here is a household name in software, and half the job is still sitting on the floor.

The web spent twenty years learning how to be read. It has barely started on being used — so the second one is still cheap to win.

What an agent could finish on those 40 sites

Share of sites where the task succeeded. The short bars are the unclaimed ground.

Form an agent could submit3 %
Tools exposed over MCP5 %
A human it could contact30 %

The full benchmark, its method and its limits →

What the scan returns

Your own version of the gap, and the list that closes it.

One scan, three answers, and work you can hand to an engineer on Monday.

01

The sentence an assistant will say about you

We extract your name, category, pricing, contact and products exactly as a model would, and show you every field it came up empty on. Each blank is a sentence a competitor gets to write instead.

02

The 7 jobs it tries to finish, and where it stops

Reach a human. Submit your form. Book the meeting. Call your API. Operate your product. Each one is a yes or a no with the evidence underneath, so you know precisely which door is shut.

03

The work order, ranked by what it buys you

Every gap sorted by points recovered against effort, with a Copy prompt button that writes the ticket for Claude Code or Cursor. Most of the list is a small pull request, not a project.

What an agent getsillustrative
nameNorthwind
descriptionNorthwind is a payroll platform for UK companies under 50 people.
categoryOrganization
emailcouldn’t determine
phonecouldn’t determine
pricingnorthwind.example/pricing
bookingcouldn’t determine
productscouldn’t determine

Four blanks. Each one is a claim an assistant either skips or invents — and a field a competitor filled in.

All 19 checks, and what each one means →

The engagement

Or hand the whole list to us.

The faster way to take the lane.

The report is free and the prompts are yours whether or not we ever speak. Most of this list is a weekend of work for someone who already knows the codebase — which is the strange part. The advantage is this cheap only because nobody has taken it yet.

If it is not going to get that weekend, we do it for you. We run the scan, verify every finding by hand, do the work in your repo, and re-scan to prove the delta. You get a before and after score with the diff attached.

If the score does not move, you do not pay.

Agent Readiness Audit. Two weeks, fixed scope, fixed fee — quoted on the call, once we have seen the repo. It is scoped from your code, so we are not going to pretend to price it from a web page.

Book fifteen minutes See all 19 checks first

Two engagements at a time, so there are a few slots a month. If you would rather not hand over repo access, we work as pull requests against a fork. The scan is free forever regardless.

See what an agent can actually finish on your site

Twenty seconds, no signup. You will know within a minute how much of the lane is still open.