Making your site ready for Agents

How well your site can be found, understood and used by an AI agent — ChatGPT, Gemini, Copilot… — acting for a user, without ever rendering your pages. We measure it across 27 technical signals grouped into 4 tiers, from a site invisible to agents to one that is fully usable.

SEO optimises what a human sees after clicking a link. Here there is no page and no click: the agent reads structured data and files, tests access, and decides on its own what to do with it. A site with excellent SEO can be completely unusable by an agent — and the reverse is true too.

Any site, whatever the sector or the technology: e-commerce, SaaS, media, public sector, non-profit… The audit reads what is public — well-known files, structured data, how pages actually behave — and tells you where you stand. Some advanced analyses target specific cases, such as agentic commerce over the UCP protocol, and only run where they make sense.

The agent-readiness audit — all 27 signals — is free and unmetered, with no card required. Only the analyses that run a language model or call a third-party API (agent simulation, Agent Performance, resource discoverability) have a capped volume on the Growth plan. See the pricing table above.

Agency costs €79 per month or €790 per year. It includes up to 6 sites and 300 simulations per month shared across sites, team and client access, and private revocable branded reports. Each pack beyond that adds one site and 50 monthly simulations for €12 per month or €120 per year.

Never — and this only concerns the shopping-agent simulation (the Commerce axis). The agent creates a real cart and opens a real checkout to measure how far it can get, then stops dead: no payment is triggered, no card data is handled, and test carts are abandoned. That is a hard rule of the engine, not a configuration option.

A few seconds to a minute for the agent-readiness audit. Allow one to two minutes more if you add the agent simulation, which runs several dialogue turns against your site.

It is the average of the checks that ran, each scored out of 100: above 85 you are fine, between 60 and 84 there are things to fix, below 60 something is blocking. Analyses that sample — a product catalog, for instance — replay the same deterministic draw for as long as nothing has moved, so that a score change signals a real change, not an artefact.

Yes. The CLI runs with no install and fails the job when the Commerce score drops below your threshold; a public badge shows the latest Agent Readiness tier in your README; and the API is driven by a key generated from your account. All of it is available on the free plan.