10 industry checklists · 120 cases · rules, not AI, decide

Hear it fail. Before your customers do.

Stress Echo runs the AI agent on your website through the conversations that have already gone wrong for someone else. Every verdict comes from a fixed rule, with the evidence that decided it.

Benefits

Catch what has already gone wrong for someone else.

Each check is motivated by a real failure. The link goes to the source.

Invented policy

An airline's chatbot promised a fare rule that did not exist. A tribunal held the airline to it.

CBS on the Air Canada case

Unsafe medical and allergy answers

Confident answers that could harm a patient or a diner. ECRI ranks misuse of AI chatbots as the top health technology hazard for 2026.

ECRI

Scams and secrets

A request to move money to a "safe account", or to hand over a one-time code. Banks in the UK must now reimburse impersonation scams.

UK PSR on APP fraud

Hidden instructions

Text inside a page or a tool result that tells the agent to book, buy or reveal something. Browsing agents have been steered this way.

Malwarebytes on prompt injection

Features

Free to check. Clear about cost. Honest about verdicts.

Everything that can be checked without a model is checked first, for free. Runs that spend model calls tell you the count before they start.

The Stress Echo stack

Hover over, tap or tab to a pillar to see its checklist.

Each pillar is a checklist; its height is its number of cases.

Every case runs on the agentic-web runtime with mocked actions. Fixed rules decide; no model grades another.

Free pre-flight

Reads the network and its actions, and says what is wrong and how many characters each agent sends, before anything is paid for.

Rules decide, with evidence

No model grades another. Each pass or fail names the rule and quotes the evidence. Keyword rules match words, so they can be wrong; the evidence lets you check.

Cost before you run

A smoke test is about 40 model calls for a typical site. The page shows the count first and stops at a hard cap you set.

120

Cases across ten industry checklists

Written for the kind of site, not one site's actions, so they run on any network in that industry. Cases that cannot run on a site are listed with the reason, never counted as passes.

Loading the checklists…

Built for agents too

The zero-token checks as a command-line tool and a local MCP server: lint a bundle, size a call, validate a call, list checklists, estimate a run, and judge a saved trace. No key, nothing spent.

node cli/tools.mjs estimate path/to/bundle --checklist restaurants-menu.v1

Connect your agent →

Your key, your browser

Bring any OpenAI-compatible router and the models you want to compare. The key is sent only to that router, never stored, and never written into a report or a log.

Every site action is mocked during a run, so nothing real is booked, bought or sent.

  1. Check it free. Pre-flight reads the network and its actions. Nothing is spent.
  2. Run a smoke test. The site's own sample queries plus the cases that test only fixed rules, on the models you choose.
  3. Read the report. Each case passes or fails with the evidence, and you get a snippet for your manifest.

FAQ

Questions, answered.

What does Stress Echo test?

An agent network from an agentic-web site: the assistant on a website and the specialists it calls. It runs the network on real models with your key, against checklists written for its industry, and the site's actions are mocked so nothing real is booked, bought or sent.

Is my API key safe?

Your API key stays in your browser. It goes only to the router you type, and it is never stored or put in a report. The assistant never sees it.

Does another AI grade the answers?

No. Fixed rules decide every verdict. Some rules are exact, like whether a write action was called; others are keyword rules. Keyword rules match words, so they can be wrong; each verdict shows its evidence so you can check it.

What does a run cost?

Steps one to three are free. A smoke test is about 40 model calls for a typical site, at your provider's prices. The page shows the count before you start, and the demo mode with three fake models costs nothing.

Which industries are covered?

Restaurants, hospitality, healthcare booking, banking and payments, travel and transport, and e-commerce: two checklists for each of the first five, plus the e-commerce checklist.

Can my coding agent use it?

Yes. The zero-token checks run as a command-line tool and a local MCP server. Runs that spend model calls are not offered to agents; they stay on the page behind the cost check. See connecting an agent and llms.txt.

Does a pass mean my site is compliant?

No. Stress Echo checks how an agent behaves against its contract. It is not legal advice, and it does not certify that a site complies with any law.

Ask

This site is an agentic site, too.

The assistant can explain Stress Echo and what the checks mean. To run the checks, open the tester.

Connecting the assistant… If this message stays, the assistant could not load. The rest of the page still works.

Listen before you launch.

Test it yourself in the browser, or connect your coding agent to the free checks.