Use case · QA and support

Bug reports your AI agent can act on.

A tester files what they saw; the agent receives what it needs. The console, the environment and the exact element travel with the report — so the first question back isn't “where exactly?”

A bug report is a guess
until someone opens DevTools.

“doesn't work on my machine”, with no console attached
a screenshot of the whole window, cropped by hand
steps to reproduce, written from memory an hour later
the ticket coming back with “which element?”

File it by pointing at it.

Filed where it happened,
not in a form afterwards.

1 · The tester pins what they saw

On the page where the bug is, at the moment it's on screen. A severity and one sentence — the rest is captured for them.

2 · The proof attaches itself

Screenshot, selector, computed styles, HTML, console output, URL, viewport and platform. Nothing typed by hand, so nothing is missing an hour later.

3 · Everything lands on one board

Filter by open or fixed, by severity, by page. The team and the agent read the same list, so “is anyone on this?” stops being a question.

4 · The agent fixes it and answers

It greps the repo for the selector, lands the change and replies on the pin with what it did. QA accepts or reopens — the report closes where it was filed.

The report the agent
would have asked for.

Everything a developer would have opened DevTools to collect is already in the ticket. The agent starts on the first read instead of the third.

Claude Code · via MCP: “Guarded the empty cart state in CartSummary.tsx — the console error was a null read. Commit 41b0e7.”

Same bug, two reports.

Before

  • “checkout is broken”
  • a screenshot of the whole screen
  • repro steps written from memory
  • three round-trips before work starts

With Handoff

  • a pin on the element that failed
  • console error and environment attached
  • the page, the viewport and the platform recorded
  • the agent starts on the first read

What a report looks like when it isn't prose.

The first pin below reports an unreadable button on our demo product — with the selector, the measured contrast and the element's own screenshot attached, which is what an agent needs to find the code.

Open the Details on a pin to see the styles and HTML that travelled with it.

What is a bug report for an AI agent?

A bug report for an AI agent is an ordinary bug report with the browser context attached — the element, its computed styles, the console output, the URL and the viewport — in a form the agent can read directly rather than parse out of prose.

Traditional bug reports are written for a human who will reproduce the problem: they describe a path, and the reader opens DevTools to find the rest. An agent can't reproduce anything. It has the repository and whatever the report contains, so every detail left out of the report becomes a question, and every question is a round-trip.

In practice this changes who does the work of collecting evidence. The tester points at the failing element; the extension captures what a developer would have gathered by hand, and the agent receives it over MCP. The report stops being a description of the bug and becomes the bug's context.

Questions

Does the tester need to know CSS?

No. They click the element that looks wrong. The selector and styles are captured for them.

Does it work on staging and behind a login?

Yes. Handoff runs in the browser, so it sees whatever page the tester is on — staging, production, or a page that needs a session.

What if the bug is in the console, not on screen?

Console output is captured with every pin, and a pin can be filed on the page as a whole rather than a single element.

Can the agent close the report itself?

It marks the pin resolved and writes what it changed. A person accepts or reopens — resolution isn't the agent's decision alone.

Do we need a separate bug tracker?

Not for this loop. Pins live on a board with severity and status. If you already have a tracker, the pin's page link and context paste into it cleanly.

Stop writing repro steps from memory.