A development story

Software
could see.

ThinkRun began with a stubborn idea: an agent should not have to guess what already happened in a browser.

Follow the evidence
The old way
01 / context evaporates

A bug happens.
Then it disappears.

A screenshot is a postcard from a crime scene. A prompt is a witness statement written after the fact. Both leave an agent to reconstruct the moment from fragments.

app.example.com / checkout

The button failed.
The moment is gone.

By the time the agent arrives, the click, the page state, and the useful evidence have all moved on.

POST /checkout → 500
TypeError: total is undefined
context: not captured
The agent arrives too late
The turn
02 / make a witness

Don’t describe
the browser. Record it.

ThinkRun captures the moment while it exists, then turns it into something an agent can inspect: a time-linked trail of what happened and why it mattered.

thinkrun / browser witnesscapture active
A live trail, not a retelling
clickstateerrorhandoff› click: pay› DOM changed› response: 500› artifact ready
Agent-ready artifact

The moment,
still intact.

  • 00:12The action that triggered it
  • 00:12The response and surrounding state
  • 00:13The error an agent can reason from

The receipt
is the story.

ThinkRun was not sketched into existence in a deck. It was assembled in the work of building, breaking, reviewing, and correcting a browser tool until it could carry context forward.

1,570commits indexed in the development history
551merged PRs found in the commit history
59PRD threads woven into the memory wiki

Record snapshot: repository memory wiki, July 9, 2026. These are history counts, not marketing projections.

The archive
03 / lessons retained

Every hard-won fix
changed the next run.

The product’s history is full of the same discipline it offers users: save the evidence, name what failed, then make the next attempt less blind.

Build log / browser control

The browser becomes a tool

The early work made browser control practical: sessions, actions, and the repeated loop of inspecting a page before acting on it.

Selected from the development archive
The point of the whole thing

Less guessing.
More seeing.

ThinkRun gives an agent a better starting point: not a vague report of a browser moment, but the moment itself—captured, organized, and ready to reason from.

Agent-ready summary
issue: checkout request failed · evidence: click → state → response → error · next step: inspect the captured context
Link copied to clipboard