Skip to content
hotato
Incident Turn-taking Say-do Atlas Docs Evidence Security
GitHub
Home/Writing

Writing

Technical notes from the team behind Hotato, local call forensics and regression guards for AI agents: trace, evaluate, test, and gate any AI agent. Each post starts from a public builder report, names the failure class, and ends at a command you run on one recording.

Both sides can talk at once now. What is your voice test suite still measuring?

Full-duplex moved the failures from wording to timing and floor control. A transcript flattens two overlapping voices into one column of words and throws the timing away.

Read the post →

The transcript passed. The call failed. A walk from a green log to a red gate.

Rank the moments in one recording, label the catch, and keep it as a contract: the walk from a clean-reading log to an exit 1 that gates the next pull request.

Read the post →

Your agent said the refund went through. Only the backend knows if it did.

Say-do grading from trace spans and the system of record, never the model's summary of itself. Includes the authorization and security-state sub-pattern.

Read the post →

Every post ends at the same front door, because the loop starts with one call:

bash
hotato autopsy ./call.wav

Repo: github.com/attenlabs/hotato

hotato

Open-source local call forensics and regression guards for AI agents. MIT. Python 3.9-3.13. Updated July 25, 2026. v1.16.0

Product

  • Docs
  • Getting started
  • Evidence
  • Security
  • Self-host
  • Changelog

Capabilities

  • Incident report
  • Turn-taking timing
  • Outcome & say-do
  • Stack integrations

Resources

  • Failure atlas
  • Atlas feed (JSON)
  • Use cases
  • Writing
  • About
  • GitHub
  • PyPI
  • llms.txt
  • License (MIT)
Built by Attention Labs · MIT · Zero-egress by default