AQuA (Ambient Quality Agent)
AQuA is an ambient quality agent that samples production agent sessions, reviews them for failures, clusters and verifies findings, and tracks issues across runs. It can analyze failures against an immutable source snapshot and propose code-anchored edits, but it does not apply edits or open pull requests.
What it does
Teams can use AQuA to find recurring quality issues in production agents and investigate their likely causes.
- Availability
- Released in the open as composable building blocks; deployment instructions use agents-cli.
- Pricing model
- Not established
- Deployment
- Runs in your Google Cloud project.
- Privacy
- Raw session transcripts, source snapshots, and BigQuery tables stay inside your project boundary; AQuA does not sit in the request path or write back to your agent.
- Licence
- Not established
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- AQuA is released in the open as composable building blocks that teams can run in their own project and adapt to their stack. [1]
This post covers the outer loop, released in the open as composable building blocks you can run in your own project, adapt to your stack, and help us shape as we explore how teams run continuous agent quality in production.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - AQuA can sweep production trajectories from Cloud Trace, Cloud Logging, or BigQuery on a schedule, after each deployment, or on demand. [1]
AQuA (Ambient Quality Agent) runs unattended beside your agent in your Google Cloud project, sweeping production trajectories from Cloud Trace, Cloud Logging, or BigQuery on a schedule, after each deployment, or on demand while your laptop is closed.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - Each run samples up to 1,000 recent sessions and reviews them against a nine-point checklist. [1]
Each run reads a sample of recent sessions and puts it through a five-stage pipeline:
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - AQuA clusters findings, verifies candidate clusters against transcripts, and tracks surviving clusters across runs. [1]
A separate model checks each candidate cluster against up to three full transcripts and discards clusters the evidence does not support.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - AQuA runs unattended in the user's Google Cloud project and does not sit in the request path. [1]
AQuA runs beside your agent in your Google Cloud project, reading trajectories and deploy-time source snapshots outside the request path.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - Raw session transcripts, source snapshots, and BigQuery tables stay inside the user's project boundary. [1]
Raw session transcripts, source snapshots, and BigQuery tables stay inside your project boundary, and AQuA never sits in the request path or writes back to your agent.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
GoogleOwner-controlled
https://developers.googleblog.com/the-outer-loop-insights-first-an-ambient-quality-agent-that-diagnoses-your-production-agent/
Retrieved 2026-10-29 00:21 UTC
Verified
Versions
1| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 1 | 2026-10-08 21:36 UTC | publication | None | Current |
In briefs
2- Turn a prompt into an editable slide, poster, or dashboard Weekly brief 2026-W41
- Extract document layout and chart data, not just text Daily brief 2026-10-08
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.