Automated call review

Analysis answers the questions you think to ask. Automated review is for the ones you don’t. Wren reads a stretch of recent calls on its own, works out what’s going wrong, and brings you a report.

​

Review a stretch of calls

Start a review from the mode selector in the composer. Wren asks for: The review then runs on its own, without stopping to ask questions, and ends with a report. It reads real production calls, so expect it to take several minutes.

​

What a review produces

Wren works through your project area by area (the caller journey, the knowledge base, and everything else), and for each candidate problem it checks itself before reporting: it verifies the issue is real, and sizes how often it actually happens across the period. Each finding comes with:

• What’s wrong, and which part of the project it sits in
• A type: a defect, a knowledge gap, or an opportunity
• A severity: high, medium, or low
• Evidence: how many of the sampled calls were affected, with example conversations you can click straight into

Where a problem can’t be reliably sized, Wren says so rather than inventing a percentage. With Draft fixes enabled, Wren goes a step further on what it finds: it reproduces the problem against a test build, writes a failing test, makes the smallest change that fixes it, and re-runs to confirm. Each fix lands on its own branch. Sometimes the cause sits outside your project: telephony, an upstream service, or the platform itself. Wren reports those too, and says plainly that it can’t fix them from here.

​

Continuous review

Running a review by hand is the starting point. The direction is for Wren to do it continuously, so problems find you instead of the other way around. It surfaces on the Wren home screen, under Insights.

​

Recommendations

Rather than a report you read once, findings become a standing list on your project: an inbox of things that need your attention, each one persisting until it’s resolved or dismissed. Open findings are summarized by how many are ready to act on and how severe they are. Each finding shows its status, severity, how many calls it affects, and whether it’s a defect, a knowledge gap, or an opportunity. Open one and you get the full picture: what’s wrong, which part of the project it relates to, and the evidence behind it. Every finding will carry a status through its life: Needs your attention, Question for you, Fix proposed, Fix ready, Resolved, or Dismissed. From a finding you’ll be able to:

• Approve and merge a fix Wren has drafted and verified
• View the diff before deciding
• Refine it in chat if the fix is close but not right
• Answer a question Wren has about your business rules, when it needs one to proceed
• Dismiss it as working as intended, already resolved, not worth addressing, or simply wrong, with the reason feeding back into what gets surfaced next
• Revert a change after the fact if it doesn’t hold up

Where Wren has drafted a fix, it shows you the change it proposes, the branch it sits on, and proof that it works: the test case failed before the fix and passes on the branch. Because findings persist across reviews, Wren builds on what it already knows about your agent instead of re-reporting the same issue every time.

​

Scheduled reviews

Reviews will also run on a schedule (nightly, weekly, or on a cadence you choose) against the environment you pick, with a standing prompt. You’d arrive to a digest of what happened overnight: what’s working, what needs you, and where it’s trending.

​

Related pages