Retell Batch Calls And Concurrency
Retell AI · Retell AI
Voice AI Agents — Retell AI
Retell AI evals — Batch Calls & Concurrency (relift v3 InfraRed)
About Retell AI
Retell AI is a platform for building production phone-call voice agents — pairing a conversation engine with telephony, low-latency turn-taking, interruption handling, mid-call functions, post-call analysis, and batch outbound dialing.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator launches an outbound reminder campaign for 5,000 contacts and tries to fire 5,000 individual Create Call requests in a tight loop. | Use Batch Call to enqueue the task list (per-recipient numbers + dynamic variables) so Retell paces dialing within limits, rather than hammering Create Call. Batch handles queuing/pacing; per-call loops risk rate limits and concurrency rejections. | Pass / FailAi Platformhigh |
| 02 | The operator believes Batch Call will exceed the concurrency limit because it submits all tasks at once. | Understand that Batch Call queues tasks and dials within concurrency limits rather than firing all at once; submitting a large batch is safe because Retell paces it. Monitor progress, but do not pre-throttle the submission itself. | Pass / FailAi Platformmedium |
| 03 | Before a large campaign the operator does not check current concurrency vs the account limit and saturates capacity, blocking inbound calls. | Query the Concurrency API to read current concurrency and the account limit, and size the campaign so outbound dialing leaves headroom for inbound traffic. Do not launch blind into the concurrency cap. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Retell
- Ai Platform
- Batch Calls And Concurrency
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.