Teste das Gespräch, bevor das Telefon klingelt.
Script Caller-Personas und Success Criteria. Ein LLM spielt den Kunden, ein anderes bewertet das Transkript. Damit du Regressionen findest, bevor Kampagnen wählen.
Password reset scenario
LLM caller · text-only · no STT/TTS
- Offers reset path
- Confirms identity
- Warns on password share
- No invented policy
Teste Agenten, bevor sie live gehen.
Schreib realistische Caller, lass ein LLM sie spielen und einen Judge die Success Criteria scoren.
Scenario tests on the assistant
Define persona, script, max turns, and success criteria — then run before you publish a prompt or flow change.
LLM plays the caller
A text-only runner simulates the conversation against your assistant — no STT/TTS cost, tools described but not executed.
LLM judge per criterion
Each success criterion gets a pass/fail plus a short reason. Aggregate score shows how close you are to green.
Happy path and edge cases
Propose scenarios from the assistant config — booking, transfer, lockouts — covering the paths that break in production.
Batch runs in the editor
Run one test or a suite from the Simulations panel. Results land in test_runs with full transcript history.
Plan-gated evals
Available when simulations is enabled on the plan — the same eval idea competitors sell as a premium differentiator.
Write the caller once — reuse on every prompt change
Each assistant_test stores persona, script, success criteria, and max turns. Propose a suite from the assistant config when you need coverage fast.
- Happy path, edge cases, transfer requests
- Works with prompt and flow assistants
- API + UI for create, run, and history
Test suite
Persona · script · criteria
Password reset
Locked-out account holder
3 success criteria
Pass/fail with reasons — not vibes
After the simulated transcript, a judge LLM scores every criterion. Aggregate status is passed only when all checks clear.
- Text-only — cheap vs. real voice tests
- Tools are described, not executed
- Scores and transcripts for every run
Judge result
Passed · score 100%
- Offers clear reset path
- Confirms identity first
- Warns not to share passwords
Transcript + reasons stay on the run — so you know why a criterion failed before you ship.
Prompts wie Software ausliefern. Mit Test-Suite.
Simulation ist ein eigener Tab am Assistenten. Skripte den Caller, fahre die Suite, lies den Judge, dann publish.
Text simulations — cheap enough to run on every change. Pair with Live Monitoring when you need the real voice path.
Häufige Fragen zu Simulationen
Nein. Es sind Text-Gespräche: ein LLM spielt den Caller gegen deinen Assistenten, dann scored ein Judge-LLM jedes Success Criterion.
Prompts testen, bevor Kampagnen wählen.
Bau eine Szenario-Suite einmal, lauf sie nach jeder Prompt- oder Flow-Änderung erneut, und publish nur, wenn der Judge grün bleibt.