> ## Documentation Index
> Fetch the complete documentation index at: https://docs.thunderphone.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Experiments (A/B testing)

> Run two agent configurations side by side on real calls and let the success rates pick the winner.

A/B testing answers "is the new prompt actually better?" with data
instead of vibes: incoming calls are split between agent **variants**,
each call is graded as usual, and you compare success rates per variant.

There are two surfaces:

* **Per agent** — tests are configured and tuned in each agent's
  builder, on its **A/B** tab (`/dashboard/agents/<id>?tab=variants`).
  That's where variants are created and the test is switched on.
* **Cross-agent overview** — the **Experiments** page
  (`/dashboard/experiments`, under Quality & Testing) aggregates every
  agent's test into one table.

## Set up a test

From the Experiments page, click **Set up an A/B test** and pick an
agent — you land on that agent's A/B tab, where you create the variant
configurations (one is marked **control**) and enable split testing.
See [Build an agent](/guides/build-an-agent) for the builder itself.

## Read the overview

For each agent with a test, the Experiments table shows:

* **Status** — Active (split testing on) or Paused.
* **Variants** — every variant as a chip, with the control labeled.
* **Leading** — the variant with the best success rate so far, with its
  percentage. Until variants have graded calls, this reads *Not enough
  data yet* — don't crown a winner off a handful of calls.
* **Calls** — total calls across the test's variants.

Agents without a test are listed underneath as one-click nudges to
start one. Clicking any row jumps to that agent's A/B tab to tune or
conclude the test.

<Tip>
  Which variant handled a call is recorded on the call itself, so you
  can filter and spot-check each side's transcripts in
  [call history](/guides/review-calls).
</Tip>

<Note>
  Prefer this built-in feature over hand-rolling A/B assignment in a
  [dynamic config webhook](/guides/dynamic-call-config) — you get
  assignment, per-variant stats, and grading for free.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Build an agent" icon="robot" href="/guides/build-an-agent">
    Create variants on the agent's A/B tab.
  </Card>

  <Card title="Simulations" icon="flask" href="/guides/test-agents">
    Pre-ship testing with AI callers, before real traffic votes.
  </Card>
</CardGroup>