> ## Documentation Index > Fetch the complete documentation index at: https://docs.usetuner.ai/llms.txt > Use this file to discover all available pages before exploring further. # Dataset best practices > How to choose, name, and maintain Dataset calls so every replay tells you something you can act on. ## Start from a question Every Dataset call should answer something specific. Is the new STT better with accents? Did the prompt fix stop the made-up policy? Does booking still work after the tool change? If you can't name the question a call answers, it probably doesn't belong in the set. *** ## Name calls so they group Your agent has one Dataset, and you pick which calls to replay together. Put the purpose at the front of each name so the set you need is easy to find in **New Replay**: | Prefix | Use it for | Example | | - | - | - | | `[latency]` | Stack and speed checks | **\[latency] Order status, road noise** | | `[stt]` | Transcription checks | **\[stt] Account number, Scottish accent** | | `[eval]` | Behaviour and policy checks | **\[eval] Made-up refund policy** | | `[tool]` | Tool-calling checks | **\[tool] waive\_late\_fee error** | | `[golden]` | Calls that must keep working | **\[golden] Standard booking** | Use the **Description** to note why the call is in the set, like "Agent promised a refund the policy doesn't allow". Names are unique per agent. *** ## Keep calls short and focused Shorter calls replay faster, cost less, and fit within the **Max call duration**. Each caller turn can add up to the **Max wait** of waiting for your agent, so with the default settings a 3-minute cap fits roughly 8 caller turns. The **Longest possible call** line in **New Replay** tells you before you run whether a call fits. If only part of a long call matters, upload a trimmed recording of that part instead. *** ## Prefer multi-channel recordings A **Multi-channel** call keeps the caller on their own channel, so the replay is clean. A **Mono source** mixes caller and agent, so fragments of the original agent can leak into the caller's turns, and your agent will hear them. Use mono calls only when there's no better recording, and listen to them first. *** ## Listen before you trust Open every new call with the headphones icon and play a few turns. Check for clipped words, agent speech inside a caller turn, and turns split in the wrong place. A bad cut makes every replay of that call misleading. See [Review the caller turns](/docs/datasets/add-calls#review-the-caller-turns). *** ## Keep your failures, and some golden calls Every call your agent got wrong is a test you get for free. Add it, fix the agent, and keep replaying it so the failure can't come back unnoticed. Balance failures with a few golden calls your agent handles well today, so fixes that break something else show up too. *** ## Replay more than once Your agent's responses vary from run to run even when the caller doesn't. Replay each call 3 to 5 times: * Failing every time means the problem is consistent. * Failing now and then means it's intermittent, and one passing replay after a fix doesn't prove much. The limit is 20 replayed calls per run, counting repeats, so 4 calls replayed 5 times fits in one run. *** ## Change one thing at a time Between two runs you compare, change only one thing, and keep the same calls, repeats, **Max call duration**, and **Advanced turn-taking** settings. Then any difference has one cause. See [Compare two setups](/docs/datasets/use-cases/benchmarking#compare-two-setups). *** ## Remember the caller doesn't adapt The caller says what they said in the original call, whatever your agent answers now. Pick calls where the behaviour you're testing happens early, and write evals about the agent's turns, not about how the conversation ends. See [The caller doesn't adapt](/docs/datasets/use-cases/capturing-failures#the-caller-doesnt-adapt). *** ## Protect your tools and data Replays reach your real agent, and your agent calls its real tools. Point it at test endpoints or test accounts before replaying calls that book, charge, refund, or change records. See [Check a tool call on a replay](/docs/datasets/use-cases/capturing-failures#check-a-tool-call-on-a-replay). *** ## Refresh the set Add calls when you launch new Intents, enter a new market, or see a new kind of failure in production. Delete calls that no longer match how your product works. Past runs keep their results after you delete a call. *** ## Mind privacy Dataset calls keep your callers' real voices and words, and a Dataset call keeps its own copy of the caller's audio even if the source call is later removed. Add only calls you're allowed to reuse for testing, and delete the ones you no longer need. *** ## Keep an eye on cost | Action | Cost | | - | - | | Adding a call from production | Free | | Adding an uploaded recording | 1.5 credits per minute of audio, charged once the call is **Ready** | | Replaying calls | The same per-minute simulation rate as generated runs, shown in **New Replay** before you run | ### Next steps Pick production calls or upload recordings. Replay your Dataset calls against your agent. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.