playground

# Prompt Playground

The prompt playground is a tool for authoring and optimizing prompts. It supports two different
ways of working: fast manual prompt iteration without a dataset, and dataset-backed prompt
experimentation with evaluators and experiments. Choose the workflow that matches the user's
current goal and the UI context they have mounted.

The playground actions named below are `ui.*` operations, called from `execute_browser_action` scripts as
`await ui.<operation>(input)` (for example `await ui.playground.run({})`). Confirm exact input
shapes with `search_browser_actions` before first use, and prefer one small script that chains related steps
over many single-call scripts.

## Workflow: Create And Iterate Without A Dataset

Use this workflow when the user wants to draft, rewrite, or manually improve a prompt and no
dataset-backed evaluation loop is in scope.

1. Clarify the task the prompt must perform: input variables, expected output shape, audience,
   constraints, and examples of good or bad behavior when available.
2. If a playground prompt already exists, call `ui.playground.prompt.read` before proposing
   changes so you have the current messages, message IDs, labels, and revision.
3. Draft or revise the prompt so it clearly states the task, required context, output contract, and
   success criteria. Keep the prompt directly tied to the user's stated goal.
4. Use `ui.playground.prompt.edit` for changes to the mounted prompt so the user can review the
   diff before accepting it.
5. Use `ui.playground.instance.add` when the user wants a fresh comparison instance that starts
   from the default prompt messages. Use `ui.playground.instance.clone` when comparing alternatives
   should preserve existing prompt content as the starting point. Discuss variants by their
   alphabetic labels, but pass numeric instance IDs to operations. After adding, use the returned
   `addedInstance` snapshot for follow-up edits.
6. Use `ui.playground.variables.set` when the user provides manual values for prompt template
   variables.
7. Use `ui.playground.repetitions.set` before running when the user is concerned about flakes,
   structured output consistency, tool-call reliability, or whether the prompt is ready to save.
   LLM outputs are nondeterministic; repetitions build confidence by checking the same task across
   multiple runs instead of trusting one successful response.
8. Call `ui.playground.run` only when the user asks to run, try, test, or compare the current
   prompt. Treat the output as qualitative feedback rather than dataset-backed evidence. One script
   can run and read in sequence:
   `const run = await ui.playground.run({}); if (!run.ok) return run; return await ui.playground.run.readOutput({});`
9. After the run finishes, call `ui.playground.run.readOutput` to inspect raw output and get the
   traceId for trace analysis when needed. If the run used multiple repetitions, inspect every
   repetition before summarizing confidence or recommending that the user save.
10. Call `ui.playground.prompt.save` only when the user explicitly asks to save or confirms that the
   current prompt should be persisted. For a first-time save of an unsaved prompt, omit `name`
   unless the user provided one; the operation will derive a valid Phoenix prompt name from the
   prompt content.
   Always pass a save description; it should read like a clear, short git commit message. Treat
   tags like releases and do not promote tags unless the user asks.
11. Inspect the output with the user, identify the next concrete improvement, and repeat the edit or
   comparison loop until the prompt is useful for the task.

## Workflow: Iterate Over A Dataset With Evaluators And Experiments

Use this workflow when the user wants evidence that a prompt is improving across a dataset, or when
they are comparing prompt variants using evaluator results. Running a prompt over a dataset is
implicitly an experiment: consult the `experiments` skill before designing the run, not only after
results arrive — it owns the iteration methodology end to end (what to stage at creation, how to
read and compare results, when an evaluator is warranted), and the `evaluators` skill owns designing
the evaluators that score them. This workflow covers only the playground mechanics of setting up and
starting a recorded run.

1. Load the dataset with `ui.playground.dataset.load` if it isn't already loaded. If the user named
   a dataset but no split and the dataset has splits, name them and ask whether to scope to one or
   load the whole dataset — then load once.
2. Make sure the starting prompt is well formed before running it: it should define the task,
   relevant variables, output format, and any constraints needed for consistent evaluation.
3. Use `ui.playground.experiment.setRecording` before running when the user wants the next
   dataset-backed playground run recorded, persisted, or saved as an experiment, or wants to name,
   describe, or attach metadata (such as a hypothesis or the variable being changed) to the next
   experiment. Set `recordExperiments` to false only when the user explicitly asks for a temporary,
   throwaway, unrecorded, or ephemeral run. Call this operation only when the requested recording
   mode or scaffold fields differ from the advertised `recordExperiments` and
   `nextExperimentScaffold` values; the staged scaffold applies to that one run and is consumed when
   it starts. This is separate from `ui.playground.prompt.save`, which saves prompt versions rather
   than run results.
4. Use `ui.playground.repetitions.set` before running when the user needs confidence across repeated
   attempts, especially for flaky behavior, structured outputs, or tool-call correctness.
5. Run the playground over the dataset. When recording is enabled, each prompt instance run over a
   dataset is captured as an experiment, with outputs and evaluator annotations available for
   review.
6. To read the experiment res