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

# Inspect results and compare runs

> Inspect saved Prompt Studio outputs, scores, errors, and traces, then compare compatible evaluation runs to understand changes in required-check results.

Use **Results** in Prompt Studio to reopen dataset evaluations, inspect the evidence behind a score, and compare a candidate run with a baseline. Comparison reads saved outputs and scores; it does not generate new answers.

This guide continues the **Support ticket triage** example from [Run evaluations](https://docs.traceport.ai/prompt-studio/testing.md). Start with the recorded `Support triage v1` run. To compare versions, prepare a second run with matching test conditions.

## Find a recorded run

1. Open **Results** in the Studio sidebar. Use the prompt selector to choose **Support ticket triage**, or **All prompts** to browse across prompts.
2. Filter by run status. With a prompt selected, you can also filter by version. Choose **All versions** to see both versions of this example; use **Clear filters** if the expected run is missing.
3. Open `Support triage v1`. Check its prompt version, model, dataset, and rules in **Run overview**.

The list's **Run status** describes execution. **Completed** does not establish that the answers met your requirements. Open the run to inspect pass rate, scoring coverage, errors, and [what each metric means](https://docs.traceport.ai/prompt-studio/testing.md#read-pass-rate-and-coverage-together).

Use **All runs** to return to the list, or **Switch result run** to open another run. Keep the run URL to reopen the same evidence later.

## Inspect a case before trusting its score

Under **Test cases**, search inputs and outputs or filter to **Failed checks**, **Not fully evaluated**, **Generation errors**, or **Evaluation errors**. Open the password-reset ticket: `I forgot my password. How can I reset it?`

Read these sections in the case panel:

| Section | What to inspect |
| - | - |
| **Test inputs** | The variable values used for this case. |
| **Expected output** | The saved reference answer, when one was supplied. |
| **Generated output** | The actual response, any case error, duration, and token counts. |
| **Evaluation results** | Each rule's score, reason, and whether it was required or advisory. |
| **Technical details** | The case, execution, and trace identifiers for this evidence. |

Use **Previous case** and **Next case** to move through the current case selection. **Open trace**, when available, opens the linked generation request. Provider-backed rule results can also link to their scoring requests.

In the recorded baseline, the password-reset ticket received `low` priority, while its reference says `normal`. The required **Support ticket contains JSON** rule passed because the response contains JSON. Read the reason and the answer together.

![Saved password-reset case showing reference priority normal, generated priority low, and a passing JSON-content rule with its reason.](https://mintcdn.com/traceport/qnQpjm16A9r4NqtM/images/prompt-studio/support-triage-evaluation-case.jpg?fit=max\&auto=format\&n=qnQpjm16A9r4NqtM\&q=85\&s=552bb6a9957c74bfc40edaec07f6c985)

The baseline password-reset answer passes the JSON rule but differs from the reference priority. This is the same saved case inspected in the evaluation guide.

### Distinguish a failed check from missing evidence

| Result | Meaning |
| - | - |
| **Passed** | Every required rule returned a valid passing result. |
| **Failed** | Required checks finished, and at least one failed. |
| **Evaluation error** | A scoring rule could not finish. Read its error or reason. |
| **Not fully evaluated** | Required evidence is missing or a check was skipped. |
| **Advisory scores** | Only advisory checks were selected; they do not determine case pass or fail. |
| **Not evaluated** | No evaluation was performed, for example because no rules were selected or generation did not complete. |

Generation and evaluation have separate states. An answer can exist while scoring is still running or has encountered an error. A provider failure or skipped rule is not a failed quality check.

Expand **Run details** to identify the saved dataset and rule snapshots, sampling seed, selected prompt version, and original estimate. Later edits to the dataset or rule library do not rewrite this evidence. Older runs without saved case snapshots expose the records still available and cannot be used for this comparison workflow.

## Prepare a comparable candidate

For this example, keep the dataset, selected cases, model, API key, and rule settings unchanged. Change the prompt version so you can inspect the effect of a specific instruction.

> [accordion] Create the support-ticket v2 run
>
> 1. Open version 1 in [Build](https://docs.traceport.ai/prompt-studio/editor.md#save-changes-or-create-a-new-draft) and click **New draft**. Describe the change as `Clarify that individual password-reset requests have normal priority.`
>
> 2. In the new draft's System message, add this sentence after the priority rule:
>
>    ```text Priority clarification theme={null}
>    Password-reset requests are account issues with
>    normal priority unless service-wide or multi-user
>    blocking is stated; they are not low-priority
>    general questions.
>    ```
>
> 3. Click **Save changes**, then **Run on dataset**. Select the same API key and model as `Support triage v1`.
>
> 4. Reuse the unchanged **Support ticket triage** dataset with all eight cases. Select the same required **Support ticket contains JSON** rule, or the saved `Support ticket checks` rule set with those settings.
>
> 5. Name the run `Support triage v2`, reuse sampling seed `42`, and [preview and launch the evaluation](https://docs.traceport.ai/prompt-studio/testing.md#set-up-the-run) within your chosen spend cap. The recorded example used `$0.10`; check the estimate for your setup.
>
> Wait for completion before comparing. The example's v2 version becomes read-only after evaluation. If your prompt already has more versions, use the version number created by your own **New draft** action.

Selecting the same percentage does not ensure the same sampled cases. Reuse the same seed with unchanged dataset content, or use `100%` as this example does. An unchanged dataset can reuse its saved snapshot.

## Compare the candidate with its baseline

**1. Open the candidate's results**

In **Results**, open `Support triage v2`, then select **Compare runs** next to **Test cases**. The open run is the candidate, labeled **This run** in the comparison.

**2. Choose the baseline**

Under **Baseline run**, select `Support triage v1`. Search comparable runs if needed.

Studio lists finished runs from the same prompt with matching selected cases, dataset snapshot, rule snapshot, generation model, and API key. Both runs need saved case evidence and at least one required evaluation rule. **Completed with errors** runs can be compared, but cases missing required scores are marked **Not comparable**.

**3. Read the result changes**

Inspect **Regressions**, **Improvements**, **Unchanged**, and **Not comparable**, plus the number of cases with all required scores in both runs.

Under **Compared cases**, use the outcome filter to focus on **Regressions**, **Improvements**, or **Changes and missing scores**. The summary still describes all compared cases. Open a row to read both full outputs and the shared test input and reference.

![Support triage v2 compared with Support triage v1, showing zero regressions, zero improvements, eight unchanged cases, and no missing required scores.](https://mintcdn.com/traceport/qnQpjm16A9r4NqtM/images/prompt-studio/support-triage-run-comparison.jpg?fit=max\&auto=format\&n=qnQpjm16A9r4NqtM\&q=85\&s=7892abdb09e9bc73c0234a799137939a)

The candidate and baseline share all eight cases and the same required JSON rule. All eight required-check results are unchanged.

### Understand the comparison labels

| Label | Required-check result |
| - | - |
| **Regression** | Passed in the baseline and failed in the candidate. |
| **Improvement** | Failed in the baseline and passed in the candidate. |
| **Unchanged** | Passed in both or failed in both. Output text and individual scores can still differ. |
| **Not comparable** | At least one run does not have valid results from all required rules for that case. |

Advisory scores do not change these labels. The comparison counts required-check outcomes, not text differences or changes in cost. Use **Switch result run** or **View baseline results** to inspect each run's recorded metrics and detailed rule evidence.

### Inspect the password-reset change

In the recorded comparison, the baseline says `low` priority and the candidate says `normal`, matching the reference. The row is still **Unchanged**: both outputs passed the JSON-content rule. The comparison reports zero automatic improvements because that rule does not measure priority correctness. **Changes and missing scores** is empty for this pair; choose **All cases** to inspect the different answers.

![Password-reset comparison showing baseline priority low and candidate priority normal beside the reference, with both runs passed and the result labeled Unchanged.](https://mintcdn.com/traceport/qnQpjm16A9r4NqtM/images/prompt-studio/support-triage-comparison-case.jpg?fit=max\&auto=format\&n=qnQpjm16A9r4NqtM\&q=85\&s=66ee12fb57d16d3eac2505e99e4ff76f)

The two saved answers differ in priority, while both pass the selected rule. Unchanged describes their required-check outcome, not identical responses.

Review output differences even when every row is **Unchanged**. To measure classification quality automatically, add a rule with appropriate [evaluation criteria](https://docs.traceport.ai/prompt-studio/evaluations.md#add-a-judge-or-reference-based-check), test it, and evaluate both versions under the same new rule settings.

The run URL reopens the recorded run. Choose the baseline again after reloading; the baseline selection is not stored in that URL.

> [!NOTE]
>
> **Compare models** in [Build](https://docs.traceport.ai/prompt-studio/editor.md#compare-models) tests one input across models. **Compare runs** here compares compatible dataset evaluations. **Release** uses evaluation evidence to check publication requirements; viewing a comparison does not publish a version.

## Send an output for human review

When a generated answer needs a person's decision, return to **Test cases**, open it, and expand **Send for human review**. Choose **Review priority** and click **Send to review**. Studio opens the queued review item in **Review**.

This action is available for a completed generated case with a recorded execution. Review priority controls the queue item's urgency; it is separate from the `priority` field produced by the support-ticket prompt.

Follow [Human review](https://docs.traceport.ai/prompt-studio/review.md) to claim the case, record independent decisions, resolve disagreements, and reuse a final correction.

## Troubleshooting

| What you see | What to check |
| - | - |
| The expected run is missing | Check the selected prompt, version, status, and list page. Use **Clear filters** to broaden the list. |
| No comparable baseline | Match the prompt, selected cases, dataset snapshot, rule settings, model, and API key. Complete both runs first. |
| A run with no rules or only advisory rules cannot be compared | Run both versions with at least one required evaluation rule. Their saved outputs remain available under **Test cases**. |
| Dataset or rule edits removed the expected baseline | Evaluate both versions again with the same updated dataset and rule settings. Historical runs keep their original snapshots. |
| **Not comparable** cases | Open each run's case and inspect missing, skipped, or errored required checks. Retry processing errors when offered; inspect them again after retrying. |
| No changes, but the answers differ | Check the selected rules. **Unchanged** means the overall required-check result stayed the same. |

After reviewing the candidate's evidence, follow [Versioning and releases](https://docs.traceport.ai/prompt-studio/releases.md) to check the prompt's publication requirements. Keep the baseline and candidate runs available for any release checks that need them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.