> ## Documentation Index > Fetch the complete documentation index at: https://www.sentrial.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Compare agent releases > Save a comparison of detected failures before and after an agent change, with coverage and source runs included. Use **Experiments → Release reports** to compare the evaluations recorded for two versions of an agent. A saved report keeps the selected runs and measurement fixed so you can return to the same evidence after more traffic arrives. Saving a report does not run evaluations or change your agent. You need an owner or admin role in the workspace. ## Prepare comparable runs 1. Give the baseline and candidate distinct release labels, such as `claims-v1` and `claims-v2`, in the same environment. Send each label from the start of every run using the [release metadata example](https://www.sentrial.com/docs/sdk/typescript.md#track-agent-releases). Keep the agent identity the same when deploying the candidate. 2. Open a saved signal policy and prepare its revision for evaluation. In **Automatic capture and evaluation**, configure that revision for your agent. Set the session and action limits, expiry and evaluation permission. To collect evaluated results, also select **Check receipts automatically** for a receipt policy, or enable the prepared model with its separate provider permission and budget. Saving the configuration alone does not start it. 3. Start the configuration before collecting the baseline. It selects session records created after activation, once they complete and settle; earlier runs are not backfilled. Check its status and capture history on the policy page. Capture and the chosen evaluator must be enabled in your deployment. 4. Collect the baseline, deploy your change, then collect the candidate. Use the same capture configuration, policy and evaluator for both. Allow the runs and their evaluations to finish before saving the comparison. A trace marked completed or an SDK-reported success is not a signal evaluation. Runs without resolved evidence remain visible in the report, but do not supply a detected-failure rate. If capture or evaluation is paused, resolve that before collecting data for a measured comparison. Automatic policy capture leaves sessions with delegated work or missing evidence unresolved. Check those runs in the source evidence before interpreting coverage. ## Save a comparison In **Release reports**, choose your agent and its **Saved signal measurement**. Enter the environment and the exact, case-sensitive baseline and candidate labels. Enter two ended, non-overlapping windows in **UTC**, with the baseline first. The window includes runs starting at **From** and excludes runs starting at **Until**. For example, 10:00–11:00 includes a run starting at 10:00, but not one starting at 11:00. These fields use UTC even when your computer uses another time zone. Open **Comparison requirements** to review the defaults: at least 90% resolved coverage and ten resolved runs per release. These thresholds determine whether a difference is shown; they do not establish statistical significance. The two windows together may contain at most 100 runs for the agent, including runs with another or missing release label. Narrow the windows if the selection is too large. Click **Save comparison**. The report is available under **Saved reports** for the selected agent; the list shows its latest twenty comparisons. ## Read the result Each release shows detected failures divided by resolved runs, plus the counts needed to understand what was left out: | Report field | Meaning | | - | - | | Runs in this window | All of the agent's runs selected by the time window. | | Assigned to this release | Selected runs with a consistent label matching the release and environment. | | Resolved coverage | Resolved runs divided by assigned runs. | | Detected failures | Resolved runs where the selected signal detected a failure. | The difference is **candidate minus baseline**, in percentage points. For a hypothetical baseline with four detected failures among eighteen resolved runs, and a candidate with one among eighteen, the rates are 22.2% and 5.6%: a difference of −16.7 percentage points. The comparison still needs to meet its coverage and run-count requirements. Traffic composition and detector errors can affect these observations, so the difference alone does not establish that the release caused an improvement. Use **Runs included in the report** to inspect excluded runs and open their original sessions. Review the tool results and assistant responses behind a detected issue. **Measurement and saved identity** shows which signal, policy and evaluator versions produced the comparison. ## Resolve an incomplete comparison | What you see | What to check | | - | - | | Set up a signal measurement first | Prepare a saved policy revision and configure its Automatic capture and evaluation section for this agent. | | No release label or incomplete release label | Send the label from the beginning of new runs. Older runs are not relabeled retroactively. | | Conflicting release labels | Keep one release and environment throughout each run; start a new run after a deployment change. | | Not evaluated or unresolved evaluation | Inspect capture and evaluation progress, missing evidence and indeterminate decisions. | | Different measurement | Collect both cohorts under the same policy and evaluator. Changing the detector changes what is being measured. | | Not comparable | Follow the displayed coverage, resolved-run or measurement reason. Missing results are not zero failures. | Later arrivals and evaluations do not update an existing report. Save a new comparison when you want a new snapshot of the evidence. ## Recover a save or removed source If saving times out, use **Check whether it saved** or **Retry this report**. The unfinished request remains in the current tab across reloads, and retrying keeps the same report identity. Browser session storage must be available. Check the saved report before choosing **Start a different comparison**. Removing or reassigning source data clears the copied results. The report then shows **Report unavailable**, rather than reconstructing a comparison from newer runs. Removing its agent or capture configuration can remove the report itself. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.