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

# From a failed trial to a reviewed regression case

> Reuse Inspect View and Label Studio, then preserve the evidence and source identity behind a new development case.

**Available in PyPI 0.19.0.** The report UI and review exchange need no new runtime
dependencies. Use the optional Inspect package for native Inspect logs.

## Start from evidence

```bash theme={null}
python examples/investigate_failures.py --output-dir investigation-demo
multivon-eval view --dir investigation-demo
```

This offline example creates a baseline and proposal, two repeated trials per
case, intentionally missing capture evidence, hostile text to verify escaping,
and two explicitly synthetic review annotations. It makes no model calls and
does not claim independent human review.

Open the proposal, filter by tag or case ID, and expand a trial. Compare it with
the baseline using the directory selector. Separate three questions: what the
application did, whether the grader judged it correctly, and whether the evidence
is complete enough for your release policy. Preserve errors and disagreements.

For executions owned by Inspect:

```bash theme={null}
inspect view --log-dir inspect-logs --port 7575
```

Use its existing messages, scoring, metadata and timeline views. Multivon does not
rebuild the native trace viewer. The tested Inspect 0.3.263 sample view overflowed
a 390-pixel viewport to 450 pixels; use a desktop viewport for that upstream view.
The Multivon report pages have a separate responsive layout.

## Review the selected execution

Download the trial JSON and candidate from the report if you need portable
references. The candidate is not an approved case or an oracle. Export the report's
saved trials with an explicit rubric using the existing
[Label Studio exchange](/guides/review-labels):

```bash theme={null}
python examples/review_saved_trials.py export proposal.json \
  --evaluator exact_match --rubric-file rubric.txt --output-dir review-tasks
```

Retain the original task file. Review in Label Studio and export its full JSON.
The importer validates the original trial binding and retains reviewer kind,
unknown/cancelled labels and disagreement. Reviewer IDs do not authenticate
independent people. Declare `human`, `model` or `synthetic` accurately.

## Author the expectation and promote deliberately

Write the expected result to `expected.txt`, and explain its authoritative source
and intended task behavior in `rationale.txt`. A rejected answer does not by itself
prove what the correct answer should be. Review that expectation separately.
For non-text outcomes, keep the independently verified outcome contract; a text
reference alone cannot replace database, tool or environment assertions.

```bash theme={null}
python examples/promote_reviewed_case.py \
  --report proposal.json \
  --tasks review-tasks/tasks.json \
  --export label-studio-export.json \
  --trial-digest YOUR_SELECTED_TRIAL_DIGEST \
  --evaluator exact_match \
  --case-id regression-invoice-17 \
  --expected-output-file expected.txt \
  --rationale-file rationale.txt \
  --reviewer-kind human \
  --min-reviewers 2 \
  --output development-regressions.json
```

The command requires consensus for that bound trial and refuses unknown,
insufficient or disagreeing reviews. Consensus may identify an application failure
or a grader false rejection; the explicit expectation determines the new case.
It writes a new file and does not overwrite existing manifests.

The promoted case has a new ID and preserves its original source group. If the
original case lacks a source group, supply `--source-id` based on actual provenance.
The recorded trace is cleared for a future execution, and a callable reference
cannot silently become its expected output. The manifest retains review evidence,
parent trial/content digests and the expectation rationale.

Promotion assigns the case to **development**. Once you investigate and tune
against a held-out failure, that source is no longer untouched validation evidence.
Keep its variants together and reserve new untouched sources for the final check.
Do not rename source IDs to make inspected data appear independent.

## Reuse boundaries and limits

Inspect owns native log inspection; Label Studio owns review UI and users;
Hugging Face remains the dataset platform. The Multivon additions bind saved
trials to reports, review decisions and explicitly authored development cases.
They do not establish a new dataset, independent labels or a scientifically
novel failure-discovery method. See the
[validation and critique](https://github.com/multivon-ai/multivon-eval/blob/main/benchmarks/industrial/INVESTIGATION_VALIDATION.md)
for actual browser, HTTP-boundary and promotion checks.