# Exporting and Using Results
> [!summary]
> Exports turn review sessions into evidence that product and engineering can act on.
---
## Export formats
Eval Labs supports structured exports such as:
- JSON
- CSV
- Markdown
Use JSON when engineering needs full structure.
Use CSV when comparing scores across many items.
Use Markdown when sharing human-readable summaries.
---
## What to check in a good export
A complete export should include:
- session metadata
- run source
- prompt count
- custom suite linkage when relevant
- cases
- Lucia responses
- review drafts
- saved reviews
- saved timestamps
- `savedBy` when reviews were saved
- `exportedBy` when exported by a logged-in user
---
## Generated-only exports
If a run was exported before review, the export may show:
```text
saved: null
savedAt: null
savedBy: null
ratings: null
```
That is expected.
Generated-only exports are useful for debugging Engine behavior, but reviewed exports are better for training and product decisions.
---
## Reviewed exports
A reviewed export is stronger because it includes human judgment.
Before sending an export to product or engineering, make sure the relevant items have been saved.
---
## How engineers should use exports
Engineers should read exports for patterns, not isolated annoyances.
A single odd response may be useful.
A repeated pattern is much more important.
Pattern examples:
- disorientation prompts route to generic capability redirect
- payment risk gets detected but next action is vague
- Lucia sounds warm but does not narrow the field
- Spanish prompts lose warmth
- trust repair language overclaims
---
## Export testing suite data from Eval Labs
>![[export-controls.png]]
_Export controls for easy usability with multiple data formats._
_Example JSON code/format from exported (custom or automated) prompt suite. _
```json
{
"format": "lucia-eval-lab-session/v0.3",
"exportedAt": "2026-04-29T19:33:10.000Z",
"exportedBy": {
"clerkUserId": "user_3D2BItLYUO1uqJOqzlZTvHZNgsF",
"email": "
[email protected]",
"name": "Aviv Hadar"
},
{
"item_index": 0,
"template_key": "payment-confusion",
"category": "utility/everyday",
"subcategory": "payments-and-settlement",
"prompt_title": "List pending payments close to arrival",
"prompt_text": "List pending payments close to arrival.",
"lucia_response": "Let's start with Ava Sterling's arrival details first. 4 open tasks still need closure, and check-in is today."
},
{
"item_index": 1,
"template_key": "overwhelm-emotional-regulation",
"category": "overwhelm/emotional regulation",
"subcategory": "operator-nervous-system",
"prompt_title": "I'm spinning a little",
"prompt_text": "I'm spinning a little. Tell me what to do first so I can breathe again.",
"lucia_response": "Take a breath. This feels heavier than it is. Nothing critical is slipping beyond the first move. I narrowed this to one first move. Begin with Ava Sterling - 4 open tasks still need closure, and check-in is today. I will keep the rest quiet and only surface what cannot wait. 9 items can stay quiet for now."
}
```
---
## Review-layer export fields
Reviewed exports may now include:
```text
review_state
canon_candidate
employee_understood_need
employee_right_next_move
employee_calming_effect
employee_risk_or_confusion
employee_senior_review
employee_reusable_learning
human_what_person_is_asking_for
human_follow_through_required
human_next_step_needed
human_emotional_state
human_pressure_level
final_what_person_is_asking_for
final_follow_through_required
final_next_step_needed
final_emotional_state
final_pressure_level
final_decision_reason
final_adjudicated_at
final_adjudicator_email
```
Use employee fields to understand broad reviewer reaction.
Use adjudication fields to understand final senior meaning.
Do not treat non-adjudicated employee reaction as canonical label truth.