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

# Exporting and Using Results

<Note>
  Exports turn review sessions into evidence that product and engineering can act on.
</Note>

***

## 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 theme={"dark"}
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

<img src="https://mintcdn.com/lucia-7204fd1f/iSwf61fx0HoguRx0/images/eval-labs/export-controls.png?fit=max&auto=format&n=iSwf61fx0HoguRx0&q=85&s=7b8cba51268765e470820b469dcaf8b1" alt="export-controls" width="1290" height="332" data-path="images/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 theme={"dark"}
{
  "format": "lucia-eval-lab-session/v0.3",
  "exportedAt": "2026-04-29T19:33:10.000Z",
  "exportedBy": {
    "clerkUserId": "user_3D2BItLYUO1uqJOqzlZTvHZNgsF",
    "email": "aviv@hellolucia.ai",
    "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 theme={"dark"}
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.