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

# Evaluation and learnings

> Measure how accurately Vizkraft answers questions for a connector and teach it with golden cases.

Evaluation helps you measure and improve how well Vizkraft answers questions for a SQL connector. It generates test questions, scores answers, surfaces recommendations, and feeds approved learnings into connector memory.

<Note>
  Evaluation is available for **SQL connectors** (PostgreSQL, MySQL, ClickHouse, and MongoDB). It does not appear for HubSpot CRM or custom MCP connectors.
</Note>

## Open evaluation

1. Open `Connectors`.
2. Find a SQL connector that has finished indexing.
3. Select the **⋯** menu on the connector row.
4. Choose **Evaluation**.

## Two tabs

Evaluation is organized into two tabs:

| Tab           | What it shows                                                       |
| ------------- | ------------------------------------------------------------------- |
| **Overview**  | Accuracy score, eval run history, recommendations, and run controls |
| **Learnings** | Golden questions to review, approve, edit, or teach manually        |

<img src="https://mintcdn.com/na-13f69f9a/q_DAu_nJy7qox8T_/public/screenshots/evaluation-overview.png?fit=max&auto=format&n=q_DAu_nJy7qox8T_&q=85&s=f5a55e49537f939d0ca88d637fb4a272" alt="Evaluation overview with accuracy gauge and run history" width="3024" height="1646" data-path="public/screenshots/evaluation-overview.png" />

## Overview tab

The overview tab is where you measure performance:

* **Accuracy gauge** — shows how well Vizkraft answered the latest eval run.
* **Run history** — tracks accuracy over recent runs so you can see improvement.
* **Run evaluation** — queues a new eval against your confirmed golden cases.
* **Recommendations** — suggested fixes when cases fail, such as table-selection or SQL adjustments.

You need at least five approved golden cases before you can run an evaluation.

## Learnings tab

The learnings tab is where you build and maintain golden cases:

<img src="https://mintcdn.com/na-13f69f9a/q_DAu_nJy7qox8T_/public/screenshots/evaluation-learnings.png?fit=max&auto=format&n=q_DAu_nJy7qox8T_&q=85&s=a0aa6acc7fe9a1781eaea4a4614ea524" alt="Evaluation learnings tab with cases to review and approve" width="3024" height="1646" data-path="public/screenshots/evaluation-learnings.png" />

### AI-generated questions

After indexing, Vizkraft can generate a set of test questions based on your schema. Each case includes:

* The question Vizkraft would ask.
* The expected SQL or result shape.
* A preview chart when the case produces visual output.

Review each case and **approve** the ones that represent good business questions, **edit** cases that need refinement, or **reject** cases that are not useful.

### Teach manually

You can also add golden cases yourself:

1. Open the **Learnings** tab.
2. Choose to teach with AI assistance or enter a case manually.
3. Provide the question and expected behavior.
4. Approve the case when it is ready.

### Generate more questions

If your dataset is thin, use **Generate more questions** to expand coverage across tables and complexity levels.

## Rate answers in chat

Every SQL answer in chat can include thumbs up and thumbs down controls.

<img src="https://mintcdn.com/na-13f69f9a/q_DAu_nJy7qox8T_/public/screenshots/chat-feedback-thumbs.png?fit=max&auto=format&n=q_DAu_nJy7qox8T_&q=85&s=9e388ea3119870664b82dd223580ddfd" alt="Thumbs up and thumbs down controls on a chat answer" width="3024" height="1646" data-path="public/screenshots/chat-feedback-thumbs.png" />

* **Thumbs up** — promotes the answer into a golden case for review.
* **Thumbs down** — flags the answer so you can correct it in learnings.

This is the fastest way to capture real questions your team actually asks.

## How evaluation connects to memory

Approved golden cases and applied recommendations can distill into [connector memory](/features/connector-memory). That means improvements from evaluation carry forward into everyday chat — not just test runs.

## When to use evaluation

* Right after onboarding a new SQL connector and completing indexing.
* After a schema change or important-tables update.
* When answers are inconsistent or frequently pick the wrong tables.
* When onboarding a new analyst team and you want a baseline accuracy score.

## Next step

Review what Vizkraft has learned in [Connector memory](/features/connector-memory), or return to [Ask questions](/features/ask-questions) to keep building golden cases from live chat.