# Kaiya - Prompts

This page is for admins who want to see or edit the actual system prompts Kaiya uses.

<figure><img src="/files/OYzcPCwCz3ToRj5REyRf" alt="" width="563"><figcaption></figcaption></figure>

You can pick a prompt set from a dropdown, such as **“Agentic Insights – Planner”** or **“Text to SQL – Clarification Checker (Medium)”**. The large text area shows the full instruction that is sent to the LLM, which you can edit and save.

<figure><img src="/files/GO3fKaT792NrK5roe8oQ" alt="" width="375"><figcaption></figcaption></figure>

Use this page when you want to standardize the way Kaiya answers across the company, when you want to enforce fiscal time, or when you are switching models and need slightly different phrasing. Avoid deleting the shipped prompts. Edit or duplicate them instead so you can roll back if needed.

#### What it does

1. **Agentic Insights – Planner**
   * This controls how Kaiya creates the step-by-step plan for Deep Insights.
   * It tells the model: “You are the planning orchestrator. Output only JSON with steps \[…]. Users expect deep-dive analysis, not a shallow answer.”
   * If you change this, you change how Kaiya *plans* the steps: SQL → Python → viz → summary → reflection.
   * Use this to add org-specific requirements: “always list assumptions”, “always create a driver table”, “always check sample size”.
2. **Text-to-SQL – Query Planner / Clarification Checker**
   * These prompts control how Kaiya turns natural language into SQL and *when* it decides to ask the user for a missing detail.
   * This is where the **Clarification Mode** dropdown in ***Settings → Kaiya*** maps to: **Low/Medium/High** correspond to different clarification prompts.
3. **Model-specific packs**
   * If your deployment uses a different LLM family, you can keep separate prompt versions and then select them via **Prompt Variation** in the main settings.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.tellius.com/tellius-6.3/settings/advanced/kaiya-prompts.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.