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

# Chatting with an agent

> Learn how to ask questions, read results, and get the most out of your agent chat interface.

## Opening the chat

From the **Agents** list, click on any agent to open its chat interface. The chat is where you interact with your agent in real time — ask questions, explore results, and follow up with more questions.

## Asking questions

Type your question in plain language at the bottom of the screen and press **Enter** (or click **Send**).

**Good questions to start with:**

* "How many sessions did we have last week, broken down by channel?"
* "Which campaigns had a ROAS above 3 in the past 30 days?"
* "Show me the top 10 highest-spend ad groups from last month."

You don't need to know SQL or the exact table names — the agent figures that out from the context you've given it and the data it can access.

<Tip>
  If the agent returns unexpected results, try being more specific. For example, instead of "last week", try "the 7 days ending Sunday 23 March 2025". Date precision often leads to more accurate queries.
</Tip>

## Reading results

Depending on your question and the agent's configuration, results can appear in several formats:

### Tables

Data is presented in a scrollable table with sortable columns. Column headers show the field names from your BigQuery data — if these aren't clear, add descriptions to your [agent context](/agents/building-agents#adding-context).

### Charts

When you ask for a visualisation (or when the agent decides a chart would be more useful), results are rendered as an interactive chart directly in the chat. You can ask the agent to change chart types:

> "Can you show that as a line chart instead?"

### Markdown text

For summaries, insights, and explanations, the agent responds in formatted text with bullet points, bold highlights, and recommendations.

## Following up

Every response is a starting point. You can ask follow-up questions that build on the previous result:

> "Great — now filter that to campaigns where spend was over €1,000."

> "Can you add a column showing the change vs. the previous period?"

> "What's the average CPA across all those campaigns?"

The agent maintains context within a chat session, so you don't need to repeat yourself.

## Saving insights

If the agent returns something useful — a metric definition, a schema correction, a calculation rule — you can save it as a **learning**. Learnings are stored and made available to the agent in future sessions, gradually improving its accuracy over time.

To save a learning, click the **Save as learning** button that appears when you hover over any agent response.

[Learn more about prompt management and learnings →](/agents/prompt-management)

## Chat history

Every chat session is stored permanently and accessible from the chat history tab. If the chat was created by a scheduled job, it's also linked to that job's run history.

Job run chats are **read-only** — they are a fixed snapshot of what the agent returned for that run. To continue the conversation from a job result, use the **Start Follow-up Chat** button in the input area. This creates a personal copy of the chat that you can continue freely. See [Personal follow-up chat](/agents/jobs-scheduling#personal-follow-up-chat) for details.

## Tips for better results

<AccordionGroup>
  <Accordion title="Be specific about time periods" icon="calendar">
    Agents use `CURRENT_DATE` as a reference point. Phrases like "last month", "this quarter", and "last 7 days" are interpreted relative to today. If you mean a specific date range, say so explicitly.
  </Accordion>

  <Accordion title="Name your campaigns or segments exactly" icon="tag">
    If you're asking about a specific campaign, use the exact name or ID as it appears in BigQuery. You can ask the agent first: "What campaigns are currently active?" to get the exact names.
  </Accordion>

  <Accordion title="Ask for one thing at a time" icon="list-ol">
    Complex multi-part questions sometimes produce one part well and miss others. Break big analyses into steps for more reliable results.
  </Accordion>

  <Accordion title="Correct the agent when it's wrong" icon="pencil">
    If the agent misunderstands something, correct it in plain language: "Actually, the `revenue` column is in euros, not cents." Then save that correction as a learning so it doesn't happen again.
  </Accordion>
</AccordionGroup>