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

# The Modem Agent

> Ask questions, find patterns, and take action using natural language

export const Prompt = ({text, variant = 'accent'}) => {
  const [copied, setCopied] = useState(false);
  const handleCopy = async () => {
    try {
      await navigator.clipboard.writeText(text);
      setCopied(true);
      setTimeout(() => setCopied(false), 2000);
    } catch {}
  };
  const clipboardIcon = <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
            <title>Copy</title>
            <rect x="9" y="9" width="13" height="13" rx="2" ry="2" />
            <path d="M5 15H4a2 2 0 0 1-2-2V4a2 2 0 0 1 2-2h9a2 2 0 0 1 2 2v1" />
        </svg>;
  const checkIcon = <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
            <title>Copied</title>
            <polyline points="20 6 9 17 4 12" />
        </svg>;
  const promptIcon = <svg width="16" height="16" viewBox="0 0 24 24" fill="currentColor" style={{
    flexShrink: 0,
    opacity: 0.4
  }}>
            <title>Prompt</title>
            <path d="M20 2H2v20h2V4h16v12H6v2H4v2h2v-2h16V2zM6 7h12v2H6zm8 4H6v2h8z" />
        </svg>;
  return <div className={`prompt prompt-${variant}`} style={{
    marginTop: '12px',
    marginBottom: '12px'
  }}>
            {promptIcon}
            <span className="prompt-text">{text}</span>
            <button className="prompt-copy" onClick={handleCopy} title="Copy to clipboard" type="button">
                {copied ? checkIcon : clipboardIcon}
            </button>
        </div>;
};

The **Modem Agent** is an AI assistant that can answer questions about your user feedback, find patterns, and take action.

Think of it like having ChatGPT or Claude, but with direct access to all of your Modem data — topics, discussions, people, companies — and the ability to read from and write to external tools like Linear, Slack, and GitHub. You describe what you need in plain language, and the agent queries your data, reasons over it, and executes actions on your behalf.

<Frame>
  <img src="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/images/agent-overview.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=adc12955a5a3d1ddead116aaab736794" alt="The Modem Agent has read/write access to Modem data (topics, discussions, people, companies) and external tools (Linear, Slack, GitHub, MCP Servers)." width="800" height="276" data-path="images/agent-overview.svg" />
</Frame>

## Where to Use It

### Dashboard

There are two ways to use the agent in the Modem dashboard:

* **Full-screen.** Click **Agent** in the sidebar for a dedicated, full-screen chat experience.
* **Sidebar.** From any page, click **Agent** in the top-right corner to open the agent as a sidebar panel. The agent stays open as you navigate, so you can chat while you work.

When the sidebar is open, the agent is aware of the page you're on and the data you're looking at. On list pages — like Topics or People — you can check specific rows and those items are automatically added to the agent's context. Think of it like selecting code in an IDE before asking a question: the agent knows exactly what you're referring to.

### Slack

DM the Modem bot or @mention it in any channel where it's been added. The agent responds in-thread.

<Note>
  Only members of your Modem organization can interact with the Modem bot on Slack. See the [Slack integration
  page](/integrations/slack#who-can-talk-to-modem) for details on authorization and auto-join.
</Note>

In both the dashboard and Slack, the agent maintains context within a conversation, so you can ask follow-up questions to drill into results.

## What It Can Do

### Modem data

The agent has full access to your organization's data in Modem. It can search, analyze, and take action on:

* **Topics.** Search and filter by type, priority, or time range. Update fields, merge related topics, and summarize trends across sources.
* **Discussions.** Query individual conversations within topics and trace them back to their source channel.
* **People.** Look up profiles, merge duplicates, update details, and trigger enrichment.
* **Companies.** Create companies, add people, update details, and trigger enrichment.
* **Automations.** Create scheduled or event-triggered [automations](/features/automations), then edit, pause, resume, run immediately, or delete them.

<Prompt text="What are users complaining about this week?" />

<Prompt text="Merge the duplicate profiles for sarah@acme.com" />

<Prompt text="Create an automation that summarizes bug reports every Monday" />

<Prompt text="Create an automation that posts in Slack when a GitHub PR is merged" />

### External tools

The agent can also read from and write to your connected integrations:

* **Linear.** Create and update issues, add comments, search the backlog.
* **Slack.** Post messages and summaries to channels, DM individual users.
* **GitHub.** Query issues, pull requests, and discussions.
* **[Coding agents.](/integrations/coding-agents)** Delegate implementation tasks to Claude Code, Cursor, or Devin.
* **[Custom tools (MCP).](/integrations/mcp-servers)** Use any external tools you've connected via MCP servers.

<Prompt text="Create a Linear issue for the top bug report this week" />

<Prompt text="Post a feedback summary to #product-updates" />

Some actions require confirmation before the agent executes them. See [advanced examples](#advanced-examples) below.

### Built-in tools

The agent also has a few general-purpose tools that don't require any integration setup:

* **Web search.** Search the web to supplement its answers with up-to-date information.
* **Image generation.** Generate images from text descriptions, useful for drafting visuals or diagrams.

<Prompt text="Search the web for recent benchmarks on React Server Components" />

<Prompt text="Generate an image of a dashboard showing user engagement metrics" />

## Advanced Examples

The agent is most powerful when it combines your Modem data with external tools in a single workflow. Instead of manually cross-referencing feedback, triaging issues, and notifying stakeholders, you can ask the agent to do it all at once.

### Weekly feedback digest

Pair the agent with an [automation](/features/automations) to get recurring summaries or react to new events without reading every message.

<Prompt text="Summarize bug reports and feature requests from the last week, grouped by severity and popularity" />

Set this as a weekly automation and Modem will deliver the digest to your inbox every Monday.

### High-priority topic alerts

The agent can also create event automations that react as soon as something changes in Modem or GitHub.

<Prompt text="When a topic reaches high priority, notify me in Slack with the topic summary and any linked Linear issues" />

### Backlog grooming

The agent can cross-reference user feedback with your Linear backlog to find gaps, duplicates, and priority mismatches.

<Prompt text="Look at the top bug report topics from the last 2 weeks. Create Linear issues for any that don't already have one, and flag existing issues whose priority doesn't match the volume of complaints." />

> **Modem Agent:** I found 14 bug report topics from the last 2 weeks. Here's what I did:
>
> * **Created 3 new issues:** Export timeout (8 reports), mobile crash on Android 14 (4 reports), broken CSV import (3 reports)
> * **Flagged 2 priority mismatches:** ENG-341 "OAuth token refresh failure" is marked Low but has 12 complaints this week. ENG-289 "Search returns stale results" is Medium but 6 users reported it in the last 3 days.
> * **Already tracked:** 9 topics already had linked Linear issues.

### Personalized release notes

You shipped a feature, but who asked for it? The agent can trace feedback back to specific users and draft targeted announcements.

<Prompt text="We just shipped dark mode. Which customers requested it? Draft release notes for the top requesters that reference their original feedback." />

> **Modem Agent:** 23 users requested dark mode over the past 6 months. Here are the top requesters:
>
> * **Sarah at Acme Corp** (3 requests): Mentioned eye strain during late-night debugging sessions
> * **DevTeam at StartupXYZ** (2 requests): Wanted it for customer demos to match their brand
> * **Marcus** (Discord): Asked specifically about OLED battery savings
>
> Draft release note for Sarah:
> *"Remember when you mentioned eye strain during those late-night debugging sessions? Dark mode is here."*

### Identify product champions

The agent can analyze engagement patterns to find your most active and invested users, perfect for beta programs, case studies, or advisory boards.

<Prompt text="Who are our most engaged users this quarter? I'm looking for beta testers for our new API." />

> **Modem Agent:** Here are your top engaged users from Q1, ranked by message volume and topic participation:
>
> * **Jake at Dataflow** (47 messages, 12 topics): Frequent feature requester, especially around API and webhooks. Already using your REST API extensively.
> * **Priya at Orion Labs** (38 messages, 9 topics): Active in #support and #feedback. Reports detailed bug reproductions with logs.
> * **Chris at Novexa** (31 messages, 8 topics): Power user in Discord. Helps other users troubleshoot and has asked about programmatic access twice.
>
> All three have discussed API-related topics. Want me to draft an invite message?

## Related

<CardGroup cols={2}>
  <Card title="Topics" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/label-alt-multiple.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=e7fbaf23c28396ac670b89cf38e1e4a6" href="/guides/topics" width="24" height="24" data-path="icons/label-alt-multiple.svg">
    How topics are discovered and organized.
  </Card>

  <Card title="Automations" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/clock.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=d7394854697ad82de384924fc1a3a555" href="/features/automations" width="24" height="24" data-path="icons/clock.svg">
    Run AI prompts on a schedule or after specific events.
  </Card>
</CardGroup>