Files
twenty/packages/twenty-docs/user-guide/ai/overview.mdx
T
BOHEUS 00e5917d4d Documentation update (#23091)
<!-- This is an auto-generated description by cubic. -->
<a
href="https://cubic.dev/pr/twentyhq/twenty/pull/23091?utm_source=github"
target="_blank" rel="noopener noreferrer"
data-no-image-dialog="true"><picture><source
media="(prefers-color-scheme: dark)"
srcset="https://www.cubic.dev/buttons/review-in-cubic-dark.svg"><source
media="(prefers-color-scheme: light)"
srcset="https://www.cubic.dev/buttons/review-in-cubic-light.svg"><img
alt="Review in cubic"
src="https://www.cubic.dev/buttons/review-in-cubic-dark.svg"></picture></a>
<!-- End of auto-generated description by cubic. -->
2026-07-21 17:39:39 +02:00

55 lines
1.8 KiB
Plaintext

---
title: AI
description: AI-powered features in Twenty.
---
<Frame>
<img src="/images/user-guide/workflows/robot.png" alt="AI" />
</Frame>
## Features
Currently, Twenty offers:
### 1. AI Chatbot
A conversational assistant that understands your context and has access to all your Twenty data.
**Key capabilities:**
- **Full data access**: Query any record, relationship, or metric in your workspace
- **Page context awareness**: Reference "this company" or "this opportunity" based on where you are in Twenty
- **Natural language**: Ask questions and get answers without navigating menus
**Example prompts:**
- "What opportunities are closing this month?"
- "Which deals have been in Negotiation for more than 30 days?"
- "Summarize my interactions with this person"
### 2. AI Agents in Workflows
Extend your workflows with AI-powered actions and autonomous agents.
**Key capabilities:**
- **AI actions**: Use AI to enrich data, classify records, generate summaries, and more
- **Autonomous agents**: Let agents execute multi-step tasks within a workflow
- **Custom prompts**: Define exactly how AI should process your data
**Use cases:**
- Automatically categorize inbound leads
- Enrich company data from public sources
- Generate follow-up email drafts based on meeting notes
- Score opportunities based on engagement patterns
## Permissions and Access Control
AI agents are managed through the existing permissions system:
1. Go to **Settings → Members → Roles**
2. Configure which data each AI agent can access
3. Set read/write permissions per object
This ensures AI agents respect your data governance policies and only access what they need.
- Follow our [GitHub](https://github.com/twentyhq/twenty) for development updates
- Join our [Discord](https://discord.gg/UfGNZJfAG6) to share feedback and feature requests