Skills & Agents

defineSkill

Define AI agent skills

Skills define reusable instructions and capabilities that AI agents can use within your workspace. Use defineSkill() to define skills with built-in validation:

src/skills/example-skill.ts

import { defineSkill } from 'twenty-sdk/define';

export default defineSkill({
  universalIdentifier: 'a1b2c3d4-e5f6-7890-abcd-ef1234567890',
  name: 'sales-outreach',
  label: 'Sales Outreach',
  description: 'Guides the AI agent through a structured sales outreach process',
  icon: 'IconBrain',
  content: `You are a sales outreach assistant. When reaching out to a prospect:
1. Research the company and recent news
2. Identify the prospect's role and likely pain points
3. Draft a personalized message referencing specific details
4. Keep the tone professional but conversational`,
});

Key points:

name is a unique identifier string for the skill (kebab-case recommended).
label is the human-readable display name shown in the UI.
content contains the skill instructions — this is the text the AI agent uses.
icon (optional) sets the icon displayed in the UI.
description (optional) provides additional context about the skill’s purpose.

defineAgent

Define AI agents with custom prompts

Agents are AI assistants that live inside your workspace. Use defineAgent() to create agents with a custom system prompt:

src/agents/example-agent.ts

import { defineAgent } from 'twenty-sdk/define';

export default defineAgent({
  universalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  name: 'sales-assistant',
  label: 'Sales Assistant',
  description: 'Helps the sales team draft outreach emails and research prospects',
  icon: 'IconRobot',
  prompt: 'You are a helpful sales assistant. Help users with their questions and tasks.',
});

Key points:

name is the unique identifier string for the agent (kebab-case recommended).
label is the display name shown in the UI.
prompt is the system prompt that defines the agent’s behavior.
description (optional) provides context about what the agent does.
icon (optional) sets the icon displayed in the UI.
modelId (optional) overrides the default AI model used by the agent.
responseFormat (optional) sets the agent’s default output shape. Defaults to { type: 'text' } for free-form text. Use { type: 'json', schema } to force structured JSON output. A runAgent() call or a workflow AI step can ask for a different shape, which takes precedence.
roleUniversalIdentifier (optional) binds the agent to a role your app defines. That role must not grant more than the application role, or the build fails; see Agent roles.

By default an agent returns free-form text. To get structured output, set responseFormat to { type: 'json' } and provide a schema:

src/agents/structured-agent.ts

import { defineAgent } from 'twenty-sdk/define';

export default defineAgent({
  universalIdentifier: 'c4d5e6f7-a8b9-0123-cdef-456789012345',
  name: 'lead-scorer',
  label: 'Lead Scorer',
  prompt: 'Score the lead and explain your reasoning.',
  responseFormat: {
    type: 'json',
    schema: {
      type: 'object',
      properties: {
        score: { type: 'number', description: 'Lead score from 0 to 100' },
        summary: { type: 'string', description: 'Short reasoning for the score' },
      },
      required: ['score', 'summary'],
      additionalProperties: false,
    },
  },
});

Schema notes:

The schema is a flat object: each property’s type must be a primitive (string, number, or boolean). Nested objects and arrays are not supported.
description (optional) on each property guides the model on what to put there.
required (optional) lists the properties the model must always return.
additionalProperties: false (optional) forbids any property not declared in properties.

runAgent

Run an agent from a logic function

runAgent() lets a logic function run one of your app’s agents (with its skills and tools). Identify the agent by the universalIdentifier you passed to defineAgent(), and pass what you want it to work on as input:

src/logic-functions/run-enricher.ts

import { runAgent } from 'twenty-sdk/logic-function';

const { threadId, status, result, error, success } = await runAgent({
  agentUniversalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  input: 'Enrich House Ad <recordId>: fill empty fields from its listing URL.',
});

Key points:

input is a string, or a list of 1 to 100 messages ({ role: 'user' | 'assistant', content: string }). A user message can also carry file attachments (see below). To hold a conversation, pass a thread rather than replaying earlier turns yourself.
By default the call waits for the agent, which can read/update records itself via its own tools — runAgent() resolves once the run completes. Pass waitForCompletion: false to resolve as soon as the run starts: status is then RUNNING and result: null, and the reply lands in the threadId conversation. A run that outlasts 15 minutes also resolves as RUNNING.
The agent can also pause until a record changes or some time has passed. runAgent() then resolves with success: true, status: 'SUSPENDED' and result: null; the agent goes on by itself later, and its reply lands in the threadId conversation. A call to a thread whose agent is still waiting fails until it finishes.
Every call is stored with its input and status, plus its reply and usage when it completes, so it shows up in the agent’s runs. Without a thread, a call gets a conversation of its own: threadId names it, and a later call never sees it.
An app can only run its own agents.
The app’s default role must grant the AI permission flag — add SystemPermissionFlag.AI to its permissionFlagUniversalIdentifiers (or set canAccessAllTools: true). Without it, runAgent() fails with a permission error.
Set a generous timeoutSeconds on the logic function — agent runs can take several seconds.
status is COMPLETED with a non-null result when the run completes without waiting; SUSPENDED with success: true and result: null while it waits; RUNNING with success: true and result: null when the call did not wait for the run; FAILED with success: false and error holding the reason (for example, when the workspace ran out of AI credits mid-run).

src/roles/default-role.ts

import { defineApplicationRole, SystemPermissionFlag } from 'twenty-sdk/define';

export default defineApplicationRole({
  universalIdentifier: 'b648f87b-1d26-4961-b974-0908fd991061',
  label: 'Default function role',
  // runAgent() requires the AI permission flag on the app's default role.
  permissionFlagUniversalIdentifiers: [SystemPermissionFlag.AI],
});

Avoid loops: if you call runAgent() from a *.updated database-event trigger and the agent updates the same record, scope the trigger with updatedFields to a field the agent never writes (e.g. the source URL), or guard on whether any target field is still empty before calling runAgent().

Sending files with a message

A user message can carry attachments, so the agent sees a screenshot or a PDF instead of only its name. Each entry references a file your app has already uploaded into the agent-chat folder:

src/logic-functions/describe-screenshot.ts

const { result } = await runAgent({
  agentUniversalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  input: [
    {
      role: 'user',
      content: 'What does this error screen say?',
      attachments: [{ fileId: uploadedFileId, filename: 'error.png' }],
    },
  ],
});

Uploading requires the UPLOAD_FILE permission flag on the app’s default role, alongside AI. filename is optional and only labels the file for the model.

Only user messages may carry attachments. They cannot be represented on an assistant turn, so runAgent() rejects them there rather than dropping them.
At most 10 attachments per message.
The fileId must name a fully uploaded file in the same workspace, under the agent-chat folder. Anything else fails the call instead of quietly answering without the file.

Asking for a structured result

Pass responseFormat to get a shape for this call only. It takes precedence over the agent’s own responseFormat, so one agent can serve callers that need different outputs. It uses the same schema as defineAgent():

src/logic-functions/score-lead.ts

const { result } = await runAgent({
  agentUniversalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  input: `Score this lead: ${JSON.stringify(lead)}`,
  responseFormat: {
    type: 'json',
    schema: {
      type: 'object',
      properties: {
        score: { type: 'number', description: 'Lead score from 0 to 100' },
      },
      required: ['score'],
    },
  },
});

Continuing a conversation

Pass a thread and Twenty keeps the conversation for you: each call sends only the new input, and the agent sees the earlier turns, including what its tools returned. Use any stable identifier from your side as the key, such as a Slack channel and thread timestamp:

src/logic-functions/reply-in-thread.ts

const { result, threadId } = await runAgent({
  agentUniversalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  input: 'What was the last touchpoint?',
  additionalInstructions: 'Answer in Slack markdown.',
  thread: { key: `${channelId}:${threadTs}`, title: 'Acme renewal' },
});

Keys are scoped to your app and agent, so two apps never share a conversation. Only app access tokens can pass a thread.
input may only hold user messages: the conversation already holds the agent’s replies.
additionalInstructions are given to the model for this call only and are not stored, which suits per-request guidance such as formatting rules or a deadline. They work without a thread too.
Every run is stored as a turn with its status, failed ones included. Its usage is stored when the agent returns, even if it ran out of credits. A failed run is not part of the conversation, so the next call does not see it.
Calls on the same thread run one at a time: a second call waits for the first to finish, so each one sees the turns before it.
When turns run as different members (see below), each one only sees the text of the others’ turns, never their tool results, since those were read with someone else’s permissions.

Running on behalf of a workspace member

Pass runAsWorkspaceMemberId when the run is triggered by a person — a chat bot answering a message, for instance — so the agent acts as that member instead of as the app:

src/logic-functions/answer-question.ts

const { result } = await runAgent({
  agentUniversalIdentifier: 'b3c4d5e6-f7a8-9012-bcde-f34567890123',
  input: 'How many open opportunities do we have?',
  runAsWorkspaceMemberId: '20202020-0687-4c41-b707-ed1bfca972a7',
});

The run then acts with the member’s own role: it can do whatever that member can do and nothing more, records it creates are attributed to them, and their row-level permissions apply. The agent’s role does not participate — it is the app’s default for runs with nobody behind them. Omit the field for autonomous runs (scheduled jobs, database-event triggers): those keep the agent’s own role. The acting application stays attached to the run’s context for provenance, without narrowing the member’s permissions.Your app is responsible for mapping the person who triggered the run to a workspace member. Naming one requires an app access token, and what a token may name depends on whether it carries a user:

A token with no user attached may name any member. A logic function runs with one, and so do tokens minted through client_credentials or from an API key.
A token issued on behalf of a user, as a front component receives, may only name that user’s own member.

Anything else — a plain user session, an API key without an app token — may not name a member at all.

runAgent() throws when the workspace member cannot be resolved — an unknown or removed member, or one with no role. It never falls back to the agent’s own role, since that would grant more access than the caller asked for.

sendInboxMessage

Start or continue a conversation in members' chats

sendInboxMessage() posts a message from your app in the chats of one or more workspace members. It can end on a tool call the member answers from the chat, after which the conversation continues with Twenty’s assistant.

src/logic-functions/notify-first-recording.ts

import { sendInboxMessage } from 'twenty-sdk/logic-function';

const { threadId } = await sendInboxMessage({
  workspaceMemberIds: [workspaceMemberId],
  threadKey: 'first-call-recording',
  idempotencyKey: 'first-call-recording',
  title: 'Your first call recording is ready',
  text: 'Your first call was recorded: **Weekly sync**.',
  toolCall: {
    toolName: 'ask_question',
    input: {
      header: 'Share',
      question: 'Do you want to share it with the other attendees?',
      options: [{ label: 'Draft a recap email' }, { label: 'Not now' }],
    },
  },
});

Key points:

workspaceMemberIds lists the members who receive the conversation, at least one. The first member of a new conversation owns it, and the others follow it as participants. A later send under the same key that lists new members adds them; members it leaves out keep the conversation.
threadKey picks the conversation for this app, shared by every member it is sent to. A new key starts a conversation titled title; a key you used before adds the message to that conversation.
idempotencyKey identifies the message within the conversation. Sending again with the same keys writes nothing new, so retries and concurrent runs never duplicate a message.
toolCall (optional) ends the message on one of:
- a call the member answers, which pauses the conversation: ask_question (one multiple-choice question), request_form (fields to fill in) or propose_tool_call (a call to approve). Its input takes the toolName, the arguments you would call the tool with and a one-sentence summary. The tool must be one your app’s default role could run itself, such as create_one_person or update_one_opportunity (with the record id); an email (send_email or draft_email, with recipients, subject and a body in HTML) needs no permission of your app. The member reviews the call in the same card as a call the assistant proposes, edits it if they want, and the approved call runs with their own access;
- one of your app’s own tools, by logicFunctionUniversalIdentifier, rendered by its front component with the input and output you pass. It does not pause the conversation.
Only one call the member answers can wait in a conversation at a time: sending another before they answer fails with THREAD_AWAITING_ANSWER. Plain messages and app tool calls are still accepted.
Only the member who owns a conversation can delete it, and a deleted conversation is gone for every member: it is not recreated, and nothing is added to it. The other members can unsubscribe to take it out of their own inbox.
Every member must have the AI permission, and the call fails without writing the message when one of them cannot have the conversation. Your app’s default role must grant SystemPermissionFlag.AI.

Overview

Apps

API

Self-Host

Contribute

UI Library

Sending files with a message

Asking for a structured result

Continuing a conversation

Running on behalf of a workspace member

​Sending files with a message

​Asking for a structured result

​Continuing a conversation

​Running on behalf of a workspace member

Sending files with a message

Asking for a structured result

Continuing a conversation

Running on behalf of a workspace member