Framework · Domain Agents

Lindy

Personal AI-employee platform: agents are 'woken up' by time-based, chat-based or event-based triggers (Slack/email/calendar/Sheets/webhook), run multi-step workflows over 100+ integrations and pause for human approval on confirmation-toggled or draft-mode actions.

Description

Lindy lets users build named agents that run their inbox, meetings, calendar and ad-hoc work. The docs explicitly enumerate three trigger families (time-based, chat-based, event-based) including webhooks, scheduled timers, Slack-message-received, email-received, calendar-event-started and Sheets-row-added. Agents call documented skills (HTTP, computer-use, Lindy Phone, Gmail, Slack, Salesforce, etc.), and most actions with side effects expose a confirmation toggle that pauses the workflow and emails the owner for approval. A draft mode queues outputs (e.g. Gmail drafts) for review before sending.

Solution

Trigger-driven workflows. A trigger (time-based, chat-based or event-based) wakes the agent, which executes a sequence of skills/integrations. Actions with side effects can be guarded by a confirmation toggle that pauses execution and emails the owner; on approval the workflow continues. Draft modes (e.g. Gmail drafts) collect outputs for manual review. The Pro tier adds computer-use for browser-based tools. Approval and the confirmation toggle are first-class.

Primary use cases

  • personal AI work assistant for inbox, meetings and calendar
  • event-driven automations triggered by Slack/email/calendar/Sheets/webhook
  • scheduled or recurring agent workflows via Timer skill
  • approval-gated execution of sensitive multi-step actions

Open the full interactive page

Diagram, neighbourhood map, code examples, related patterns and full provenance.