A platform for building agents, or a comms surface where agents already run.
Lindy is a horizontal AI agent platform. You assemble Lindies in a visual builder, pick a trigger (new email, calendar event, Slack message, inbound call, webhook, or schedule), wire them to tools, and pay per action. this+that is different. It's a comms-forward AI that reads the messages your team's inbox and chat channels receive, surfaces tasks for the whole team, and runs workflows. Both products are useful. They sit in different parts of the stack.
A horizontal agent platform, or a comms-forward AI for your team's messages
AI assistants come in different shapes. We think of three waves: Wave 1 is the general-purpose chat you open and ask (Claude, ChatGPT, Gemini, Copilot). Wave 1.5 is the polished personal agent layered on top of chat. Wave 2 is the fit-for-purpose AI that owns one job end-to-end, with UI tailored to it (more in our essay on AI's second wave).
Lindy sits in Wave 1.5, the polished personal-agent tier between raw chat and fit-for-purpose Wave 2 products. Lindy puts event triggers at the center of the product. New email, missed call, Slack message, calendar event, webhook, and schedule are all first-class primitives in the Lindy builder, which makes Lindy look closer to Wave 2 at first glance. The distinction is who the product is for. Lindy is a horizontal agent platform that happens to listen to comms. You build Lindies, you pick the triggers, you wire the tools, you pay per action. The product is sold to the person building automations. this+that is the inverse: a comms surface that happens to run agents. The product is your team's inbox, Slack, Teams, and Google Chat with AI scanning every message your team receives, surfacing tasks for the whole team, and running workflows. The product is sold to the team drowning in messages. Lindy 3.0 added an Agent Builder, Autopilot (browser-use), and Team Accounts in 2025; the Gaia voice agent handles inbound and outbound phone calls. It is a serious platform. Many teams will end up using both. They solve different problems.
Feature by feature
How the two products compare across the things that matter most.
| Topic | Lindy | this+that |
|---|---|---|
| Category | Wave 1.5. Horizontal agent platform with a visual builder, hundreds of integrations, and event-based triggers across email, voice, chat, and CRM. | Wave 2. Fit-for-purpose AI that lives inside the work surface, acting on messages that arrive without you asking. |
| What the product is | An agent builder. You assemble Lindies, pick triggers, wire tools, and the agents you build run on top of your stack. | A comms surface. Your inbox, Slack, Teams, Google Chat, and Telegram with AI already running on every message. |
| Who it is sold to | The person building automations. Power users, ops people, founders who want to assemble custom AI workflows. | The team drowning in messages. Founders, CEOs, COOs, and CTOs at 20-100 person teams whose inbox has become the work. |
| Where work starts | With a trigger you configured. New email, calendar event, Slack message, inbound call, webhook, or schedule. Lindy is event-reactive, not just on-demand. | With incoming messages, automatically across all six channels. No trigger to configure for each one. |
| Channels and surfaces | Email (Gmail, Outlook), Slack, iMessage and SMS, web, mobile, plus Gaia for inbound and outbound voice. Each channel set up per Lindy. | Gmail, Outlook, Slack, Teams, Google Chat, and Telegram, continuously scanned by default. One connect-once setup, not per-workflow. |
| Task layer | No persistent team task layer. Lindies do work in the moment; tracking lives wherever the integration writes (Linear, Jira, HubSpot, etc.). | DoBox. Every message scanned for tasks, with the whole team able to see, assign, and track them in one place. |
| Workflows / routines | Visual agent builder with triggers and branching steps. Lindy 3.0 added Agent Builder (prompt-to-agent) and Autopilot (cloud computer for browser use). Multi-Lindy delegation. | Plain-language workflow builder. 32 action types. IF/ELSE branching, loops, and sub-agents. Triggered by messages or schedules. |
| Memory / knowledge | Persistent memory across surfaces (same Lindy, same memory across email, SMS, and Slack). Per-Lindy knowledge bases. Shared org memory via Team Accounts. | The brain. A writable team knowledge layer with personal and team spaces. Agents read and write. Pages can be published outward through public artifacts. |
| Team capabilities | Team Accounts (Lindy 3.0) add shared agents, shared org memory, and admin controls. | Team task assignment, shared task view, and team-request grounding (your agent searches a teammate's brain to draft a suggested reply). |
| Trust controls | Configurable confirmation steps per action. Lindies can run fully autonomous or require human approval before send or execute. | Approval gates on every workflow action. Drafts not sends by default on outbound. Provenance: every task links back to the source message. |
| Integrations | Hundreds of native integrations (Gmail, Outlook, GCal, Slack, Notion, Linear, Jira, HubSpot, Salesforce, Teams, Zoom). MCP server (Plus tier and up) makes Lindy agents callable from Claude, ChatGPT, or any MCP client. | Open MCP standard. Any tool with an MCP server or API plugs in. |
| Pricing | Plus $49.99/mo, Pro $99.99/mo, Max $199.99/mo, Enterprise custom (SSO, SCIM, HIPAA, BAA). Credit-based usage with overages at 2x. Per-user. | Free during beta. |
- Lindy is the most polished horizontal AI agent platform in Wave 1.5. The Agent Builder, branching workflows, and hundreds of integrations are mature.
- Event-triggered by default. Lindy can react to a new email, a missed call, a Slack message, or a calendar event the way Wave 2 products do.
- Gaia voice agent handles inbound and outbound phone calls, which most personal-agent products do not.
- Persistent memory across surfaces means the same Lindy carries context whether you reach it by email, SMS, or Slack.
- Autopilot (cloud computer / browser use) extends the platform beyond API-only integrations.
- MCP server makes any Lindy callable from Claude, ChatGPT, or any MCP client — useful if you want a Lindy as a step inside a larger AI workflow.
- For the person who wants to build custom AI agents and wire them into the work, Lindy is a serious pick.
- A different center of gravity. The product is your team's inbox, Slack, Teams, Google Chat, and Telegram, not an agent-builder you set up on top.
- DoBox: every message scanned for tasks automatically, with the whole team able to see, assign, and track them in one place. No "build a Lindy for that" step.
- Plain-language workflow builder for the cases where you do want custom logic. 32 action types, branching, loops, sub-agents.
- The brain is a writable team knowledge layer that agents read and update as a side effect of doing real work, not a per-Lindy knowledge base.
- Team-first design from the start: task assignment, shared views, and team-request grounding are first-class capabilities, not a Team Accounts add-on.
- Open MCP standard plus a public MCP server that makes this+that's tasks reachable from Claude Desktop, ChatGPT, or Lindy itself.
See what's waiting in your inbox
Connect your inbox and get a free analysis of the tasks, follow-ups, and open commitments this+that would surface across your channels.
Free to use · No credit card required