Connect the steps.
Drag nodes. Wire them up. Ship an AI pipeline that runs on a schedule, on a button, or as a tool in any chat.
Four steps. No code required.
- 01
Draw
Drag nodes onto the canvas — LLM, Condition, Tool, HTTP.
- 02
Wire
Connect inputs to outputs. Branch on model decisions.
- 03
Publish
Make it callable from chat or via webhook.
- 04
Run
Manual click, scheduled cron, or external trigger.
Drag, drop, deploy.
Build multi-step AI pipelines without writing orchestration code. Drop LLM, Condition, Tool, HTTP, and Template nodes onto the canvas, wire the outputs to the next inputs, and test from any node to see the full execution trace. Real-time validation catches cycles and missing connections before you run.
- Drag-and-drop nodes: LLM, Condition, Tool, HTTP, Template
- Branching paths based on model output
- Real-time validation and cycle detection
- Test from any node, see the full execution trace
Publish once, use everywhere.
Publishing a workflow makes it a callable tool that any chat or agent can reach by @-mentioning its name. Your teammates get access to complex multi-step logic through a natural language interface, with typed inputs and outputs so the model knows exactly what to pass and what to expect back. Roll back to any previous version if something breaks.
- Publish to make workflows callable from chat
- @-mention by name from any conversation
- Inputs and outputs typed via schema
- Versioned — roll back any time
Triggered your way.
Run a workflow manually with a form, on a schedule, from a webhook, or nested inside another workflow. Webhook URLs make it straightforward to trigger AI pipelines from your existing services — post to the endpoint, receive the result. Nesting lets you build large, composable systems from small, testable pieces.
- Manual: click to run with form inputs
- Scheduled: cron-style intervals
- Webhooks: external triggers via secure URL
- Nested: call one workflow from another
Composable, not brittle.
Node library
LLM, Condition, Tool, HTTP, Template, Input, Output.
Branching
Route based on conditions or model decisions.
Sub-workflows
Compose larger flows from smaller ones.
Streaming runs
Watch each node execute in real time.
Variables & templates
Parameterize prompts and HTTP requests.
Versioning
Every save is a versioned snapshot.