Skip to main content
SuperFlow is Lyzr’s visual workflow builder. It lets you chain AI agents, LLM calls, tools, HTTP requests, code, conditionals, loops, and human approvals into a single automation — all on a drag-and-drop canvas, with no glue code to maintain. Unlike a hobby-grade flow tool, SuperFlow is built for mission-critical workloads. Every step is durably journaled, every successful step runs exactly once, and every in-flight run survives crashes, restarts, and deployments without losing work. Long-running approvals can pause for days or weeks at zero cost. Failed steps retry automatically. Past runs are replayable end-to-end. The engine you’d build yourself for a payments pipeline — but as a visual builder. You can find SuperFlow in Agent Studio.

​
When to use SuperFlow

A single Lyzr agent is great when the work fits one model with a set of tools. A SuperFlow is the right choice when:
  • You need multiple steps that aren’t all “ask the LLM” — for example, fetch from an API → run an agent → branch on the result → call another agent.
  • The flow involves branching or looping based on data (if/else, case switching, iterate over a list).
  • A human needs to approve something mid-flow before it continues.
  • You want to schedule the whole thing to run on a cron (every Monday morning, every 5 minutes, etc.).
  • You’re composing several agents together — a researcher feeds a writer feeds an editor.

​
Mental model

A SuperFlow is a graph of nodes connected by edges:
  • Every node has inputs and outputs. Data flows along the edges as JSON.
  • Each node receives the output of the nodes upstream of it, does its job, and emits its own output downstream.
  • A SuperFlow always starts with one Trigger node, which defines what input the workflow accepts.
  • Downstream nodes can reference any upstream node’s output using expressions like {{ $('Trigger').json.email }}.
This is the same idea as a flowchart — except every box is an executable step, and the lines between them carry real data.

​
Built for mission-critical workloads

These properties are what set SuperFlow apart from “good enough” workflow tools — they’re the ones you actually need when a SuperFlow is running real revenue, real customer-facing actions, or real money movement:
  • Durable execution. Every meaningful step — LLM call, tool call, HTTP request, code execution, loop iteration — is journaled to durable storage before completion. A service restart in the middle of a 50-step workflow resumes from the exact point of failure, not from the beginning.
  • Exactly-once side effects. A step that has already run successfully will never run again. No double charges, no duplicate emails, no re-fired API calls on retry. Once the journal says “this step completed,” the engine treats that as final.
  • Pauses are free. A SuperFlow waiting on a human approval, a schedule, or a delay consumes essentially no resources. Runs can wait hours, days, or weeks and resume exactly where they paused — useful for onboarding flows, escalation paths, and any process gated on human action.
  • Crash-safe schedules. Cron triggers use durable timers, not in-memory schedulers. A schedule won’t “miss a tick” because the runtime was down — queued ticks fire as soon as they’re due once the service is back.
  • Per-node retries with exponential backoff. Configure every node that talks to an external system to retry on transient failures. Retries are themselves durable — the retry count survives restarts.
  • Live and historical observability. Watch a run in real time on the canvas; replay every past run with full per-node outputs preserved. OpenTelemetry traces are emitted end-to-end without setup.
See Reliability & durable execution for the full guarantees and a mission-critical checklist.

​
Key capabilities

  • Visual canvas — drag nodes from a palette, connect outputs to inputs.
  • 30+ node types — AI Agent, LLM, HTTP Request, Code (JavaScript), If, Switch, Loop, Wait for Approval, Execute Workflow, document parsing, and more.
  • Expressions — reference any upstream node’s data with {{ $json.field }} and {{ $('NodeName').json.field }}.
  • Triggers — start a SuperFlow manually, via webhook, or on a durable cron schedule.
  • Human-in-the-loop — pause a run, route it to a person for approval, resume from there. Pauses are durable and free.
  • Sub-workflows — reuse one SuperFlow inside another with the Execute Workflow node.
  • Per-node retries — configurable max attempts and backoff for every node that calls out.
  • Live execution monitoring — watch nodes light up in real time as the run progresses; inspect per-node JSON output.
  • History — every past run is replayable with all its node outputs preserved.
  • Lifecycle controls — pause, resume, or terminate any in-flight run; controls are durably backed.
  • Sharing — share a SuperFlow with teammates so they can view, edit, or run it.

​
Where to go next