Visual Agent-in-Workflow Builder

node editor demo — the agent is just another step

Node Palette

Port colors = data type

event payload
structured JSON
agent output (fuzzy)
boolean branch
add nodes in order: trigger → … → action

Execution Log

— pipeline idle —
Nodes auto-wire left → right.
Condition nodes branch: true = upper pipe, false = lower (drops packet).
Drag canvas to orbit · wheel zooms.

Triggers vs Polling

A trigger (webhook) is push-based: the source calls you the instant something happens — cheap and low-latency. Polling asks "anything new?" on a schedule — simpler to build, but wastes calls and adds up to one full interval of delay. Most platforms (Zapier, n8n, ByteChef-style tools) support both and prefer webhooks when the source offers them.

Deterministic Steps vs Agent Steps

A Fetch or Send step is deterministic: same input, same output, easy to test and retry. An agent step embeds an LLM that plans, calls tools, and returns fuzzy output. Best practice: constrain the agent to a schema (structured JSON out), keep it sandwiched between deterministic steps, and validate its output before anything irreversible runs.

Retries & Idempotency

Networks fail, so workflow engines retry failed steps (often with exponential backoff). That's only safe if steps are idempotent — running twice has the same effect as once. Techniques: idempotency keys on writes, "upsert" instead of "insert", and never retrying a payment step without a dedupe token.

Agent Inside Workflow — or Workflow Inside Agent?

Agent-as-step (this demo, and ByteChef's open-core model): the workflow owns control flow; the agent handles one fuzzy task (classify, summarize, extract). Predictable, auditable, cheap. Agent-as-orchestrator: the agent decides which workflows/tools to call — flexible for open-ended goals, but harder to test and bound. Rule of thumb: if you can draw the flow in advance, make the agent a step.

Enjoy this tool? Build your own with Super