Documentation
Everything you need to generate, build, connect and run AI agent workflows with Worfilo.
- Getting started: build your first AI agent workflowGet started with Worfilo: create an account, connect your apps and APIs, then generate or build your first AI agent workflow and watch it run live.
- Generate AI agent workflows from a descriptionGenerate AI agent workflows from a plain-language description: Claude drafts a validated graph with your apps, APIs and MCP servers, ready to refine.
- Building AI agent workflows on the canvasHow Worfilo workflows are structured: triggers, nodes, ports, data edges and tool edges, branching and merging, and how the executor decides what runs.
- Runs and replay: watch AI workflows run step by stepRun an AI agent workflow and watch each node's status live, inspect its inputs and outputs, test one node, and replay any run on the graph it used.
- Templates and expressions: pass data between nodesPass data between workflow nodes with Jinja templates: read the trigger payload and upstream outputs, branch on expressions, and keep raw values intact.
- Schedules and triggers: run workflows automaticallyRun AI agent workflows on a schedule: pick daily, weekly or a cron expression, set a timezone and payload, preview the next runs, and run it now.
- Connectors: GitHub, Slack, Notion, Linear and TavilyConnect GitHub, Slack, Notion, Linear and Tavily to your Worfilo account, then run their actions as workflow steps or give them to an agent as tools.
- Custom APIs: connect any HTTP API with any authRegister any HTTP API once with its base URL and auth, from no auth and API keys to OAuth 2.0 and AWS Signature v4, then call it from workflows and agents.
- MCP servers: a marketplace of tools for your workflowsConnect Model Context Protocol servers from the Smithery marketplace or by URL, then call their tools from a workflow node or hand them to an agent.
- Publishing and versions: draft vs published workflowsPublish a Worfilo workflow to freeze its draft into a numbered version. Triggers and the workflow API run that version while you keep editing the draft.
- Workflow API: run workflows from your own codeCall a published workflow over HTTP with an API key and its workflow ID, send it input and get its output back, and test it first in the chat playground.
- Execution controls: retries, timeouts and error handlingControl how Worfilo runs AI workflows: per-node retries with backoff, timeouts and error modes, and run-wide parallelism, timeouts and token caps.
- Credentials and securityHow Worfilo protects API keys, app connections and MCP secrets: encryption at rest, redaction in run history, SSRF protection and sandboxed templates.
- PII masking: keep personal data away from the modelMask names, emails, phone numbers, card numbers and national IDs before an AI agent sees them, using the Mask PII node and its data profiles.
- Usage limits: plans and what countsWhat each Worfilo plan limits: workflows, runs at once, runs and AI generations per 24 hours, API keys, APIs, MCP servers and triggers.