The node library ships with around two dozen node types across five groups. Mix them freely to build anything from a two-step notification to a branching, AI-driven pipeline.
The Web Search node (and an agent's web tool) query the Brave Search API, governed by a per-organization search budget. The Code and HTTP Request nodes can be disabled per workspace by an admin, so they may not appear in every workspace's library.
Start a workflow. The first node must always be a trigger.
| Node | What it does |
|---|---|
| ▶️ Manual | Run on demand from the hub. |
| 🔗 Webhook | Start from an inbound HTTP POST. |
| ⏰ Schedule | Run on a cron schedule or interval. |
| 🧩 Integration event | React to an event from a connected tool. |
| 📂 Folder watcher | Fire when a doc lands in a knowledge folder. |
| 📋 Form | Start from a submitted in-app form. |
Embed intelligence anywhere in the flow.
| Node | What it does |
|---|---|
| ✨ LLM | A single prompted model call. Free text or structured JSON. |
| 🤖 Agent | Run a full agent with tools, knowledge, and sub-agents. |
| 🌐 Web Search | Search the web via the Brave Search API. |
| 🛡️ Guardrails | Check or constrain content against rules before it proceeds. |
| 🎨 Image Generation | Generate an image from a prompt. |
| 🔎 File Search | Retrieve relevant passages from knowledge / files. |
Branch, repeat, and fan out.
| Node | What it does |
|---|---|
| 🔀 Condition | Branch on a condition — separate true / false paths. |
| 🔁 Loop | Iterate over a list, running the body for each item. |
| ⫶ Parallel | Run multiple branches at the same time and join. |
Do work and move data.
| Node | What it does |
|---|---|
| 💻 Code | Run a custom code snippet to transform data. |
| 🌍 HTTP Request | Call any HTTP API; parses JSON responses. |
| 🧩 Integration Action | Perform an action in a connected tool (create issue, send email…). |
| 📚 Knowledge Folder | Read from or write a document to a knowledge folder. |
| 🗃️ Table | Describe, validate, and materialise tabular data. |
| 🔢 Tabular Query | Query tabular data with SQL. |
| 📎 Insert Context | Fold an upstream node's output into the context. |
| 📌 Publish Result | Publish a deterministic result for downstream use. |
| ⏳ Delay | Pause the run for a set duration. |
| 🔔 Notification | Send a notification to your team. |
End the flow or pause for a person.
| Node | What it does |
|---|---|
| 📤 Output | Return the final result and end the run. |
| ✅ Human Approval | Pause and wait for a person to approve or reject. |
AI nodes see the output of upstream nodes and can return free text or structured JSON for downstream steps. The LLM node is a single prompted model call; the Agent node runs a full agent with tools, knowledge retrieval, and optional sub-agents. Both expose the same core settings:
| Setting | Description |
|---|---|
| Model | Pick any model an admin has enabled. Each node chooses independently across the six providers. |
| System prompt | Instructions for the AI. Insert upstream values with {{ }} context references. |
| Knowledge folders | Attach folders the node searches during the run. |
| Tools | Enable web search, integration actions, and more for the node to call. |
| Structured output | Define a JSON schema so downstream nodes can reliably parse the result. |
| Temperature / top-p / max tokens | Tune creativity, sampling, and response length. |
For a node that delegates to one of your saved Agents, select the agent and it supplies its own model, prompt, tools, and knowledge — you don't re-configure them on the node.
Control-flow nodes shape how execution moves through the graph. A Condition node splits into "true" and "false" paths so you can route work based on data. A Loop node iterates over a list, running its body once per item. A Parallel node fans out into branches that run at the same time and then joins their results — useful when several independent steps can happen concurrently.
An Output node returns the final result and ends the run. A Human Approval node instead pauses the run and waits for a person to approve or reject before continuing — covered in detail under Running & approvals.
Every AI node and integration action draws on your organization's budget, and when a budget is reached the relevant capability pauses automatically so costs stay predictable. Every numeric cap has a hard minimum, and 0 means disabled, never unlimited.