AI Agent

Runs an AI agent that completes a task using the context and capabilities you grant it.

Overview

The AI Agent node sends a task to an AI agent that works autonomously across multiple steps before returning a result. Unlike Prompt AI, which answers a single prompt in one shot, the agent can be granted capabilities — like browsing the web — and decides on its own how to use them to complete the task. Use it to:

• Research information on the web and return structured findings
• Answer questions that require reading several pages or documents
• Combine attached files with live web data

Parameters

Parameter	Description	Required
Prompt	The task for the agent to complete	Yes
Context & Capabilities	Files the agent can read and capabilities it may use	No
Response Format	Text, JSON, or JSON Schema (default: Text)	No
JSON Schema	Schema constraining the response (only shown for JSON Schema)	No
Max Steps	Maximum reasoning steps per run, 1-30 (default: 8)	No
View Live	Watch the agent's browser live while it runs (web browsing only)	No

Prompt

Describe the task. Use expressions to include item data:

Find the current pricing for {{$item.data.competitorName}} and summarize their plans.

Context & Capabilities

A list of items the agent gets access to. Each item is one of:

• Files — files (PDF, image, text) the agent can read as context. Use an expression to pass a variable number of files. The optional Description tells the agent what the files contain, so it only opens the ones the task actually requires. Files are limited to 50 pages total.
• Web Browsing — grants the agent a remote browser. It can visit pages, read their text and links, take screenshots to inspect page layout, and interact with pages by clicking elements and typing into inputs. Each run can load at most 50 MB of network data. Options:
  • URL — limit the agent's direct navigation to this site. It will not open unrelated URLs on its own, though it can still follow links on the pages it visits. Leave empty to allow browsing anywhere.
  • Allow files — let the agent download files and capture screenshots while browsing and return them as files from this node. Off by default.
  • Allow ads — ads are blocked by default. Turn this on for sites that refuse to work with ads blocked.

Response Format

• Text — the result is returned as a plain string.
• JSON — the agent must return valid JSON, parsed into an object you can reference downstream (e.g. {{$item.data.summary}}).
• JSON Schema — the agent must return JSON matching the schema you provide. See the Prompt AI documentation for the supported schema keywords.

Output

The node outputs one item per input item with the agent's result in the data field:

{{$item.data}}

When Allow files is enabled and the agent produces files (screenshots or downloads), they are returned on the item's files field for downstream file nodes to consume:

{{$item.files}}

Billing

Each run is billed from your AI allowance based on the tokens the agent consumes (input, output, and cached tokens, priced per model).