Visual builder for deterministic AI agent networks
Publish documents for feedback, pull edits and comments back into your agent
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
GB
Pricing model
Freemium
Not given
Pricing
Pay-what-you-think pricing during soft launch with a minimum of $5/month. 7-day money-back guarantee after activation.
Free plan: $0, up to five active documents, documents up to 4 MB, 1 GB storage, last ten versions restorable, invite up to ten people per document. Pro plan: $10 USD per month (billed as $120 per year) or $12 USD per month (billed monthly), unlimited active documents, documents up to 16 MB, 50 GB st
Key features
Real-time execution tracking with token cost monitoring
PDF rasterization and chunking for image-based PDFs
Dynamic document loading from Google Drive, APIs, and MCP sources
Quorum-based consensus verification for field extraction
Loop patterns for iterating over LLM list elements
Field-level context mapping between nodes
Self-hosted execution with customer API keys
Encrypted credential management for Drive, REST, URLs, and MCP
Non-technical user interface for prompt and flow editing
Publish HTML or Markdown files with shareable links
Readers can leave comments and edit text with author permission
Pull edits and comments back as structured data
MCP server for agents without file or command access
Custom share links with passwords and expiry dates on Pro
Version history with restore capability
Publish entire folders as sites on Pro plan
Connect to external APIs and embed sites on Pro
What makes it different
Precise control over agent paths without code-first framework overhead
Field-level context injection instead of dumping all data into prompts
Live control and inspection without redeployment cycles
Compliance-ready with self-hosted execution and customer-controlled keys
Purpose-built for PDF pipelines and document extraction workflows
Documents stay active at stable links across multiple published versions
Works natively with AI coding agents without requiring manual context management
CLI does not require Node, Python or other runtime dependencies
Screenshots in comments are listed by ID and only fetched on request
LLM Flow Designer
Onlay