| What it does | Publish documents for feedback, pull edits and comments back into your agent
| The evidence layer for AI-agent actions
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | GB
| US
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | 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
| Developer: Free with no time limit (1,000 verified actions/month). Builder (Founding): $59/month for first 12 months, then $99/month (5,000 verified actions/month, then 2.5¢ per action). Team: $299/month (25,000 verified actions/month, then 1.5¢ per action). Growth: $999/month (100,000 verified acti
|
|---|
| Key features | - 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
| - Records agent actions through API or OpenTelemetry spans
- Verifies actions against systems of record including Stripe, Shopify, Salesforce, HubSpot, Zendesk, Intercom and Coinbase
- Integrates with agent frameworks: LangGraph, CrewAI, OpenAI Agents SDK, Pydantic AI
- Supports workflow runtimes: Temporal and Inngest
- Action contracts define verification rules with limits and required effects
- Settlement window re-checks verify actions again at end of settlement window
- Webhooks and Slack/PagerDuty alerts on verdict results
- Public hash verification allows verifying verdicts without an account
|
|---|
| What makes it different | - 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
| - Verdicts come from deterministic rules, not language models
- Never blocks actions; verifies after the fact only
- Takes no payment from vendors; paid only by customer
- Tested against real models: Claude, GPT and Gemini
- Priced by verified actions, not seats or agent claims
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 17 |
| Referring domains (Majestic) | 0 | 1 |