| What it does | The evidence layer for AI-agent actions
| AI operating system for running a business with coding, research and specialist agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | 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
| Starter (Free): metered AI usage, read-only specialist areas, core integrations, 2 light workers; Founder ($79/month or $63/month annually): all 230+ integrations and 5,500+ actions, approvals, up to 5 AI workers, cloud computer, API keys, NX CLI, email support; Business ($199/month or $159/month an
|
|---|
| Key features | - 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
| - Research with sources showing where information came from
- 59 models to choose from including NX, ChatGPT, Claude and others
- 230+ integrations with 5,500+ actions across connected apps
- Approval required before risky actions like spending, sending or deleting
- Encrypted credential vault protecting account tokens at rest
- Company context memory carried between sessions
- 5 specialist departments covering 30 business areas
|
|---|
| What makes it different | - 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
| - Own AI model (NX) included with ability to switch between 59 different models
- Unified operating system for business combining coding, research and automation in one place
- Approval-based governance preventing accidental AI actions like spending or deletion
- Research functionality showing sources and allowing read-only verification mode
- Connected Google and Meta account integration with data privacy protections
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 42 ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 17 | 14 |
| Referring domains (Majestic) | 1 | 2 |