| What it does | Take your AI support bot from 4/10 to 10/10
| Checkpoint and attack test for AI agents
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| SI
|
|---|
| Pricing model | Free trial
| Open source
|
|---|
| Pricing | Free during beta. After beta: $29/month (your own AI keys, unlimited runs) or $59/month (AI included, 50 runs/month).
| Not given
|
|---|
| Key features | - Bot Score: rates bot performance across five dimensions (rules, facts, solutions, tone, trick resistance)
- Break my bot: 15 adversarial customer scenarios test for vulnerabilities
- Fix it for me: automatically rewrites rule sheet and tests against saved situations
- Train my bot: 30-minute automated training on weak spots with test validation
- GitHub integration: sends improvements as pull requests for engineer approval
- Real chat analysis: identifies problems in actual customer conversations with privacy masking
- Knowledge check: validates bot replies against FAQ and policy documents
- AI comparison: test bot performance across Claude, ChatGPT, and Gemini with costs and speed
- Open source engine: public GitHub implementation of scoring and testing algorithms
| - Holds risky actions for human approval
- Plain code with fixed rules
- Works with any model
- Attack test reports success rates
- Logs all actions asked, answered and executed
- Open source rules readable by anyone
- Approval expires after one action
- Some actions permanently locked
- Installed via pip
|
|---|
| What makes it different | - Nothing ships without engineer approval: all changes go through GitHub pull request review
- Privacy by default: customer data anonymized, keys encrypted, uploads not stored
- Open source testing engine: full algorithm transparency available on GitHub
- Works with your existing AI: supports Claude, ChatGPT, and Gemini with user's own keys
- Unified team experience: one plan covers support, product, and engineering roles
| - Plain code rules cannot be argued with by persuasive text
- Model cannot edit the rules it runs under
- Free and open source under Apache 2.0 licence
- Publishes all test results including failures
- Independent lab with nothing for sale
|
| 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 | 0 |
| Referring domains (Majestic) | 0 | 0 |