Rivac AI LabsAll work
Live & Delivered
Checksum AI: Self-Healing Test Generation
Automatically generates, runs, and maintains end-to-end and API tests, opening pull requests to fix broken tests as an application changes.
Delivered and in production use.
checksum.ai
What We Built
The full scope of this engagement
An eval pipeline measuring test-generation quality and self-heal accuracy
The production-error-to-test pipeline that converts observability signals into new regression tests
Framework and integration expansion, including CI/CD and git-provider pull-request bot integrations
Customer-facing usage and ROI reporting supporting Checksum's usage-based pricing
More from our work
- Live & DeliveredComputable: Open-Source GPU Price IndexPublishes a transparent, verifiable price index for GPU compute, aggregating rates across major providers into a reproducible benchmark.
- Live & DeliveredYunique AI: AI Governance & Compliance AdvisoryA boutique advisory firm helping organizations gain visibility into internal AI use and implement defensible governance practices around it.
- Live & DeliveredPromptScout: AI Answer-Engine Visibility TrackingMonitors how brands are mentioned and cited across AI answer engines, turning the findings into weekly visibility reports and content recommendations.
- Live & DeliveredAIO.GEO Protocol: Verifiable AI-Accessibility AuditsAudits how AI systems perceive and access a website's content, issuing verifiable proof of the findings instead of unverifiable ranking claims.
- Live & DeliveredFlowTask: Company Brain for AI AgentsTurns unstructured Slack, email, and document activity into structured, tracked tasks, and compiles that context into a persistent memory layer AI agents can query.
- Live & DeliveredAgentOS (SapienX): Human Control Layer for AI Agent TeamsA control plane for deploying and governing a team of AI agents, requiring human approval before consequential actions execute.
Want a project like this?
This is real client work. Talk to us about what you're trying to build and we'll tell you honestly what it would take.
Talk to us about a project like this