| Key features | - Geometric foundational models for blueprint analysis
- Automatic extraction of areas, lengths, counts, volumes, and materials
- Traceability back to sheet, layer, and geometry source
- Visual verification with detections drawn back onto sheets
- Takeoff API for programmatic access
- MCP server integration for AI agents
- Support for electrical, plumbing, and interior finishes divisions
- Workflow support for estimation, RFI extraction, submittal review, and spec review
- Construction tool integrations with Trimble, Fieldwire, and Contractor Foreman
| - Agent trace debugging with step-by-step timeline view
- LLM judge evaluations on production traces with templates
- Token spend tracking by model, agent, tool and user
- AI Assistant for natural language questions over data
- Dashboard templates for traces, analytics and spend
- OpenTelemetry native ingestion
- Correlation of traces, events and user sessions
- Silent regression detection with daily quality comparisons
- Cost leak identification from failing tools and retries
- User journey analysis joining traces with funnels and events
|
|---|
| What makes it different | - No bespoke models or per-project retraining required
- Full traceability with every quantity keyed back to source geometry
- Same foundational models accessed through app, API, or MCP server
- Built by industry experts with deep construction and AI backgrounds
| - Catches AI failures that don't throw errors, like silent regressions and cost leaks
- One platform connecting traces, evals, spend and product analytics for comprehensive understanding
- AI Assistant to ask questions in plain English instead of writing queries
- Compare changes against production evidence rather than demos
- Integrations with major AI frameworks without code changes to production tools
|
|---|
Kamai