Program · PMP
Multi-agent research board
Parallel agents, scope baseline, risk register, and acceptance list share one view. The PM decides; agents explore.
Talk about this →Work
Demonstrable slices of systems. Each piece runs through research, engineering, product, and cost.
Prompt
Prompt eval and regression
Prompts as interfaces: versions, goldens, failure clusters, regression gates. Built for prompts that have to live.
Talk about this →Research
Reproducible research lab
Experiment cards, data slices, metric boards, and paper-grade reproduction scripts. Evals before demos.
Talk about this →Engineering
Full-stack agent studio
A delivery chain from PRD to preview: code, data, permissions, release. Humans appear at decision points.
Talk about this →Product
Product-grade autonomy slider
Complete, targeted edit, plan, and full agent. Each notch has permissions, audit, and interrupts.
Talk about this →CMA
AI spend ledger
Tokens, labor, rework, and risk reserves booked to cost objects. Contribution margin and rolling forecasts, weekly.
Talk about this →