Phase 1
Intake validation
Verify consent, completeness, and baseline sufficiency
Owner: intake-agent
How it works
The core design principle is simple: understand the user properly, plan in the right sequence, and keep the plan alive after generation.
Phase 1
Verify consent, completeness, and baseline sufficiency
Owner: intake-agent
Phase 2
Build structured profile and user intelligence
Owner: profile-agent
Phase 3
Downgrade unsafe or low-confidence planning before deeper agents run
Owner: evaluation-agent
Phase 4
Sequence domains and choose the correct intensity
Owner: strategy-agent
Phase 5
Generate measurable actions by domain
Owner: domain-agents
Phase 6
Package outputs, initialize tasks, and expose review loops
Owner: compiler + tracker