AI Command
A coordinated intelligence team, not a chatbot
Each agent holds a narrow mandate, permissioned memory and visible provenance. You can always see which agents collaborated, what evidence they used, their stated confidence, and whether a human validated the recommendation.
9 specialist agentsProvenance visibleHuman decision authority
Agent roster
Agent detail
Reasoning and hypothesis testing
THE ANALYST
Organizes supporting and contradicting evidence, exposes assumptions and forces confidence to be stated.
Latest transmission
“You have three facts and one belief. Tell me which is which.”
- Working instrument
- REASON™
- Memory scope
- Current case + your competency record
- Human validation
- Required before any assessment is filed
- Stated confidence
- Moderate — provenance gap flagged
Orchestration sequence
ACTIVE- 01STUDENT proposes hypothesis
- 02THE ANALYST evaluates reasoning
- 03THE CARTOGRAPHER examines relationships
- 04THE ARCHIVIST checks evidence
- 05THE ORIGIN SPECIALIST examines media
- 06THE ADVERSARY challenges assumptions
- 07THE COUNSEL identifies boundaries
- 08THE BRIEFER organizes findings
- 09THE INVESTIGATOR DECIDES
Hunter™
Human judgment
ANALYST
CARTOGRAPHER
ARCHIVIST
SENTINEL
ORIGIN
ADVERSARY
COUNSEL
BRIEFER
- 01 · STUDENT proposes hypothesis
- 02 · THE ANALYST evaluates reasoning
- 03 · THE CARTOGRAPHER examines relationships
- 04 · THE ARCHIVIST checks evidence
- 05 · THE ORIGIN SPECIALIST examines media
- 06 · THE ADVERSARY challenges assumptions
- 07 · THE COUNSEL identifies boundaries
- 08 · THE BRIEFER organizes findings
- 09 · THE INVESTIGATOR DECIDES
The investigator decides.
Standing rule
AI accelerates the investigation. The investigator owns the conclusion.
A confident model output is not a finding. Ask which evidence produced it, what would falsify it, and whether a human is willing to sign it.