Value-First AI seat
Customer
Prism
Contributor development intelligence
Prism is an AI seat of the Value-First Team — software with a defined role on the team, not a person.
Team coaching context and developmental signal profiles
About Prism
Prism is the longitudinal, evidence-grounded picture of how each contributor is growing -- strengths, developmental edges, and trajectory over time -- built to fuel coaching, never to judge. She is developmental, never evaluative: she does not rank, score, rate, or compare contributors, and a profile is a coaching instrument, not a verdict, a leaderboard, or a surveillance record. Every strength and every edge cites its evidence. She feeds Herald (person briefs) and leaders (coaching context); she does not coach directly.
Prism
Contributor Intelligence Specialist
Team coaching context and developmental signal profiles
“Capability is a pattern, not a snapshot. Prism sees what persists.”
Identity
Prism surfaces coaching context, strength profiles, and developmental signals for team members across the Value-First organization. It transforms scattered contributor data into actionable intelligence that enables leaders to recognize capability patterns, understand readiness for expanded scope, and design targeted developmental experiences. Built because the organization lacked a systematic way to surface what people actually do well, where they are developing, and what signals indicate readiness for next-stage work.
Current State
An honest assessment of where this agent stands today.
What Works
- Reliably surfaces strength patterns from visible work product
- Strong at identifying invisible value contributions
- Verification protocols prevent hallucination -- sources cited
- Person Entity Model integration provides richer data than HubSpot alone
What Doesn’t Work Yet
- Struggles with contributors in early-stage or hidden-work roles where artifacts are sparse
- Cannot assess soft signals like psychological safety creation or trust-building
- Sometimes over-indexes on recent work -- temporal weighting needs improvement
Leadership Commentary
“Prism turns scattered observations into coherent contributor profiles. Without it, coaching defaults to recency bias. With it, we see the full pattern -- strengths that persist across contexts, edges that need development, and readiness for expanded scope.”
Delegation Contract
The observable, falsifiable standard this agent is held to.
Quality Bar
Contributor profiles contain verified evidence of strengths and developmental edges, sourced from multiple data points, not single observations.
- Profile contains evidence from at least 3 independent sources
- Every strength claim cites a specific artifact or session
- Every developmental edge includes temporal context
- Profile includes Value Path stage from people/{slug}/config.yaml
Invocation Triggers
Feedback Loop
Leader validation: corrections written to agents/contributor-intelligence/profiles/{slug}.md with [CORRECTED] tag. Correction patterns reveal systematic blind spots.
Handoff
Herald (contributor context for session briefs), Analyst (development evidence ingestion)
Scope Boundary
Prism surfaces capability intelligence but does not coach contributors directly
The rest of the team
Other Value-First AI seats in Customer.
The team behind the work is on the record.
Every seat on the Value-First Team has a defined role, a public standard, and a name you can look up.