Three Pillars

Prism has three goals on the developer side: ship more finished work, use tokens well, and get better at prompting. The product groups its capabilities into three pillars that serve those goals — and in PRISM Score v3.0 they all roll up into a single headline number: the share of sessions you actually crushed.

Goal	v3.0 metric	Pillar that moves it
Ship more finished work	PRISM Score · Speed (CSPW)	Prompt Advisor (helps sessions reach goal_complete)
Use tokens well	Token Usage (Crush Weight, TPT)	Usage Intelligence (cost visibility) + Prompt Advisor (shorter paths)
Get better at prompting	Skill (APG)	Prompt Advisor (coaching) + Usage Intelligence (habit tracking)

See PRISM Score v3.0 for the headline score and Algorithm Overview for how a session gets graded as crushed.

Prompt Advisor

Audience: individual developers.

Helps you write better prompts and improve your AI-collaboration habits in real time and after the fact.

Feature	Description
Context-management nudges	Single-line /compact / /clear suggestions from the submit hook when a session’s turn count or context growth crosses a threshold
On-demand prompt review	/prism:advisor "prompt" returns a graded rewrite with concrete file paths and expected behavior
Session advisor cards	LLM-authored coaching cards per sub-session, tied to the weakest prompt habit — see Advisor & Summaries
Session title & summary	LLM-generated title and 1–2 sentence recap on every session, editable from the dashboard
Skill profile	Average Prompt Grade (APG) with per-pillar trends — see Skill
My Report	Chapter-based personal review with strengths, weaknesses, worst prompts, and heatmaps — see My Report

Usage Intelligence

Audience: developers first; team leads for aggregate views.

Turns raw telemetry into outcome, cost, and habit signals you can act on.

Feature	Description
PRISM Score	Crushed-session rate over time — see PRISM Score v3.0
Speed	Crushed sub-sessions per window with TTC (Time To Crush) — see Speed
Token Usage	Crush Weight, TET, TPT, and token mix — see Token Usage
Prompt Grade	Per-prompt grading with a per-session breakdown — see Prompt Grade
Trivia	Sub-sessions filtered out by the substance floor — see Trivia
Integrity	Anti-gaming flags raised against your sessions — see Integrity
Sub-session explorer	Browse and drill into any closed sub-session, turn-by-turn — see Sub-sessions

Governance — under development

Audience: team leads and platform engineers.

Caution

Governance is still under development. The pillar is scoped below for context, but the features listed aren’t available yet. Ship dates are not yet committed.

Policy and guardrails for AI-coding tool usage at the team and org level. Governance will run in the Optra gateway and activate only when gateway routing is enabled.

Planned feature	Description
Budget caps	Soft warnings and hard blocks at org / team / developer spend limits
Guardrails	DLP, PII detection, prompt-injection guard, content filtering
Model access control	Restrict which models developers can use
Cost centers & tiers	Attribute spend and assign spending tiers by role or project
Rightsizing recommendations	Data-driven policy suggestions with estimated savings

See Gateway Routing for how gateway mode works today — the routing is in place; the governance layer on top is what’s still being built.

How the pillars work together

Developer writes prompt
    → Prompt Advisor scores it, nudges if needed
    → Request routes through the gateway (if enabled)
    → Telemetry captured (Ingest → Engine)
    → Session closes on /clear or topic shift
    → Outcome judge grades it crushed / not crushed
    → Usage Intelligence updates PRISM Score, Speed, Token Usage
    → Developer improves → cycle repeats

Better prompts (Advisor) make sessions more likely to land their goal, which raises the crushed-session rate (PRISM Score) and pulls Crush Weight down (fewer tokens per finished session). The three pillars aren’t separate products — they’re three views of the same loop. Governance will plug into the gateway hop once its feature set lands.