Skip to content

Search is only available in production builds. Try building and previewing the site to test it out locally.

FAQ

Optra Prism is a free intelligence layer for AI-assisted coding. It plugs into Claude Code and gives you visibility into how you use AI — then helps you improve through PRISM scoring, real-time coaching, and usage analytics.

Yes. The Personal tier is free forever — no trial, no credit card. It includes full PRISM scoring, coaching, waste detection, and analytics. Team and Enterprise plans add governance features.

  • OTEL telemetry — logs, metrics, traces (token counts, timing, model usage)
  • Prompt text — your actual prompts, used for PRISM scoring

Prompt text is used for scoring and coaching only. See the privacy policy for details.

No. The plugin hooks are lightweight:

  • Prompt scoring: <100ms (local heuristics)
  • Response timing: negligible overhead
  • Telemetry export: async, non-blocking

Gateway routing adds a small network hop (~50–100ms) if enabled. Disable it for zero latency impact.

Do I need to restart Claude Code after setup?

Section titled “Do I need to restart Claude Code after setup?”

Yes. The plugin sets environment variables on session start, so a restart is needed after initial setup or gateway toggle.

No. The prompt advisor always exits with code 0. Suggestions are advisory only — your prompt always goes through.

Change prismThreshold in ~/.prism/config.json. Default is 4. Higher = more coaching. Lower = less coaching.

Sign up at dashboard.prism.optra-ai.com to get a free gck_* key.

The LLM scorer (primary) is ~90% accurate. The heuristic fallback is ~70% accurate. Scores are calibrated against expert-rated sessions.

  • 7.0+ is Expert tier — strong habits
  • 5.0–6.9 is Proficient — solid foundation
  • Most developers start at 3.0–5.0 and improve to 6.0+ within 2 weeks

Do scores affect my Claude Code experience?

Section titled “Do scores affect my Claude Code experience?”

No. Scores are informational. They don’t limit your access, change model behavior, or affect billing. They’re purely for your awareness and improvement.

Sessions are scored by the background scoring worker after each S3 write batch (30-second debounce). Scores typically appear in the dashboard within 1–5 minutes.

Common causes:

  1. Plugin not configured — run /prism:setup gck_YOUR_KEY
  2. Session too recent — wait 1–5 minutes for data processing
  3. API key issue — verify at /prism:status

Team leads can see aggregate analytics (scores, usage, waste patterns) but not individual prompt text unless configured by an admin.

Yes. The entire stack (dashboard, ingest, engine) can run locally or on your infrastructure. See the Architecture page for the component overview and the Environment Variables page for configuration.

  • PostgreSQL (Supabase or self-managed)
  • NATS JetStream
  • S3-compatible storage
  • Node.js (dashboard)
  • Rust runtime (ingest, engine)