Skip to content

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

PRISM Score

The PRISM score measures the quality of your AI-assisted coding sessions across five dimensions.

PRISM = 0.25×PQ + 0.20×IE + 0.20×VD + 0.10×TU + 0.10×AF

Each dimension has two metrics, each scored 0–10. The dimension score is the average of its two metrics.

How well-crafted your prompts are.

  • Specificity (0–10): Does the prompt include file paths, function names, line numbers, error messages?
  • Decomposition (0–10): Is the prompt focused on a single task, or bundling multiple requests?

High PQ example:

“Fix the null pointer in src/auth/validate.ts:42 — the user.email field is undefined when the OAuth callback has no profile scope”

Low PQ example:

“fix the bug”

How quickly you converge on a solution.

  • Convergence (0–10): Do subsequent prompts build toward a solution, or circle back?
  • Recovery (0–10): When things go wrong, do you recover efficiently or retry blindly?

Whether you validate AI-generated code.

  • Review (0–10): Do you review output before accepting?
  • Validation (0–10): Do you run tests, check types, or verify behavior?

How effectively you use available tools.

  • Selection (0–10): Do you choose the right tool for the job?
  • Context (0–10): Do you provide sufficient context for tool execution?

Whether you leverage advanced AI capabilities.

  • Delegation (0–10): Do you use subagents, skills, or parallel tool calls?
  • Configuration (0–10): Do you use CLAUDE.md, hooks, plan mode, or MCP servers?
RangeTierDescription
9.0–10.0EliteOptimal AI collaboration patterns
7.0–8.9ExpertStrong habits with minor gaps
5.0–6.9ProficientSolid foundation, room for improvement
3.0–4.9PractitionerDeveloping skills, significant improvement possible
0.0–2.9NoviceEarly stage, high token waste likely

Higher PRISM scores correlate with lower token consumption:

TierToken multiplierMeaning
Elite~1xBaseline efficient usage
Expert~1.3xSlightly above minimum
Proficient~1.8xNearly double the tokens
Practitioner~2.5xSignificant waste
Novice~3–5x3–5x more tokens than necessary

A Novice-tier developer might spend $50/month where an Elite-tier developer spends $10 for equivalent output.