Prism AI PR Reviewer
Autonomous Tree-sitter AST semantic code analyzer & pull request reviewer engineered for CI/CD.
Architecture
Prism runs as a high-throughput Rust binary integrated directly into GitHub Actions or GitLab CI. It computes AST-level deltas between git commit SHAs, identifies mutated control-flow paths, validates type signatures, and constructs a dense context payload containing only relevant caller/callee graphs. This payload is scored against security heuristics and evaluated via high-precision LLM reasoning.
Key Decisions
Built native Tree-sitter bindings in Rust for Rust, Go, Python, TypeScript, and Kotlin.
Impact: Reduced token usage by 68% and eliminated formatting-related hallucinated review comments.
Pre-screened changes for known CVE patterns and concurrency hazards before LLM invocation.
Impact: Zero API cost spent on files that statically pass invariant checks.
Generated direct unified diff suggestions that developers can accept with a single click in GitHub PRs.
Impact: Decreased PR review cycle turnaround times by 42% across adopting engineering teams.
Benchmarks
| Metric | Prism AI PR Reviewer | Standard / Competitor |
|---|---|---|
| Average Review Latency | 720 ms | 4,800 ms (Raw Diff LLM Bot) |
| LLM Tokens per 500 LOC PR | 1,450 | 6,800 (Full File Context Wrapper) |
| Signal-to-Noise Ratio | 96.4% | 61.2% (Standard AI Bot) |
Installation & Setup
npm install -g @akilaisadev/prism
# Or add directly as GitHub Action:
uses: akilaisadev/prism-action@v2
with:
github-token: ${{ secrets.GITHUB_TOKEN }}