Tech Freshness Defense
Benchmarked against: Anthropic — Reduce hallucinations Version: 1.0 | Scope: All agents
Your training data is ~10 months old. Any fast-moving library API you "know" is probably wrong.
PK (Perishable Knowledge) = fast-moving tech knowledge that expires. This is the single biggest risk to code quality in an AI-driven team.
The problem
AI models confidently generate code using APIs that no longer exist. Real incidents:
- Three Work Orders rejected in a single day for the same root cause (no Pre-Flight Check)
- Fabricated version numbers (e.g., "LangGraph 2.0" when actual version was 1.0.9)
- Code using deprecated APIs that fail at runtime
Captain's directive: enforce with tools, not discipline.
Knowledge classification
| Category | Examples | Rule |
|---|---|---|
| Timeless | Design patterns, algorithms, frameworks | Use directly |
| Perishable | Library versions, API signatures, config formats | Verify before using |
Danger Zone libraries
These libraries change APIs frequently. Never write code from memory when importing from these:
| Ecosystem | Why dangerous | How to verify |
|---|---|---|
ai / @ai-sdk/* | Vercel AI SDK v4→v5→v6 broke APIs completely | Read node_modules/ai/package.json + actual exports |
next / next/* | Next.js 14→15→16 changed App Router, caching, middleware | Read node_modules/next/package.json |
@cloudflare/* | Workers API evolves fast | Check wrangler.toml + Cloudflare docs |
@supabase/* | Client APIs change between major versions | Read actual installed version |
langchain / langgraph | v0.x→v1.x API overhaul | Check .venv installed version |
Mandatory verification steps
When modifying code that imports from a Danger Zone library:
- STOP — Do not write code from memory
- CHECK VERSION — Read
package.jsonorpip show <pkg>for installed version - CHECK ACTUAL API — Read the actual source in
node_modules/or.venv/lib/ - THEN write code — Based on what you verified, not what you "know"
Skipping freshness verification on Danger Zone libraries = work accident.
Pre-Flight Check integration
The Pre-Flight Check 3D scoring system includes Knowledge Freshness as one of three dimensions:
Blast Radius × Knowledge Freshness × Reversibility = Risk Score (0-6)
Enforcement
Tech freshness is enforced through:
- Pre-commit hooks that check for Pre-Flight Check records
- WO submission gates requiring freshness verification
- Danger Zone auto-detection in import statements