Fix agent prompt cache misses by splitting the system prompt at a shared marker. Cloudflare's first request hit cache 14-26% of the time. Audit and fix inside.
Build an observability knowledge graph for incident RCA: Netflix's ontology, a runnable RDF + SHACL demo, and the 42-second query where toy graphs break.
Fix a Postgres storage bottleneck: 3 queries to confirm it, and a test where local NVMe hit 9.2x the TPS of gp3. Plus the durability bill nobody quotes.
A 15-30% traffic anomaly or outage? Cloudflare's eclipse analysis shows the fix: five-minute buckets against a three-week matched baseline.
A zero downtime database migration is five feature-flagged phases, not a cutover. P95 said 4x slower, P90 said 17x, and the comparison code took a region down.
AI Gateway for Workers AI is now one argument on env.AI.run. What it logs instantly, why caching stays off until you ask, and the 60-second TTL floor.
Run agent tool calls in parallel by swapping the loop for a DAG planner: ten round trips become two levels, plus the cap, budget and critic on top.
How to secure MCP write tools: the spec puts confirmation on the client — the one layer you don't control. Cloudflare's WriteGuard moves the gate server-side.
Production-grade AI agents need more than a working demo. 353,000 signed up to learn agents; 6,000 shipped a capstone. Here's exactly what closes the gap.