Flamegraphs Find It. Replay Proves It.
Use Grafana Pyroscope and proxymock with an AI coding agent to find a Go CPU hotspot, preserve API behavior, and verify the performance fix.
Posts about ai/ml
Browse 39 posts in this category
The Best Model Is a Routing Decision
The best model isn't the smartest — it's whichever should get the next unit of work. Notes from NVIDIA on routing, local models, and the AI factory.
Imaginary Test Data. Real Token Bill.
Testing AI applications with invented traffic looks fine until real users arrive. Then come the retries, the fallback models, and the token bill.
AI writes code in seconds, but delivery still takes days
AI pushed throughput up 59%, yet median delivery got worse. The bottleneck moved to validation. How replaying production traffic in CI closes the gap.
The Three Pillars Were Built for Humans
Metrics, logs, and traces were built for humans and cheap storage. AI inverts both assumptions, and the next maturity level is a deterministic replay sandbox.
Which Bugs AI Agents Fix Better With Traffic
A second run of our AI bug-fixing benchmark shows where captured traffic lifts agents toward 90%, why service maps barely help, and which bugs still fail.
We won't train on your data is not a security architecture
MSA clauses and contractual guarantees aren't an architecture. If your production traffic leaves your cloud, you're trusting a policy, not a system.
The AI Code Explosion: Why Your Mocking Strategy is Breaking Down
AI-generated code breaks traditional mocking. Here's how BYOC capture and replay with proxymock keeps verification grounded in real production traffic.
Your AI agent is fixing the wrong service
I tested 100 bugs across 240 microservices the model has never seen. Alert only: 51% pass rate, wrong service 34% of the time. Traffic captures: 77%.