A client's AI features were burning through their OpenAI budget 3x faster than projected. Adding OpenTelemetry's GenAI semantic conventions revealed the problem wasn't what anyone expected.
- Published On
ai
- A startup founder built their MVP almost entirely with AI coding agents. It worked. Then they hired a team, and within two months nobody could ship anything. I got called in to figure out why.
- Published On
- A client's team tripled their PR output with coding agents. Six weeks later, their cycle time had doubled and nobody could explain why.
- Published On
- AI code review tools are everywhere now. After rolling one out on a real project, I learned more about our team than about the tool itself.
- Published On
- The latest DORA report confirms what I've seen on consulting engagements — AI tools amplify existing conditions. If your processes are solid, AI accelerates you. If they're not, you just create technical debt faster.
- Published On
- Practical insights from months of using AI-assisted coding in real client projects — what works, what doesn't, and how it changed my workflow.
- Published On
Tags
consulting (45)debugging (20)architecture (15)developer-experience (14)reliability (13)devops (7)observability (7)performance (7)code-quality (6)ai (6)kubernetes (4)postgres (4)database (4)technical-debt (3)microservices (3)testing (3)engineering-culture (3)databases (2)security (2)opentelemetry (2)monitoring (2)postgresql (2)productivity (2)ci-cd (2)tooling (2)javascript (2)goals (2)error-handling (1)secrets-management (1)webhooks (1)infrastructure (1)resilience (1)containers (1)environments (1)queues (1)cloud (1)cost-optimization (1)orm (1)refactoring (1)on-call (1)alerting (1)incident-management (1)typescript (1)distributed-systems (1)caching (1)platform-engineering (1)dependencies (1)deployment (1)code-review (1)feature-flags (1)api (1)contracts (1)logging (1)mongodb (1)migration (1)workflow (1)nestjs (1)angular (1)sandbox (1)sonarcube (1)learning (1)journey (1)mdx (1)