Tag
I'm a Spring/Kafka backend engineer who could read Python but never wrote it. The AI world pulled me in, so I learned it by building a 10-lesson course that maps every concept back to Java, then built the tutor agent that taught me.
Traces, Tempo and the LGTM stack
If you distribute a Claude Code agent to a marketplace, every developer who runs it spends your reasoning budget and yours to answer for. Here is how I wired Claude Code's built-in OpenTelemetry into a Grafana/LGTM stack to watch cost, tokens and tool decisions — per run.
A 5 minute experiment: wiring Alibaba's page-agent into my career site and pointing it at DeepSeek, so the whole UI takes orders in plain English. How it works under the hood, what its reasoning traces actually look like, and why I kept it strictly local.
Shipping an AI feature into my own product · Part 2
My site has an 'Ask Zakaria' AI box that answers untrusted recruiter input. So I spent an afternoon trying to break it — prompt leaks, tool-call injection, XSS, a cross-language jailbreak. Here's what held, and why the real defense isn't a clever prompt.
Kyutai's Pocket TTS is a 100M-param, CPU-only text-to-speech model that does zero-shot voice cloning. Getting it to clone my voice took one afternoon — two gotchas worth writing down (uvx isolation and the mp4 trap), plus a Claude Code skill so I can trigger it mid-session.
Shipping an AI feature into my own product · Part 1
Why my career site now answers questions out loud — the graceful-degradation bean, the SSE streaming, the atomic quota race, and the discoverability bug that had nothing to do with code.