Author
Software Engineer · AI Builder · Writer · Expedia Group
Software engineer writing about AI, Claude Code, LLMs, OpenAI, Anthropic, and developer tooling. 172 articles on AI engineering, production systems, and the tools shaping modern development. 5+ years at Expedia Group, Tekion, and BYJU'S.
Google Search · Preferred sources
If you already read this writing, add umesh-malik.com as a Preferred Source. Google can then highlight it with a preferred badge in Top Stories, AI Overviews, and AI Mode — for you, not as a site-wide ranking boost.
Check your LLM server for a KV cache leak: compare pool size to context length and send a canary prompt. Cloudflare's GLM-5.3 bug exposed 155 responses.
Set up Cloudflare Origin Range Requests with one Cache Rule. Why a 4 MiB seek cost 68 MiB of origin traffic on a 64 MiB range size, and a script to verify 206s.
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.
How to check if you installed compromised LiteLLM 1.107.0 from PyPI or Docker: a 60-second detection script, the cook.pth startup trick, and what to rotate.
How to review AI-written code you don't fully understand: sort changes into 3 risk tiers by path. In my repo 54% needed no human read. Here is the routing.
Is document.currentScript inline rendering safe for SEO? I measured what rendered, raw-HTML and Markdown readers see, plus CLS and the cost of 1,000 scripts.