Blogs

How does one request keep its identity across a dozen services? I animated the W3C Trace Context spec so you can scrub, poke and break each header yourself.

How do you deal with AI cheating in technical interviews? Eye contact, pauses and pasted code are weak signals. Here is how to collect better evidence of real skill, without confusing ordinary AI use with identity fraud.

How do you add observability to Hermes Agent with self-hosted Langfuse? A walkthrough of enabling the bundled plugin, the SDK gotcha that silently kills tracing, per-model cost tracking on Coolify, and what the traces actually look like.

What’s the difference between prompt engineering, context engineering, harness engineering, loop engineering, and evaluation engineering? A side-by-side comparison with diagrams for AI engineers building production systems.

On rivers, cells, chemistry teachers, and the illusion of a permanent self: a non-technical exploration of identity, impermanence, and the observer within.

How do you know if an AI agent is telling the truth? When my research agents fabricated 11 model names and 4 fake paper titles, I learned the hard way that autonomous AI research requires independent verification.

After years away from the Python India community, I walked into PyConf Hyderabad 2026 as a speaker. I walked out with a reminder of why I started.

I went on a weekend trip. I came back to a new Claude, a new GPT and an existential crisis. The pace of AI is no longer monthly. It’s weekly.

I went down the rabbit hole of AI in the adult industry. I expected simple chatbots; I found a sophisticated engineering stack pushing the boundaries of edge computing, privacy and opensource AI.

I forked CoverView and added pattern backgrounds, color palettes, platform presets and fixed Unsplash bugs. Here’s my journey of improving an abandoned opensource tool.

I built an RSVP-based speed reader app in a few hours using AI tools. Here’s why I stopped using it after a day and what I learned about building vs. solving problems.

How I used tprof and Python 3.12 sys.monitoring for targeted profiling to benchmark orjson against the standard json library and measure serialization speed.

How I passed the OpenTelemetry Certified Associate exam on my second try: my prep plan, the strict proctoring, failing by 2% and what finally got me through.

My 2025 in review: a memorable meeting at work, judging a hackathon, learning to drive, self-hosting, making AI reels, giving talks and lessons I learned.

Explore my self-hosting journey from Heroku to Cloudflare Pages, PikaPods to Hetzner VPS. Learn how I host Listmonk, Uptime Kuma, Jellyfin, and more using Coolify and Proxmox for cost-effective home server management.

Learn about the three types of workplace power; role power, relational power, and expertise power; and how to leverage them for career growth and influence in any organization.

A practical, case‑driven guide for CXOs and engineering leaders to build trustworthy, compliant and revenue‑generating AI systems.

How each generation of interface rewires our brains, and why every “essential” skill eventually becomes obsolete.

How do you monitor AI systems in production? Practical strategies for instrumenting LLM applications with OpenTelemetry, tracking token costs, latency and quality metrics.

What are the hidden costs of using LLM-as-a-Judge? Learn about common biases, failure patterns and smarter evaluation strategies for LLM applications.

Discover the RSS feeds that keep me updated and informed in the digital world.

What is RAG and how has it evolved? From Naive RAG to Advanced RAG to GraphRAG and LightRAG: understand the evolution of Retrieval-Augmented Generation systems.

My experience judging a GenAI hackathon in Hyderabad: how I was invited, the evaluation criteria, the scoring spreadsheet I built and how we picked winners.

How do you create Python packages using Rust? A step-by-step guide using PyO3 and maturin, with examples from Ruff, uv and Polars.