https://niranta.blog/ A personal blog by Nitin. Writing about AI, quotes, experiments, and life. Analytical and personal, somewhere between Stratechery and Marcus Aurelius. en-us Wed, 03 Jun 2026 15:49:59 +0000 https://niranta.blog/logo.png https://niranta.blog/ https://niranta.blog/ai/ai-changing-design-jobs-forever/ https://niranta.blog/ai/ai-changing-design-jobs-forever/ Wed, 03 Jun 2026 00:00:00 +0000 AI AI is already rewriting design work inside enterprise teams. The execution-heavy version of the job is shrinking. The strategic, empathetic, end-to-end version is the only one that survives. https://niranta.blog/ai/headless-ai-is-here/ https://niranta.blog/ai/headless-ai-is-here/ Wed, 27 May 2026 00:00:00 +0000 AI We all love chatting with AI in chat windows. The real revolution is happening behind the scenes. Salesforce just made it impossible to ignore. A reflection on headless LLM interactions and where this goes next. https://niranta.blog/ai/finding-the-right-place-for-mcp/ https://niranta.blog/ai/finding-the-right-place-for-mcp/ Sat, 23 May 2026 00:00:00 +0000 AI I used to think every API needed an MCP server. JIRA taught me otherwise. A reflection on when MCP earns its keep, when direct tool calling wins, and how the multi-user auth story is finally maturing in 2026. https://niranta.blog/experiments/kritique-multi-persona-council/ https://niranta.blog/experiments/kritique-multi-persona-council/ Tue, 19 May 2026 00:00:00 +0000 Experiments Most AI writing tools optimize for fluency. The harder problem is judgment. Kritique is a tool I built for myself that replaces single-model rewriting with a structured council, multiple personas critiquing an artifact from distinct lenses until the loop hits threshold convergence, with the dissent preserved. https://niranta.blog/personal/contagious-aging/ https://niranta.blog/personal/contagious-aging/ Mon, 18 May 2026 00:00:00 +0000 Personal A 2025 study from Korea University found that a single protein, ReHMGB1, can carry the signal of cellular aging through the bloodstream. Notes from a paper that is worth sitting with. https://niranta.blog/quotes/someone-has-to-sell/ https://niranta.blog/quotes/someone-has-to-sell/ Sun, 17 May 2026 00:00:00 +0000 Quotes A short line from a video my friend Steve sent. "If you are all going to eat, someone has to sell." A reflection on why sales is the oxygen of every business, and why I plan to make it a hiring requirement at my next venture. https://niranta.blog/ai/limits-of-the-personal-engineering-org/ https://niranta.blog/ai/limits-of-the-personal-engineering-org/ Sat, 16 May 2026 00:00:00 +0000 AI The three-layer engineering stack works in most situations. The harder skill is knowing the situations where it does not. Six concrete failure modes where the right move is to switch the stack off and reach for something smaller. https://niranta.blog/ai/impeccable-design-skill-claude-code/ https://niranta.blog/ai/impeccable-design-skill-claude-code/ Thu, 14 May 2026 00:00:00 +0000 AI Impeccable, by Paul Bakaus, is a Claude Code skill that gives the model the actual vocabulary designers use, then enforces it across 23 commands. After running it on dashboards, marketing sites, internal tools, and client work, it has become a permanent fixture in my stack. https://niranta.blog/personal/world-before-and-after-chatgpt/ https://niranta.blog/personal/world-before-and-after-chatgpt/ Tue, 12 May 2026 00:00:00 +0000 Personal Writing has become easy. Reading has become hard. A reflection on verbosity overload after ChatGPT, the tells of AI-generated text, and why putting your own voice first still matters. https://niranta.blog/ai/the-personal-engineering-org/ https://niranta.blog/ai/the-personal-engineering-org/ Sun, 10 May 2026 00:00:00 +0000 AI Three open-source tools, gstack, Superpowers, and Visual-Explainer, turn a single Claude Code terminal into a coordinated engineering team that thinks strategically, enforces process, and communicates visually. https://niranta.blog/experiments/peptides-101-athlete-sons/ https://niranta.blog/experiments/peptides-101-athlete-sons/ Sat, 09 May 2026 00:00:00 +0000 Experiments A personal deep dive into peptides, what they are, why athletes use them, common types like BPC-157 and TB-500, side effects, and my own experience trying them. https://niranta.blog/ai/claude-code-lessons/ https://niranta.blog/ai/claude-code-lessons/ Thu, 07 May 2026 00:00:00 +0000 AI After months of building production-grade systems with Claude Code, here are the hard-won practices that have cut token consumption by 60-80% while improving output quality and reliability. https://niranta.blog/curiosities/from-black-holes-to-quantum-computers/ https://niranta.blog/curiosities/from-black-holes-to-quantum-computers/ Wed, 06 May 2026 00:00:00 +0000 Curiosities For months I've been falling asleep to Brian Cox, Michio Kaku, Susskind, and the YouTube physics crowd. Black holes, Hawking radiation, the LHC, Planck time. Then a friend's startup pulled me into quantum computing, and the late-night curiosity became real homework. https://niranta.blog/experiments/why-19pine-ai-changed-how-i-handle-drudgery/ https://niranta.blog/experiments/why-19pine-ai-changed-how-i-handle-drudgery/ Tue, 05 May 2026 00:00:00 +0000 Experiments I test most new AI tools. Most disappoint. 19pine.ai was different, it's the first one that genuinely shifted how I spend my days, starting with a two-hour Comcast negotiation I never had to sit through. https://niranta.blog/ai/my-personal-ai-evaluation-framework/ https://niranta.blog/ai/my-personal-ai-evaluation-framework/ Sun, 03 May 2026 00:00:00 +0000 AI I've tested more AI products than I care to admit. Most disappoint. Here is the brutally practical eight-dimension framework I use to decide whether any tool is actually worth my time and money. https://niranta.blog/personal/why-some-friendships-leave-me-tired/ https://niranta.blog/personal/why-some-friendships-leave-me-tired/ Sat, 02 May 2026 00:00:00 +0000 Personal A personal reflection on energy-draining friendships, the imbalance that defines them, why I keep showing up anyway, and the small ways I've started to protect my energy without losing the kindness that gets me into the trouble in the first place. https://niranta.blog/ai/the-5-gate-rule/ https://niranta.blog/ai/the-5-gate-rule/ Fri, 01 May 2026 00:00:00 +0000 AI AI coding assistants are fast. That's the problem. Speed without verification is how you ship shell injection, database corruption, and backwards alerts, all in the same session. https://niranta.blog/ai/improving-existing-apps-with-claude-code-gstack-superpowers/ https://niranta.blog/ai/improving-existing-apps-with-claude-code-gstack-superpowers/ Thu, 30 Apr 2026 00:00:00 +0000 AI Most AI coding workflows assume you're starting from scratch. Here is the exact flow I use with gstack and Superpowers to safely improve production code I already have. https://niranta.blog/experiments/splitting-ai-models-by-architectural-layer/ https://niranta.blog/experiments/splitting-ai-models-by-architectural-layer/ Wed, 29 Apr 2026 00:00:00 +0000 Experiments Most teams pick one model and hardcode it everywhere. We did too, until we didn't. Here is how splitting by architectural layer changed our cost profile, latency, and reasoning quality. https://niranta.blog/ai/token-anxiety/ https://niranta.blog/ai/token-anxiety/ Sun, 26 Apr 2026 00:00:00 +0000 AI My entire day-to-day existence is now tethered to tokens. When they run out, I don't just lose productivity. I lose my damn mind.