Welcome, AI Engineers!

👋🏽 I'm Anup. I'm an AI and Software Engineer building production Agentic AI and Generative AI systems. I work on RAG pipelines, multi-agent architectures, and multi-cloud deployments.

My newsletter, The AI Engineering Brief, covers practical AI engineering for people shipping real systems. X/Twitter/Bluesky: @anup.

GPUs

How fast does it serve? Throughput, latency, and picking the right GPU

Part 2 of 2 on inference engineering for AI engineers.

07 May

LLM Scaling

Fitting LLMs on Self-Hosted GPUs

How much VRAM does your LLM need, and which GPU should you actually rent? A free calculator covering DeepSeek, Llama, Mixtral on H100, B200, A100.

04 May

Claude Code

The Harness Is the Product

Where does product quality live in an LLM-based system? A leaked source and a detailed postmortem, both from Anthropic in the last four weeks, make the answer unusually concrete.

24 Apr

Agentic Architecture

Harness Engineering: The Outer System That Makes Agents Reliable

Building a good harness is what separates a good agentic implementation from a great one.

02 Apr

Claude Code

Write Skills Like Workstations, Not Prompts

Claude Code skills work best when you treat them as workstations, not prompts: folders with scripts, gotchas, templates, and progressive disclosure that manage the agent's attention budget at runtime.

18 Mar

eval driven development

Ship Prompts Like Software: Regression Testing for LLMs

Because "it seemed fine when I tested it" is not a deployment strategy. Part 4 of 4: Evaluation-Driven Development for LLM Systems

26 Feb

evals

Four Ways to Grade an LLM (Without Going Broke)

Your evaluation technique should match the question you're asking, not your ambition.

25 Feb

LLM VRAM Calculator

A free VRAM calculator for self-hosted LLMs that picks the smallest fitting GPU instance ( H100, B200, A100 ) across FP16, FP8,

Eliza Redux: A Voice AI crisis support Agent

Voice AI crisis support chatbot that responds in under a second. Built and deployed in 90 minutes for a hackathon

Vision Transformer (ViT) Paper PyTorch Implementation

Replicated the famous Vision Transformer paper using PyTorch to improve my understanding of Transformer architecture applied to vision problem(s)

Matrix-themed Chat Interface

Matrix-themed Chat Interface Built an immersive Matrix-themed chatbot interface leveraging Heroku's AI inference and agent APIs. The project

Wispr Flow

Ever since I started using Wispr Flow, I get ideas out faster without breaking focus. It’s more accurate than Apple’s native transcription, adapts to my style, and saves me loads of time by turning speech into clean, structured text instantly.

Workflowy

Workflowy is a minimalist, endlessly nested outliner that helps you organise thoughts, tasks, and notes without distractions. It lets you zoom into bullets, structure ideas hierarchically, and switch views. It's simple but incredibly powerful.

Plaud AI

Plaud AI is a card‑sized, AI‑powered note‑taker that transcribes and summarises meetings with speaker labels, real‑time highlights, multilingual transcription, and ‘Ask Plaud’ querying. It’s like having a smart, hands‑free assistant for meeting notes.

Comet

Comet by Perplexity is now my default browser. I use it for search, shopping, email, and calendar. With Shortcuts, I can trigger workflows on websites that draft outreach or gather research. It feels like browsing with superpowers.