Welcome, AI Engineers!

Edit

👋🏽 I’m Anup. I’m an AI and Software Engineer with over two decades of technology leadership experience. I focus on designing and deploying production-grade Generative AI and Agentic AI systems that solve real business problems at scale. I combine deep technical expertise with architectural thinking to build systems that are reliable, interpretable and aligned with human values.

This site is where I share what I’m working on and learning. You’ll find my projects, a list of tools and podcasts I like, and a growing collection of “Today I Learned” notes at anup.io/til. My newsletter (anup.io/blog), The AI Engineering Brief, explores the evolving landscape of AI engineering with practical architectures, deep dives into protocols like MCP, A2A and agentic frameworks, and applied insights that connect research with real-world deployments.

Whether you’re building RAG pipelines, experimenting with multi-agent systems or thinking about how AI will reshape software, you’ll find frameworks, essays and reflections here to help you stay ahead of the curve. Subscribe to get new content delivered to your inbox.

Data in CSV Format Isn’t Always the Best for LLMs

When you feed a large table into an LLM, the way you format the input can change the model’s

07 Oct

Prompt Engineering vs Context Engineering

From Anthropic: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents Prompt Engineering: Prompt engineering refers to methods for writing and organizing LLM

06 Oct

Why LLMs Confidently Hallucinate a Seahorse Emoji That Never Existed

Ask any major AI if there's a seahorse emoji and they'll say yes with 100% confidence.

06 Oct

Goodbye Manual Prompts, Hello DSPy

Today I learned about a smarter way to deal with the headache of prompts in production. Drew Brunig’s talk

05 Oct

Nemawashi (根回し)

There’s a Japanese concept called nemawashi (literally “root-walking”) that offers a way around the dreaded “big reveal” in engineering

05 Oct

AI agents are starting to do real work

Ethan Mollick argues that AIs have quietly crossed a line. OpenAI recently tested models on complex, expert-designed tasks that usually

04 Oct

Vibe Coding

Cargo Cult Vibe Coding

In the age of AI code generation, we risk trading craftsmanship for ritual It's the 1940s in the

04 Oct

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)

Edit

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

Edit

EfficientNetB2 Computer Vision Model

An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi. The model performs

Edit

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.

Edit

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.

Edit

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.

Edit

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.

Edit