RAG
RAG at Scale: What It Takes To Serve 10,000 Queries A Day
Most teams start with a simple RAG prototype. It feels elegant, almost magical. A vector database, a handful of chunks,
Welcome, AI Engineers!
šš½ I'm Anup. I'm an AI and Software Engineer who helps teams build production-grade agent systems that actually work at scale. I've designed AI systems across Salesforce, insurance tech, and AI startups. Now I focus on the hard parts: agent orchestration, MCP/A2A protocols, and building the Internet of Agents.
This site is where I share what I'm working on and learning. You'll find my projects, 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 and A2A, and agentic frameworks.
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.
Join engineers getting weekly insights on agents, RAG & production LLM systems
The AI Engineering Brief Newsletter
Agentic Architecture
Understanding Generative UI
A Layered Walkthrough of the Generative UI paper everyone is talking about
AI Agents
Senior Developers Are Better at Using AI Agents
Experience matters more than prompt engineering. Senior developers outperform juniors with AI agents because they have decades of pattern recognition. They know what good code looks like, what to ask for, and when the AI is wrong.
Agentic Architecture
Eliza Redux: A Real-Time Voice AI Crisis Support Agent
I built a crisis support voice AI Agent in roughly 90 minutes at a voice AI hackathon and won. Here&
AI Browser
Atlas Unshrugged
ChatGPT Atlas vs Perplexity Comet: Real-World AI Browser Showdown
When OpenAI announced Atlas, I was curious. I've used
AI Strategy
Stop Planning Your AI Strategy and Start Running Experiments
Earlier this year, I watched a Fortune 500 financial services company spend $4 million and eight months on their AI
Introducing AI Engineering Premium
When I started this newsletter, my goal was simple: to explore how AI systems are actually built. Over time, itā
Featured Projects
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 famousĀ Vision TransformerĀ 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
EfficientNetB2 Computer Vision Model
An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi. The model performs
Recommended Tools
Wispr Flow
Ever since I started using Wispr Flow, I get ideas out faster without breaking focus. Itās more accurate than Appleās 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 cardāsized, AIāpowered noteātaker that transcribes and summarises meetings with speaker labels, realātime highlights, multilingual transcription, and āAsk Plaudā querying. Itās like having a smart, handsāfree 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.
Recommended Podcasts
AI for Humans
Educational, light-hearted discussions breaking down AI concepts
Google DeepMind: The Podcast
Research-focused, neuroscience-inspired models, safe and ethical AI
Latent Space
Technical updates, real-world engineering, foundational models
NVIDIA AI Podcast
In-depth interviews on AI transforming industries