The Compute Blog
Writing
I write about how modern AI systems actually work: the tools they use, the knowledge they retrieve, and the engineering that makes them reliable. Start with the reading path below, or catch up on recent posts.
Full articles live on The Compute Blog. This page is a guide to where to begin.
A curated learning path
Start here
Read in order: connect an agent to tools, give it useful context, evaluate its behavior, then decide when to bring in more agents.
Fundamentals · Basics
What are AI agents?
What really makes an AI agent?
Tooling · Model Context Protocol
What is MCP
Start with how agents connect to tools and data: MCP hosts, clients, servers, and the capabilities they exchange.
Retrieval · RAG architecture
Retrieval Augment Generation
What is a RAG system and how does it work?
Retrieval · RAG architecture
RAG Architect’s Handbook
Move beyond a basic retrieval pipeline with query transformation, reranking, GraphRAG, and adaptive patterns—and the trade-offs behind them.
Evaluation · Agent reliability
Evaluating Agentic Systems
Check whether an agent actually works by evaluating its tool calls and final answers, using golden datasets and a practical DeepEval example.
Orchestration · Multi-agent systems
Multi-Agent Systems
Decide when multiple agents are worth the coordination cost, then explore orchestration patterns with Microsoft Agent Framework and Google ADK.
From the feed
Recent posts
Up to 20 recent entries from the blog’s RSS feed, refreshed when this site is built. For older posts and anything published since, visit the full blog.
- Multi-Agent SystemsWhen to Let Your Agents Work as a Team
- Evaluating Agentic SystemsHow Do You Know Your Agent Actually Works?
- Gemini: Managed Agents & Interactions APIGoogle's newest solution to abstracting away the complexity of building agents
- Microsoft Agent FrameworkBuilding Production-Ready AI Agents in Python
- RAG Architect’s HandbookA Deep Dive into Next-Gen RAG Patterns
- Google Agent Development KitYour guide to building agents with Google Agent Development Kit (ADK)
- Agent to Agent ProtocolWhen AI Agents Finally Start Talking to Each Other
- OpenAI Agent BuilderMy experience developing Agentic workflows with the latest low/no code Agentic tool from OpenAI
- AI Agent toolsThe tools that you should know about, while developing AI agents
- What is MCPI promise it's not as complicated as you might think
- Retrieval Augmented GenerationOne of the most cost-effective, easy to implement, and lowest-risk path to higher performance for GenAI applications
- LangflowMake your AI agent using a no/low code approach & easily build powerful AI agents
- What are AI agents really?Let's do a deep dive into what AI agents are, and their building blocks
- FastAPI in pythonExplore FastAPI’s powerful features, including async support, automatic validation, and built-in documentation, making it the go-to framework for modern Python APIs.
- Containers in software engineeringLearn the basics of docker & kubernetes in under 10 minutes
- Github Actions - a great introduction into CI/CDLearn about one of the most important parts of DevOps in under 10 minutes
- Hasura - Effortless unified API on all your dataHow to ship a rock-solid API on your data – in minutes
- What are orchestrators in data systems?Everything you need to know about modern data pipeline orchestration
- 5 things that make you a great software engineerThat they don't tell you about
- Boost Your Productivity with the Best VS Code ExtensionsHow to save time and become more efficient at software engineering using VS Code extensions