AI Agents
LangGraph, CrewAI, AutoGen and agentic design patterns that survive production.
7 long reads · 113 minutes in total
Evaluating AI Agents: Offline Evals, Trajectory Checks, and Regression Suites
A practical design for testing agent outcomes and tool-use trajectories offline, then turning the results into trustworthy release gates.
21 Nov 202614 min
AI Agents Interview Questions: Durable Execution, Checkpoints, and Replay
Twelve interview questions on making long-running AI agents recoverable, resumable, and observable without confusing saved conversation history with durable execution.
10 Nov 202614 min
Multi-Agent Research Assistant with LangGraph: Planner, Workers, and Critic
A production-minded AWS blueprint for a LangGraph research assistant that delegates bounded research, checks evidence, and returns traceable answers.
9 Nov 202619 min
MVP Architecture: Agentic RAG System
2 Nov 202626 min
AI Agents Interview Questions: Tool Safety and Side-Effect Control
Twelve interview questions explore how to authorize, execute, and observe AI-agent tool calls without trusting the model to make security decisions.
1 Nov 202613 min
A Single-Agent Support Assistant: Tools, SQL Knowledge, and a Small-Team Blueprint
A production-minded AWS blueprint for a single-agent customer support assistant that searches a PostgreSQL knowledge base through constrained tools.
1 Nov 202619 min
AI agent architecture for large enterprise environment for building LLM-driven systems, agent orchestration, RAG pipelines, autonomous workflows, and live production AI agents.
This design assumes you want reliability, observability, security, compliance, scalability, and future flexibility. 1. Executive Architecture Summary A production AI-agent platform should not be just: User → LLM → Respon...
18 May 20268 min
Newsletter
Get new AI Agents reads on Saturday.
The week’s new long reads on architecture, cloud and AI — with the diagrams left in. Delivered Saturday morning, no noise in between.