Agentic Systems
Tool use, planning loops, LangGraph, AutoGen, MCP, memory and multi-agent orchestration — building autonomous AI systems that act.
16 articlesin Agentic Systems
Agent Skills: Knowledge That Loads on Demand
Stop growing your system prompt. How SKILL.md folders and progressive disclosure work, how to write a description that fires, and when a skill beats a tool or an MCP server.
Durable Agents and Sandboxing: Surviving the Crash
Checkpoints do not make a side effect safe. Idempotency keys, the interrupt replay trap, choosing a runtime, and the isolation and egress rules that contain generated code.
Harness Engineering: Everything Around the Model
Long-running agents fail in the code around the model. Clean sessions, progress on disk, a task list that starts failing, and checks the agent cannot talk its way past.
A2A: When Your Agent Needs Another Team’s Agent
Agent Cards, long-running tasks and artifacts, how A2A differs from MCP, and the honest test for when a plain function call is the better answer.
Building a Production Tool Registry
Design and maintain a central catalogue of agent tools — versioning, capability tagging, and dynamic discovery for scalable agent systems.
Managing Short-Term Memory in Agents
Manage the context window as working memory — what to include, summarise, or drop to keep agents coherent across long conversations.
Designing Reliable Planning Loops
Build reliable thought-action-observation cycles that let agents decompose complex goals into executable steps without going off-track.
Long-Term Memory for AI Agents
Persist agent knowledge beyond the context window — vector stores, key-value caches, and structured stores for cross-session recall.
LangGraph: Stateful Agentic Workflows
Model agent workflows as stateful graphs — nodes execute LLM calls or tools, edges control flow — for reliable, debuggable, and resumable agents.
Episodic Memory: Agents That Learn From Experience
Store and retrieve past agent episodes — full trajectories of thought, action, and outcome — so agents avoid repeating mistakes and replicate past successes.
AutoGen: Conversational Multi-Agent Systems
Microsoft's conversational multi-agent framework where agents exchange messages to collaborate, critique, and complete tasks — the v0.4 async rewrite, GroupChat patterns, and when to reach for it over LangGraph.
From Chatbot to Agent: Adding Tools, Memory, and Planning to a Simple Chat Interface
A practical walkthrough of evolving a basic LLM chatbot into a capable agent — adding tool calling, persistent memory, and multi-step planning.
AI-Powered Code Review: Building a Review Bot That Actually Helps
How to build an AI code review system that catches real issues — architecture, prompt design, GitHub integration, and practical lessons.
Multi-Agent Architecture Patterns in Production
Orchestrator, supervisor, and swarm patterns for multi-agent systems with real trade-offs and failure modes.
MCP Servers: Building Tool-Using AI Agents with the Model Context Protocol
How MCP works, how to build MCP servers that expose tools to AI agents, and practical patterns for connecting LLMs to your systems.
Testing Autonomous Coding Agents: GitHub Copilot, Cursor, and Windsurf in Real Projects
A hands-on experiment comparing autonomous coding agents on real engineering tasks — multi-file refactoring, bug fixing, and feature implementation.