AI Wisdom
Learning Track

Agentic Systems

Tool use, planning loops, LangGraph, AutoGen, MCP, memory and multi-agent orchestration — building autonomous AI systems that act.

16+
Topics
9
Published
100%
Free
Browse articles ↓

16 articlesin Agentic Systems

Agentic Systems
EngineerAgentSystem promptModelSKILL.mdScriptReview and pin

Agent Skills: Knowledge That Loads on Demand

Intermediate

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.

Updated 6 min
Read →
Agentic Systems
CustomerRefund agentPayment APICheckpointsManagerSandbox

Durable Agents and Sandboxing: Surviving the Crash

Advanced

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.

Updated 5 min
Read →
Agentic Systems
YouHarnessAgent sessionCode and gitProgress fileChecks

Harness Engineering: Everything Around the Model

Advanced

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.

Updated 6 min
Read →
Agentic Systems
BuyerProcurement agentAgent CardCompliance agentTheir policy dataVerify

A2A: When Your Agent Needs Another Team’s Agent

Advanced

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.

Updated 5 min
Read →
Agentic Systems
EmployeeAssistantModelTool registryOrder lookupHR and IT toolsRefund toolConfirm

Building a Production Tool Registry

AdvancedPRO

Design and maintain a central catalogue of agent tools — versioning, capability tagging, and dynamic discovery for scalable agent systems.

Updated 11 min
Read →
Agentic Systems
UserAgentPromptModelToolsPinned factsRolling summary

Managing Short-Term Memory in Agents

Intermediate

Manage the context window as working memory — what to include, summarise, or drop to keep agents coherent across long conversations.

Updated 14 min
Read →
Agentic Systems
OperatorAgentToolsBoth regionsPlanPlan checkVerifier

Designing Reliable Planning Loops

AdvancedPRO

Build reliable thought-action-observation cycles that let agents decompose complex goals into executable steps without going off-track.

Updated 12 min
Read →
Agentic Systems
CustomerAssistantModelProfile factsWrite check

Long-Term Memory for AI Agents

AdvancedPRO

Persist agent knowledge beyond the context window — vector stores, key-value caches, and structured stores for cross-session recall.

Updated 12 min
Read →
Agentic Systems
CustomerGather detailsApply policyIssue refundCheckpointsSupervisor

LangGraph: Stateful Agentic Workflows

AdvancedPRO

Model agent workflows as stateful graphs — nodes execute LLM calls or tools, edges control flow — for reliable, debuggable, and resumable agents.

Updated 12 min
Read →
Agentic Systems
EmployeeHelpdesk agentModelEpisodesWorth keeping?

Episodic Memory: Agents That Learn From Experience

AdvancedPRO

Store and retrieve past agent episodes — full trajectories of thought, action, and outcome — so agents avoid repeating mistakes and replicate past successes.

Updated 13 min
Read →
Agentic Systems
DeveloperCoderReviewerStop ruleSandboxed tests

AutoGen: Conversational Multi-Agent Systems

AdvancedPRO

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.

Updated 12 min
Read →
Agentic Systems
IT adminAgent loopModelToolsCompany systemsTask stateManagerStep record

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.

Updated 13 min
Read →
Agentic Systems
A pull request diff plus repository context goes to a review agent that checks against team standards, filters low-confidence findings, and posts inline comments on 30 to 40 percent of pull requests.A pull request diff plus repository context goes to a review agent that checks against team standards, filters low-confidence findings, and posts inline comments on 30 to 40 percent of pull requests.

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.

Updated 10 min
Read →
Agentic Systems
Product teamSupervisorResearch workersCRM workerWriterJob storeDeadline, budgetOne trace

Multi-Agent Architecture Patterns in Production

AdvancedPRO

Orchestrator, supervisor, and swarm patterns for multi-agent systems with real trade-offs and failure modes.

Updated 14 min
Read →
Agentic Systems
EngineerAssistantModelAllowlist and filterCode hostTicketsDeploy status

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.

Updated 12 min
Read →
Agentic Systems
Five real tasks on a 50,000-line .NET 9 application were given to Copilot, Cursor and Windsurf, and each result was checked by build, tests and human review.Five real tasks on a 50,000-line .NET 9 application were given to Copilot, Cursor and Windsurf, and each result was checked by build, tests and human review.

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.

Updated 14 min
Read →