AI Agents & Orchestration

Workflows vs agents, design patterns, agent loops, multi-agent systems, MCP, and durable execution.

7 articles · about 130 minutes of reading

1. 1Workflows vs Agents: When an LLM App Needs AutonomyLearn the difference between LLM workflows and agents, when each is the right choice, and how to build the same feature both ways in TypeScript to compare them.Difficulty: Intermediate14 min read
2. 2Agent Design Patterns in TypeScript: Chaining to Evaluator-OptimizerSix proven patterns for LLM systems, with TypeScript code: prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and autonomous agents.Difficulty: Intermediate20 min read
3. 3Build an AI Agent Loop from Scratch in TypeScriptWrite a production-ready agent loop in TypeScript: Zod-typed tools, turn, token, and time limits, parallel tool calls, error handling, events for your UI, and unit tests.Difficulty: Advanced22 min read
4. 4Multi-Agent Systems: Orchestrators, Subagents, and When to Use ThemBuild an orchestrator that delegates to parallel subagents in TypeScript, write good briefs, control token costs, and learn when multiple agents beat a single one.Difficulty: Advanced18 min read
5. 5Model Context Protocol (MCP): Build and Use MCP Servers in TypeScriptUnderstand MCP hosts, clients, servers, and transports, build a TypeScript MCP server with tools, resources, and prompts, and use it from Claude Code and your agents.Difficulty: Intermediate19 min read
6. 6Agent Memory, State, and Durable Execution with PostgresGive agents memory that lasts and runs that survive crashes: memory tiers, checkpointed steps in Postgres, leases, and idempotent side effects.Difficulty: Advanced20 min read
7. 7Human-in-the-Loop Agents: Approvals, Pauses, and Resumable RunsPause an agent before risky actions, persist the run, ask a person to approve, edit, or reject, and resume with the right tool results, in TypeScript and Next.js.Difficulty: Advanced17 min read