5 Agentic Design Patterns: ReAct, Planning, Reflection, Routing, Multi-Agent
Bashiri Smith · Facebook reel · 2026-08-21 · 0:11 · 162,336 views · Open on Facebook
Topics: AI Agents, Tool Use & MCP, AI System Design & Architecture · Level: intermediate
Summary
A production AI agent needs more than an LLM plus a prompt. It needs a clear pattern for reasoning, making decisions, using tools and finishing work. The post covers five core agentic design patterns: Tool Use/ReAct, Planning, Reflection/Critic, Routing and Multi-Agent. It advises picking the simplest pattern that can reliably complete the task.
Key points
- Tool Use / ReAct: the agent reasons, chooses a tool, observes the result, then decides the next step (a loop).
- Planning: the agent breaks a large goal into smaller, executable steps before doing the task.
- Reflection / Critic: the agent generates an output, evaluates it, finds weaknesses and improves it.
- Routing: the system classifies the request and sends it to the right model, tool, workflow or specialist agent.
- Multi-Agent: specialized agents split the work, collaborate, review each other's outputs and combine the results.
- You don't need five agents for every problem. Choose the simplest pattern that reliably completes the task.
- A production agent is more than an LLM connected to a prompt.
Resources mentioned
- BASWE: Agent Cheatsheet for AI Engineers · pdf · drive.google.com · free
The creator's free cheat sheet (a Google Drive folder) summarizing agent design patterns. - BASWE.Ai Engineer (Skool community) · community · skool.com · paid
The creator's paid community and program, with an AI learning roadmap (including the full ops and evaluation track), daily calls with engineers and recruiters, resume and portfolio help, and a job-search pipeline.
Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Pointer to Bashiri Smith's Complete AI Engineer Roadmap for 2026 (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), How to Evaluate a RAG Pipeline: Retrieval vs. Generation (Interview Answer) (Bashiri Smith on Facebook · notes) and 76 more
Try this
- Learn the five agentic design patterns: ReAct, Planning, Reflection, Routing and Multi-Agent.
- Download the free Agent Design Patterns Cheat Sheet.
- For each problem, choose the simplest agent pattern that can reliably complete the task.
More in AI Agents, Tool Use & MCP
- An X research bot built with Hermes
- Agent Harness Efficiency: Scaffolding Beats MCP vs. CLI
- Run Your Hermes Agent on Free LFM2.5-2.6B via OpenRouter
- Running a Local Ornith Model as the Backend for a Hermes Agent
- Mixture-of-Agents Setting Was Quietly Using Up Codex/ChatGPT Quota
- Mind Viruses: How Bad Ideas Spread Through Multi-Agent LLM Systems