An LLM Is Not an Agent: The 10 Building Blocks That Make AI Agentic
goyalshaliniuk · x · 2026-10-06
The author argues an LLM alone is not an agent — it becomes agentic only when the surrounding system can understand goals, plan work, use tools, retain context, act, and recover from failure.
The 10 building blocks listed: Foundation Model (reasoning, generation, tool calling), Agent Orchestration (routing, workflow, retries), Context and Instructions, Memory and State, Knowledge and RAG, Tools and Actions (APIs, databases, code execution), Planning and Workflow, Multi-Agent Collaboration, and more.
More from coding & agent
- Claude Opus rebuilt Terraria in 3D: 346K lines of C# in 8 days, zero hand-written code — Promptmethus · 2026-10-07
- Dev puts the entire game of Minecraft inside Twitter with working multiplayer — jaivinwylde · 2026-10-07
- Scikit-learn Team Launches Skore, an Enterprise Platform for Tabular AI Built With AI Agents — GaelVaroquaux · 2026-10-07
- Amateur Team Discloses Identity-Constitutive Memory Protocol for AI Agents, Keeps Core Docs Secret — AdeptBathroom3318 · 2026-10-07
- Prompting agents to mimic Modal's GPU glossary styling yields polished HTML artifacts — sumitdotml · 2026-10-07
- Jordan and coauthors tackle when to stop generator-verifier loops while controlling false discovery — _onionesque · 2026-10-07