Fragmented - AI Developer Podcast 305 - Subagents explained - What they are, when (not) to spawn them
20 snips
Feb 17, 2026 Clear definitions of what an AI agent is and how its reactive loop works. A deep dive into modes versus subagents and how mode switching alters system behavior. An RTS-style scout analogy shows how parallel subagents gather intel without polluting context. Practical guidance on when to spawn isolated, scoped workers and when to avoid them.
AI Snips
Chapters
Transcript
Episode notes
Agent As A Reactive Loop
- An agent runs a reactive loop: reason, act, verify, and repeat until a task is done.
- This framing distinguishes agents from mere prompt files or SDKs and clarifies their purpose.
Agents.md vs Agent SDKs
- 'Agents.md' is just a system instructions file, not an agent process.
- Agent SDKs (LangChain, OpenAI Agent SDK, etc.) are tools to build reactive-loop agents programmatically.
Modes Swap System Instructions
- Modes (plan/build) swap system instructions and change agent behavior and permissions.
- Mode switching is deeper than UI; it alters the system prompt the model receives.