# Extended Thinking

> Give the model a private scratchpad to reason deeply before it responds.

- **Category**: Agentic AI
- **Subcategory**: Reasoning
- **Canonical URL**: https://designpattern.fyi/patterns/extended_thinking/

---

## Description
**Intent**: Unlock deeper, multi-step reasoning by giving the model a first-class internal monologue that doesn't pollute the final output.

**Context**: Standard CoT mixes reasoning and response in the same token stream, which creates pressure to produce clean, confident-looking output even mid-reasoning. Native thinking blocks remove that pressure — the model can be uncertain, wrong, and self-correcting in the scratchpad.

**Solution**: Use models with native extended thinking support (Claude extended thinking, o1/o3 reasoning traces). Set a `thinking_budget` (token cap) appropriate to task complexity. The thinking block is returned separately or stripped from the user response depending on your UX needs. Pair with adaptive-compute-allocation to avoid paying for extended thinking on simple tasks. See also: chain-of-thought, scratchpad, large-reasoning-model-paradigm.



## Use Cases
- Hard reasoning tasks: multi-step math, complex code generation, strategic planning.
- Cases where you want the reasoning visible for audit but not shown to end users.
- Tasks where the model needs to explore multiple approaches before committing.






## Trade-offs


### Advantages

- Significantly improves accuracy on hard benchmarks vs. standard CoT.

- Thinking is isolated — model can be uncertain without undermining response confidence.

- Thinking budget is tunable — balance cost vs. reasoning depth per task.




### Considerations & Drawbacks

- Expensive — thinking tokens count against your bill.

- Not all models support it natively; prompting workarounds are imperfect substitutes.

- Thinking content can be verbose and hard to parse for downstream use.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/extended-thinking/)