# Tool-Augmented Self-Correction

> After drafting, the model uses external tools (search, code execution, calculator) to verify its own claims — grounded self-correction, not more confident hallucination.

- **Category**: Agentic AI
- **Subcategory**: Verification & Reflection
- **Canonical URL**: https://designpattern.fyi/patterns/critic/

---

## Description
**Intent**: Ground the self-correction loop in external reality, not just the model's own beliefs.

**Context**: Your agent generates drafts with factual claims (verifiable by search), code (runnable), or arithmetic (calculable). After drafting, the model self-critiques — but the critique is just another model call with no external grounding. It reinforces the same errors it made the first time.

**Solution**: After draft generation, the model emits a critique that names suspected errors and issues tool calls to verify them. Tool results inform the revised output. Iterate until tools find no more issues or the budget exhausts.


## Use Cases
- The model has external tools (search, code, calculator) that can provide grounded ground-truth signals.
- Ungrounded self-critique recycles the model's blind spots and fails to catch real errors.
- Iteration to convergence (or a budget cap) is acceptable in the latency model.





## Trade-offs


### Advantages

- Grounded self-correction beats ungrounded reflection — tools provide external reality checks.

- Tool invocations during critique are auditable and replayable.




### Considerations & Drawbacks

- Latency and cost per turn — tool calls add up.

- Tool selection during critique is itself a reasoning problem the model can get wrong.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/tool-augmented-self-correction/)