# What is chain-of-thought prompting?

> Chain-of-thought prompting asks AI to reason step by step before answering. When it helps, and how to ask for a short reason you can check.

Source: https://learn.ynteractive.com/content/glossary/chain-of-thought-prompting · Updated 2026-10-01 · Free from Stepthrough (https://learn.ynteractive.com)

[Prompting](https://learn.ynteractive.com/content/glossary#topic-prompting) · [AI glossary](https://learn.ynteractive.com/content/glossary)

Updated October 1, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about)

Chain-of-thought prompting is asking an AI model to work through a problem in steps before giving its final answer, for example "think step by step" or "explain your reasoning first." Breaking the problem down can improve answers on tasks that need logic, math or several decisions in a row.

## Why it matters for a small business

For business tasks, the main value is often less about smarter answers and more about checkable ones. When a model has to state why it chose a category, a priority or a price range, you can spot a bad assumption in seconds instead of trusting a bare label.

It matters less than it used to for some tools. Many newer [reasoning models](https://learn.ynteractive.com/content/glossary/reasoning-model) work through problems internally before replying, so adding "think step by step" may change little. What still helps everywhere is asking for a short, visible reason next to each decision you need to review.

## In a real lesson: Build an AI Agent That Categorizes Business Expenses

Stepthrough doesn't have a lesson that uses the phrase "think step by step." The closest practical version is in [Build an AI Agent That Categorizes Business Expenses](https://learn.ynteractive.com/content/n8n-ai-agent-categorize-business-expenses-google-sheets), for Maple Street Bookkeeping, a made-up firm.

Its system prompt limits the agent to six categories (Office Supplies, Software & Subscriptions, Meals, Travel, Utilities, Needs Review) and asks for a **Note** on every expense: one sentence on what it was for and anything the bookkeeper should check, like a missing receipt. Then comes the key line: if an expense could fit more than one category, or the details are unclear, use Needs Review and say why.

That is a lightweight chain of thought aimed at the reviewer. When you send the three test expenses (printer paper and toner, monthly accounting software, a client lunch), each comes back with a category and a short note, and the Note column in the Expense Log sheet shows the reasoning a bookkeeper needs before posting anything.

[Try this lesson free](https://learn.ynteractive.com/modules/n8n-ai-agent-finance) or [read the step-by-step guide](https://learn.ynteractive.com/content/n8n-ai-agent-categorize-business-expenses-google-sheets).

## Common confusions

### Chain-of-thought vs prompt chaining

Chain-of-thought is reasoning inside one answer. [Prompt chaining](https://learn.ynteractive.com/content/glossary/prompt-chaining) is splitting work into separate prompts, where each step's output feeds the next (draft, then check, then fix).

### Is the shown reasoning what the model really did?

Not always. A written explanation can sound convincing and still be wrong, so treat it as something to check, not as proof. Compare the reason with the actual facts.

## Tips

- Ask for a one-sentence reason next to each decision rather than a long essay.
- Give the model a safe "unsure" option (like Needs Review) so it doesn't force a confident answer.
- For multi-step math, ask it to show the numbers it used so you can check them.

## Related terms

[Reasoning model](https://learn.ynteractive.com/content/glossary/reasoning-model) · [Prompt chaining](https://learn.ynteractive.com/content/glossary/prompt-chaining) · [Self-check prompt](https://learn.ynteractive.com/content/glossary/self-verification) · [Text classification](https://learn.ynteractive.com/content/glossary/text-classification) · [Expense categorization](https://learn.ynteractive.com/content/glossary/expense-categorization)

## Where you use it: free lessons

- [Build an AI Agent That Categorizes Business Expenses](https://learn.ynteractive.com/content/n8n-ai-agent-categorize-business-expenses-google-sheets) (n8n, 12 min)

## Frequently asked questions

**Should I add "think step by step" to every prompt?**

No. It helps on problems with several steps or calculations. For writing an email, it mostly adds length.

**Does chain-of-thought make the answer correct?**

It can make it more likely to be correct on some tasks, but it doesn't guarantee it. You still check the result.

[All AI glossary terms, A to Z](https://learn.ynteractive.com/content/glossary) · [Free prompt templates](https://learn.ynteractive.com/content/prompts)