# Build a usable agent from scratch

From connecting data to handing it to your team, build an agent that answers accurately.

使用指南 · 模块: getting-started · 使用者 / 管理人员 · 部署形态：资料未说明 · 已确认产品版本：资料未说明 · 来源：编辑整理 · 按产品 4.2.76-1110（CLI 0.0.18）核对；私有部署的旧版本可能不包含近期变化。

This tutorial starts with connecting data, builds an agent your team can rely on, and verifies it with real questions. It uses store sales analysis as an example; replace it with your own business.

## Prepare

- Connecting data sources requires a project owner or project administrator. Regular members can start from step 2 using existing data sources.
- A read-only database account, or tidy Excel / CSV files.
- Five to ten business questions your team really cares about, with reference answers for verification.

## Steps

**Connect data and select only the tables you need**

Add a data source by following [Connect data sources](https://docs.asktable.com/en/data/connect). Select only the tables needed to answer the business questions, such as orders, stores, and products. Wait for metadata parsing to complete.

**Write table and field notes**

Open the data source. For each table, write one sentence on “what one row represents”; for commonly used fields, write the unit, code meanings, and definition, such as “amount: amount paid, in cents, after coupons”. IDs and technical fields unrelated to analysis can be hidden. See [Table and field notes](https://docs.asktable.com/en/data/semantics) and [Hidden fields and masking](https://docs.asktable.com/en/data/hidden-fields).

This step has the greatest impact on accuracy.

**Create the agent and select data sources**

In “Agents”, click “Create” and choose a similar template (such as “Store operations analyst”) or start from scratch. Add the data source under “Configuration” → “Data sources”. Write a description that says which questions it can answer. See [Create and configure agents](https://docs.asktable.com/en/agent/overview).

**Write business definitions**

Under “Documents”, write a [business document](https://docs.asktable.com/en/agent/documents) for each key metric, such as “Sales = amount paid - refunds, counted by payment date”. Under “Configuration” → “Preferences”, write background and answer style that apply to every question. See [Basic settings and knowledge preferences](https://docs.asktable.com/en/agent/profile).

**Add analysis methods**

When your team has a fixed analysis routine (such as a weekly report format or anomaly investigation steps), write it as a [skill](https://docs.asktable.com/en/agent/skill) and attach it to the agent. Make sure “User clarification” stays enabled in [Capability settings](https://docs.asktable.com/en/agent/capabilities).

**Test with real questions**

Select this agent in a conversation, ask the prepared questions one by one, compare the results with the reference answers, and check the executed SQL.

When an answer is wrong, add information according to the cause:

| Cause                                    | Add to                                                                |
| ---------------------------------------- | --------------------------------------------------------------------- |
| Wrong field chosen or code misunderstood | Table and field notes                                                 |
| Wrong definition                         | Business documents                                                    |
| Steps or format not as required          | Skills                                                                |
| Complex query with a fixed pattern       | [Training set](https://docs.asktable.com/en/data/manage#training-set) |

After changes, retest with the same questions until the results are reliable.

**Set permissions and share**

If different people may see only different data, have an administrator configure [data permissions](https://docs.asktable.com/en/permissions) first. Then share the agent with specific colleagues or the entire project from the “Agents” list.

**Connect your team's tools**

As needed, connect the agent to [Feishu](https://docs.asktable.com/en/integrations/feishu) or [Slack](https://docs.asktable.com/en/integrations/slack), set up [scheduled reports](https://docs.asktable.com/en/integrations/scheduled-reports), or [embed](https://docs.asktable.com/en/integrations/embed) it in a business system.

## Check the outcome

- All prepared questions get correct results, with the correct definitions visible in the SQL.
- When colleagues ask with their own accounts, they see only the data their permissions allow.
- After launch, review [Logs and user feedback](https://docs.asktable.com/en/agent/logs-feedbacks) regularly and add notes, documents, or skills for wrong answers.

## Next steps

- Methods for writing accurate questions, which you can share with colleagues: [How to get accurate results](https://docs.asktable.com/en/question-tips)
- Limit data by department and region: [Design data permissions by department and region](https://docs.asktable.com/en/permissions/design)