> For the complete documentation index, see [llms.txt](https://docs.codewords.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.codewords.ai/automations/readme.md).

# Introduction to Cody

### What is Cody?

Cody is your AI automation assistant. You describe what you want in plain language, and Cody builds the workflow or agent — real automation code, not drag-and-drop blocks.

Cody collaborates with you to understand the goal, handles multi-step logic, and connects the apps you need.

### How it works

#### 1. Understanding your needs

Describe what you want to achieve.

Cody figures out the steps, logic, and integrations, then shows a clear plan as a todo list. You review, edit, and approve before building starts.

#### 2. Clarifying questions

If Cody needs more context, it asks follow-up questions so the final automation matches what you intend.

#### 3. Building the workflow

Once you approve, Cody writes the code and connects integrations. You’ll be prompted to connect any app Cody doesn’t already have access to.

You don’t have to write the code yourself — Cody handles the technical details.

#### 4. Testing, debugging, and deploying

Cody deploys your automation and runs tests against real data. If something fails, it reviews the logs, finds the cause, and applies fixes.

### What you can do

* **Build new workflows** — Describe lead tracking, content generation, or any other idea, and Cody builds it end-to-end.
* **Modify existing workflows** — Add steps, connect different apps, or refine logic in chat.
* **Debug and optimize** — When something doesn’t work, Cody inspects logs and helps you fix it.
* **Connect other platforms** — Integrate with external apps, or with custom apps built on tools like Lovable, Bolt, and v0.

### Why Cody is different

#### Conversational automation

Instead of drag-and-drop blocks or long forms, you build by talking. Describe the goal in English; Cody turns it into a working automation.

#### Real code without coding

Most automation tools stick to predefined actions. Cody generates real Python automation code, so it can handle complex logic, multi-step flows, and deeper API integrations.

You get the flexibility of code with the ease of conversation.

### FAQs

<details>

<summary>Do I need coding experience to use Cody?</summary>

No. You describe what you want, and Cody handles the code behind the scenes.

</details>

<details>

<summary>What kinds of workflows can Cody create?</summary>

Anything from lead tracking and report generation to AI agents that analyze data, send alerts, or integrate with Slack, Notion, Google Sheets, and more.

</details>

<details>

<summary>Can Cody fix or debug workflows automatically?</summary>

Yes. Cody reviews logs, identifies the issue, and applies fixes — no manual debugging required.

</details>

<details>

<summary>How is Cody different from traditional automation tools?</summary>

Cody doesn’t rely on drag-and-drop blocks. It generates real, production-grade code that supports advanced logic and multi-step automation.

</details>

<details>

<summary>How do I set how Cody responds to me?</summary>

Open [Settings → Personalization](https://codewords.agemo.ai/#settings/personalization) and write **Custom instructions** — for example your role, preferred tone, or tech stack. Cody applies them across chats. See [Account](https://docs.codewords.ai/help-center/billing/account) for examples and details.

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.codewords.ai/automations/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.