> 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/the-building-process.md).

# The building process

CodeWords handles the building process for your automations. This page covers the details of how prompting, clarifying, and deploying work.

You can get started by prompting — describe what you want, and Cody builds it with you. For a quick start, see [Quickstart](https://docs.codewords.ai/quickstart) and [Build your first automation](https://docs.codewords.ai/build-your-first-automation).

### Prompt: Describe your idea

Head to the chat and describe what you want to build in natural language. Cody clarifies the idea with you and builds it end-to-end.

Try prompts like:

> “A workflow that monitors feature launches on my competitor websites”

> “A workflow that extracts the transcript from YouTube videos”

> “A workflow that enriches my LinkedIn name list with contact info”

> “A workflow that sends this form when someone submits an inquiry”

If you’re not sure what to build, ask Cody for ideas. Share a problem you’re trying to solve, a repetitive task that creates friction, or what your job looks like day to day.

### Collaboration with Cody

Once you’ve decided what to build, Cody asks clarifying questions to refine the idea before building.

For example:

* Where should the output go?
* How often should this workflow run?
* What should the focus of this workflow be?

You can skip a question or let Cody decide.

When you’re ready, Cody asks if it should start building. Confirm, or keep iterating in chat first.

Cody also asks whether you want to build first and test later, or test as it builds. Either way, Cody still tests the workflow and debugs errors automatically.

#### Todo lists

When Cody starts building, it produces a todo list — an overview of the steps to reach the finished automation. You can see what’s done, in progress, and still to do.

#### Using your deployed workflow

When Cody deploys the workflow, it gives you a unique URL to the run page so you can start using it right away.

You can also find and manage workflows in the [Projects](https://codewords.agemo.ai/workflows/library) tab.

<figure><img src="https://1922564109-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDPhSzUJZB9UnI8nwVLWT%2Fuploads%2FdWf9RE19FAOos7JWOQtc%2FScreenshot%202026-05-14%20at%2022.41.51.png?alt=media&amp;token=a40ec8e2-0f42-4689-92f5-c2916e396b52" alt=""><figcaption></figcaption></figure>

#### Making changes

To adjust a deployed workflow, go back to your chat with Cody and ask for edits. The building process restarts — this time to update the existing workflow.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.codewords.ai/automations/the-building-process.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
