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

# Conversation design workflow

Go over the bot design process step by step, from planning to publishing.

Conversation design is about building and maintaining chatbots. Learn more here:

{% content-ref url="/pages/mpXraHKLeRYz6821AeNL" %}
[Conversation design](/buildabot/conversation-design.md)
{% endcontent-ref %}

<figure><img src="https://2786867680-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LLTwFwbOqJj4dDhg8Ju%2Fuploads%2FXmEJ5iS3nEvD98oSyHKF%2FScreenshot%202024-01-30%20at%2016.18.10.png?alt=media&amp;token=f763fdb8-8e4f-43a8-82b2-9b0962c557a3" alt=""><figcaption><p>The chatbot design workflow.</p></figcaption></figure>

## **1.** Plan

Planning your bot right is crucial to be efficient. This step encompasses:

* Defining your goals
* Exploring your tech
* Designing your flowchart

## 2. Build

Now it's time to actually build your bot in Chatlayer. This means:

* translating all of the steps you outlined in your design to the right blocks in Chatlayer
* writing the full text for all of the bot messages

At the end of this stage you should have a first version of your bot ready for testing.

{% content-ref url="/pages/hmqJy3fBdWwIavmO9DJk" %}
[Broken mention](broken://pages/hmqJy3fBdWwIavmO9DJk)
{% endcontent-ref %}

## 3. Test and improve

Test the first version of your bot thoroughly. Do not rely only on the bot builders themselves but also include people who were not involved. Advise testers to:

* Go through each of the flows multiple times
* Try all possible combinations of choices within the conversation
* Try to trigger all bot messages to detect any bugs, spelling mistakes, or points where users might get stuck.

Make sure any issues testers find are resolved before publishing the bot.

## 4. Publish

Once issues have been resolved, you are ready to put your bot live. In the first few weeks after going live, closely monitor the traffic on your bot. This will not only give you insight into how many people are using the bot and how often but also allow you to identify key areas for improvement. By monitoring and analyzing user conversations it is possible to:

* Identify if the bot is performing as intended: is it able to successfully help customers with the intended use cases, without any errors?
* Reveal if users have any requests the bot is not yet set up to handle. If many users have such requests, it might be a good idea to expand your bot's scope and add extra use cases in the future.

Remember that conversation design is an iterative processes and a chatbot always remains a work in progress to meet new customer demands. Therefore, it is important to continually monitor your customer conversations and periodically revisit these steps to improve the experience.

## 5. Iterate

You would like to add a new use case to your chatbot? Go through the same steps and iterate to make your bot even better!


---

# 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.chatlayer.ai/buildabot/conversation-design/conversation-design-workflow.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.