Generate Sequence Diagrams for Azure B2C User Journeys with ChatGPT

Working with Azure B2C is an XML battle, especially when it comes to customizing user journeys using custom policies. A starter pack you can get from GitHub helps you set up your own policy.

GitHub - Azure-Samples/active-directory-b2c-custom-policy-starterpack: Azure AD B2C now allows uploading of a Custom Policy which allows full control and customization of the Identity Experience Framework

Azure AD B2C now allows uploading of a Custom Policy which allows full control and customization of the Identity Experience Framework - Azure-Samples/active-directory-b2c-custom-policy-starterpack

GitHubAzure-Samples

The readme is comprehensive and has all the necessary information, but
sometimes, it helps to have a flow sequence diagram. Sequence diagrams can be
created using Mermaid, given a syntax that can be included in your Markdown
documentation. The renderer will then visualize the sequences for you.

Generative AI can help here

There is an excellent way to do this with Generative AI. In my case, I use
ChatGPT. The steps are as follows.

First, upload the XML policy files you want to analyze. In my example, I'm
interested in the sign-in and sign-up user journey, so I'm only uploading
TrustFrameworkBase.xml, TrustFrameworkExtensions.xml, and
SignUpOrSignIn.xml.

Next, prompt ChatGPT to generate the sequence diagram based on the uploaded
files. In the case I provide here, I used the following prompt:

Create a sequence diagram for the <User Journey Name> user journey in Azure AD B2C. The diagram should integrate the flow of claims directly into the main sequence and use notes and background colors to distinguish between different flows.

### Sequence Diagram Details:
1. The initial request where the user opens the page and requests the policy.
2. The user decision point where they choose between different options (e.g., Sign Up or Sign In).
3. The detailed flow for each option, including:
    - Collecting claims
    - Validating and transforming claims
    - Interactions with Azure AD for validation and user data retrieval
    - Displaying success messages to the user
4. The token refresh flow if applicable.
5. Use notes to highlight claims collection and validation.
6. Use different background colors to distinguish between different options (e.g., Sign Up and Sign In).

Replace <User Journey Name> with the user journey I uploaded, in the example Sign In or Sign Up. The chatbot will start to analyse the files, and as a result, I get back this Mermaid sequence diagram.

You can look at the result in GitHub, which supports rendering Mermaid diagrams.

As with all generative models, the output may vary depending on how you prompt it and what model you use. It is more about the basic idea that we can transform one format to another, which helps us create documentation we don't have out of the box.

Give it a try.