Genesys Cloud - Developer Community!

I've been working hard on the recent update to my Claude Code plugin to allow it to understand existing Architect flows:

LinkedIn post about the release

This has been an interesting challenge as flows are complex and their JSON definition (which my plugin retrieves) can be jolly big! So can easily pollute an AI agent's context.

I believe I have cracked it now though, as testing by me and others in the community of v2 of the Claude Code plugin attests to.

It works by deterministically simplifying flows into a intermediate representation, which Claude Code can progressively enrich and search.

This now means you can use AI to, among other things:

• Identify logical issues - such as misinforming the customer of where they're being transferred, never leaving a loop due to incorrectly updating a variable
• Static issues - dead branches, not handling Data Action failures/timeouts
• Enforcing standards - enforcing a set of standards are followed in how the flow is created, such as consistent variable names and error handling
• Documenting flows - as well as being able to ask questions of them
• Mapping dependencies

If you have any feedback I'd love to hear it! My aim is to make developing and maintaining flows easier, so hopefully this goes some way to achieving that.

You can find the plugin here: GitHub - MakingChatbots/genesys-cloud-plugins

#Architect
#CXasCode
#PlatformAPI

------------------------------
Lucas Woodward
Winner of Orchestrator of the Year, Developer (2025)

LinkedIn - https://www.linkedin.com/in/lucas-woodward-the-dev
Newsletter - https://makingchatbots.com
------------------------------

Lucas Woodward Thank you for sharing.

------------------------------
Phaneendra
Technical Solutions Consultant
------------------------------

This is great. Thanks for sharing!

------------------------------
Dominik
Principal Professional Services Consultant
------------------------------

Great work, this will come in quite handy.

------------------------------
Jason
na
------------------------------

Thank you @Lucas Woodward for the share!

------------------------------
TIMOTHY
Technology Experience Manager
------------------------------

That's really interesting! 👏

------------------------------
Camila Meneghini
------------------------------

Thanks all!

Someone in the comments on LinkedIn asked if it can audit a flow and suggest ways to optimise overall flow size. I wanted to share my reply here as it demonstrates the flexibility of this tooling:

Claude Code was able to use my plugin to understand the flow and suggest the following improvements:

------------------------------
Lucas Woodward
Winner of Orchestrator of the Year, Developer (2025)

LinkedIn - https://www.linkedin.com/in/lucas-woodward-the-dev
Newsletter - https://makingchatbots.com
------------------------------

Great, Thanks for sharing !

------------------------------
Ashiesh Sharma
GCX- GCP, ARC, SCR, QM
Producer | Conductor | Composer
BT plc
------------------------------

Great work, Lucas! Tackling the JSON size and context window pollution in Architect flows is a massive win for anyone working with Genesys Cloud.

Your post highlights a crucial mindset shift we should embrace: we need to move beyond just building flows that 'work' to designing them with clean structure and readability as core principles. When flow architecture is intuitive and well-structured, it creates a powerful dual benefit:

1. Human Onboarding & Maintenance: A basic user or a new team member can instantly understand the business logic, intent, and routing paths without getting lost in spaghetti flows.

2. AI Agent Efficiency: As your plugin demonstrates, clean and predictable patterns allow AI agents to parse, reason about, and enrich the intermediate representation with fewer iterations and far lower context overhead.

In a way, writing clean, well-structured flows is becoming the ultimate combination of good software engineering and effective prompt design. Kudos for pushing the community forward!

------------------------------
Israel Valverde
------------------------------

Great work, thank you for sharing!

------------------------------
MinHyuk
na
------------------------------

Thanks for sharing @Lucas Woodward

------------------------------
Akhil
------------------------------