Workflow · Production

Building Your Own Product Copilot: Challenges, Opportunities, and Needs

The problem

Software engineers building product copilots face pain points at every step of the engineering process — including prompt engineering, orchestration, and testing — because existing software engineering processes and tools have not caught up with the challenges involved in building AI-powered applications.

Workflow diagram · grounded in source
1
User query as trigger
trigger
“whatever you type in your chat saying something like refactor this”
2
Intent detection
ai_action
“the first step was to perform intent detection”
3
Skill routing
routing
“Once an intent is detected, the prompt is then routed to the appropriate skill, "like adding a test or generating documentation," that is capable of handling the request.”
4
Response output and processing
output
“After the model returned a response for the prompt, additional processing was necessary in order to interpret the response.”
Reported outcome

(not stated)

Reported stack
GPT-4Mural
Source
https://arxiv.org/html/2312.14231v1
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

(not stated)

What tools did this team use?

GPT-4, Mural.

How is this workflow AI workflow structured?

User query as trigger → Intent detection → Skill routing → Response output and processing.