dfe-analytical-services / dfe-analytical-services/analysts-guide

[Feature]: Guidance on how we use AI within the DfE

Open
#236 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
R
Stars
6
Forks
9
PR merge metrics
No merged PRs in 30d

Description

### Description

Suggested at the DISD away day, we could do with a framework around how we expect AI to be used by analysts within the DfE.

I guess sections along the lines of:
- Using AI prompting to generate draft FOI / PQ responses
- How AI is used in EES
- How AI can be used to optimise code
- vectorisation
- code consolidation (converting to functions)
- AI in QA

### Use case

As an analyst I want to know how I can / should use AI in my day to day work

### Why this is important

Help give analysts confidence / security on how they can use AI

### Additional Context

Would be good to break this up and get input / case studies from teams on how they do some of this.

Contributor guide

Open the contributing guide

Research direction

Start by turning the listed use cases into a proposed guidance structure and gather input or case studies from the relevant teams. Done means analysts can find clear, confidence-building guidance for prompting, EES, code optimisation, and QA, including how AI should and should not be used.

Written by the indexing model from the issue text.

Assessment

Domain
ai, documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.