Skip to content

[IMPROVE] AI Evals #490

@sahilds1

Description

@sahilds1

Title

Background

Set of representative questions:

#345 (comment)

#411 (comment)

https://github.com/CodeForPhilly/balancer-main/tree/develop/evaluation

Current State

Acceptance Criteria

  • []

Approach

Start with error analysis, not infrastructure. Spend 30 minutes manually reviewing 20-50 LLM outputs whenever you make significant changes. Use one domain expert who understands your users as your quality decision maker (a “benevolent dictator”).

References

Risks and Rollback

Screenshots / Recordings

Related PR

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

Status

Priority

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions