codeforpdx / codeforpdx/tenantfirstaid

LangSmith Experiments on Single-turn dataset

Open
#245 0 comments 0 reactions 1 assignee View on GitHub

@yangm2 is already working on this.

Since Jan 15, 2026.

backend
Dominant language
Python
Stars
13
Forks
21
Avg merge
6d 7h
Merged PRs (30d)
3

Description

This issue captures ideas for experiments to run against single-turn baseline results

  • gemini 2.5 pro w/o RAG - quantify how much RAG is improving correctness
  • gemini 3.0 preview w/ RAG - quantify correctness/tokens-per-second/tone/cost-per-answer
  • chatGPT frontier model (5.2?) w/ VertexSearch - gemini vs chatGPT
  • thinking budget (in tokens) - investigate correlation factor between thinking budget and correctness, thinking budget and cost-per-answer
  • gemini 2.5 pro w/ few-shot examples ??? - correctness
  • fine-tune gemini 2.5 pro ??? - correctness
  • a/b-test variations on system prompt - correctness

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.