PitHub
HomeExplore
New pit
MCP serverSave straight from your agent
About usHow it worksFAQBlogContact us
Sign in
PitHub
Sign in
HomeExploreCreateSign in

Explore

Loading…

Explore

Tagged #quality

ActiveNewMost usedRecommended
AllAI & Prompt Engineering324Engineering176Data & Analytics89Product4Design28Sales2Marketing4Finance
#qualityClear filters
NINia Costa@niacosta·3mo ago

My notes from fixing reviewing agent-written code

I wanted help with reviewing agent-written code without pretending the model knew facts I had not provided.

Nia Costa

I am stuck on reviewing agent-written code. I need to review generated code for silent assumptions, missing tests, and operational risk, but my current attempt is getting vague and too big. What would you check first?

ChatGPTgpt-5

First, shrink the decision. Do not solve the whole subject at once. 1. Reproduce the failure before changing code. 2. Keep the patch smaller than the diagnosis. 3. Write the rollback before deployment. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages
3302.9k
NINia Costa@niacosta·2mo ago

Gemini found the hole in my reviewing agent-written code plan

I kept the useful constraints and dropped the role-play. It works better when the missing details are stated plainly.

Nia Costa

For reviewing agent-written code, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

Geminigemini-2.5-pro

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For reviewing agent-written code, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages
3301.4k
NINia Costa@niacosta·3mo ago

A blunt review of my approach to reviewing agent-written code

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Nia Costa

Give me a short checklist for reviewing agent-written code. I want something I can run before I call the work done.

ChatGPTgpt-5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Reproduce the failure before changing code - [ ] Keep the patch smaller than the diagnosis - [ ] Write the rollback before deployment - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages
3401.4k
NINia Costa@niacosta·4mo ago

How I ask for help with reviewing agent-written code

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Nia Costa

Be blunt about my plan for reviewing agent-written code. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Claudeclaude-opus-4.5

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, keep the patch smaller than the diagnosis.

Show all 3 messages
3401.5k
NINia Costa@niacosta·5mo ago

Forked from@owenmorgan/How I ask for help with a prompt for spreadsheet cleanup

What finally made reviewing agent-written code click for me

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Nia Costa

Help me review generated code for silent assumptions, missing tests, and operational risk. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation

Geminigemini-2.5-pro

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For reviewing agent-written code, I would start with these checks: - Reproduce the failure before changing code - Keep the patch smaller than the diagnosis - Write the rollback before deployment If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages
340271
pitter's avatarThe pitter@pitter·2mo ago

How to evaluate LLM applications in production

A copy-ready, evidence-first prompt for the timely question: How do we build meaningful LLM evaluations?

The pitter

What is the best prompt for this trending question: How do we build meaningful LLM evaluations?

ChatGPTgpt-5.6

## Copy-ready prompt ```text Act as an evaluation scientist. Answer this question: “How do we build meaningful LLM evaluations?” Objective: create an evaluation suite that predicts real production quality. First, ask up to five concise questions needed to tailor the analysis. If no answers are available, state reasonable assumptions and continue. Use current information as of today; browse authoritative primary sources where possible, distinguish facts from inference, and cite every time-sensitive claim with a direct link and publication date. Cover: task taxonomy, representative data, graders

Open conversation
2000
pitter's avatarThe pitter@pitter·2mo ago

How to review AI-generated code

A copy-ready, evidence-first prompt for the timely question: How do we review AI-generated code safely?

The pitter

What is the best prompt for this trending question: How do we review AI-generated code safely?

ChatGPTgpt-5.6

## Copy-ready prompt ```text Act as a principal engineer and application security reviewer. Answer this question: “How do we review AI-generated code safely?” Objective: create a repeatable review checklist for AI-generated changes. First, ask up to five concise questions needed to tailor the analysis. If no answers are available, state reasonable assumptions and continue. Use current information as of today; browse authoritative primary sources where possible, distinguish facts from inference, and cite every time-sensitive claim with a direct link and publication date. Cover: requirements tra

Open conversation
2000

Browse by tag

#ai314#chatgpt211#claude208#gemini208#prompting182#agents174#context-engineering172#coding160
24
Strategy31
Operations4
Customer Success3
People & Recruiting4
Security & Compliance8
Legal2
Other Professional1
#debugging106
#software-learning100
#data85
#analysis55
#statistics55
#202650
#data-literacy50
#prompt-template50
#trending-questions50
#business25
#design25
#testing25
#automation21
#finance21
#cash-flow16
#research16