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 #few-shot

ActiveNewMost usedRecommended
AllAI & Prompt Engineering324Engineering176Data & Analytics89Product4Design28Sales2Marketing4Finance
#few-shotClear filters
THTheo Young@theoyoung·2w ago

A blunt review of my approach to prompting from examples

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Theo Young

Give me a short checklist for prompting from examples. 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 - [ ] Put the source of truth in the prompt - [ ] Mark missing evidence instead of filling it in - [ ] Add a stop condition before tool use - [ ] 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
3313.9k
THTheo Young@theoyoung·1mo ago

How I ask for help with prompting from examples

This started as a messy question about prompting from examples. The follow-up made the answer practical.

Theo Young

Be blunt about my plan for prompting from examples. 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, mark missing evidence instead of filling it in.

Show all 3 messages
3312.4k
THTheo Young@theoyoung·3mo ago

My notes from fixing prompting from examples

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Theo Young

I am stuck on prompting from examples. I need to turn three good examples and one bad example into a clear repeatable instruction, 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. Put the source of truth in the prompt. 2. Mark missing evidence instead of filling it in. 3. Add a stop condition before tool use. 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
3413.8k
NINico Lane@nicolane·2w ago

Forked from@theoyoung/What finally made prompting from examples click for me

What finally made prompting from examples click for me

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Nico Lane

Help me turn three good examples and one bad example into a clear repeatable instruction. 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 prompting from examples, I would start with these checks: - Put the source of truth in the prompt - Mark missing evidence instead of filling it in - Add a stop condition before tool use If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages
3200
ANAnika Brooks@anikabrooks·2w ago

Forked from@theoyoung/My notes from fixing prompting from examples

My notes from fixing prompting from examples

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Anika Brooks

I am stuck on prompting from examples. I need to turn three good examples and one bad example into a clear repeatable instruction, 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. Put the source of truth in the prompt. 2. Mark missing evidence instead of filling it in. 3. Add a stop condition before tool use. 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
3200
ISIsaac Stone@isaacstone·2w ago

Forked from@theoyoung/How I ask for help with prompting from examples

How I ask for help with prompting from examples

This started as a messy question about prompting from examples. The follow-up made the answer practical.

Isaac Stone

Be blunt about my plan for prompting from examples. 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, mark missing evidence instead of filling it in.

Show all 3 messages
3200
NINico Ibrahim@nicoibrahim·2w ago

Forked from@theoyoung/Gemini found the hole in my prompting from examples plan

Gemini found the hole in my prompting from examples plan

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Nico Ibrahim

For prompting from examples, 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 prompting from examples, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages
3200
AMAmina Farah@aminafarah·2w ago

Forked from@theoyoung/A blunt review of my approach to prompting from examples

A blunt review of my approach to prompting from examples

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Amina Farah

Give me a short checklist for prompting from examples. 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 - [ ] Put the source of truth in the prompt - [ ] Mark missing evidence instead of filling it in - [ ] Add a stop condition before tool use - [ ] 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
3200
THTheo Young@theoyoung·2mo ago

Gemini found the hole in my prompting from examples plan

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Theo Young

For prompting from examples, 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 prompting from examples, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages
3411.1k
THTheo Young@theoyoung·2mo ago

What finally made prompting from examples click for me

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Theo Young

Help me turn three good examples and one bad example into a clear repeatable instruction. 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 prompting from examples, I would start with these checks: - Put the source of truth in the prompt - Mark missing evidence instead of filling it in - Add a stop condition before tool use If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages
331119

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