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 #citations

ActiveNewMost usedRecommended
AllAI & Prompt Engineering324Engineering176Data & Analytics89Product4Design28Sales2Marketing4Finance
#citationsClear filters
LELeo Fischer@leofischer·3w ago

Gemini found the hole in my a research prompt that cites its work plan

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

Leo Fischer

For a research prompt that cites its work, 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 a research prompt that cites its work, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages
3411.4k
LELeo Fischer@leofischer·1mo ago

My notes from fixing a research prompt that cites its work

This started as a messy question about a research prompt that cites its work. The follow-up made the answer practical.

Leo Fischer

I am stuck on a research prompt that cites its work. I need to research a question, separate facts from inference, and attach sources to each claim, 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
3413.9k
LELeo Fischer@leofischer·2mo ago

A blunt review of my approach to a research prompt that cites its work

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

Leo Fischer

Give me a short checklist for a research prompt that cites its work. 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
3312.8k
RARavi Gupta@ravigupta·2w ago

Forked from@leofischer/What finally made a research prompt that cites its work click for me

What finally made a research prompt that cites its work click for me

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

Ravi Gupta

Help me research a question, separate facts from inference, and attach sources to each claim. 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 recommendat

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 a research prompt that cites its work, 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
BEBen Haddad@benhaddad·2w ago

Forked from@leofischer/My notes from fixing a research prompt that cites its work

My notes from fixing a research prompt that cites its work

This started as a messy question about a research prompt that cites its work. The follow-up made the answer practical.

Ben Haddad

I am stuck on a research prompt that cites its work. I need to research a question, separate facts from inference, and attach sources to each claim, 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
LALayla Fischer@laylafischer·2w ago

Forked from@leofischer/How I ask for help with a research prompt that cites its work

How I ask for help with a research prompt that cites its work

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

Layla Fischer

Be blunt about my plan for a research prompt that cites its work. 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
QUQuinn Harper@quinnharper·2w ago

Forked from@leofischer/Gemini found the hole in my a research prompt that cites its work plan

Gemini found the hole in my a research prompt that cites its work plan

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

Quinn Harper

For a research prompt that cites its work, 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 a research prompt that cites its work, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages
3200
BEBen Brooks@benbrooks·2w ago

Forked from@leofischer/A blunt review of my approach to a research prompt that cites its work

A blunt review of my approach to a research prompt that cites its work

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

Ben Brooks

Give me a short checklist for a research prompt that cites its work. 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
LELeo Fischer@leofischer·3mo ago

What finally made a research prompt that cites its work click for me

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

Leo Fischer

Help me research a question, separate facts from inference, and attach sources to each claim. 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 recommendat

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 a research prompt that cites its work, 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
3312.5k
LELeo Fischer@leofischer·3mo ago

How I ask for help with a research prompt that cites its work

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

Leo Fischer

Be blunt about my plan for a research prompt that cites its work. 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
3311.1k
COcontext window cat@context_window_cat·1w ago

How do I build a deep research agent with reliable citations?

A source-planning and claim-verification prompt for research agents that need traceable, current, and non-fabricated citations.

context window cat

# How do I build a deep research agent with reliable citations? Act as a research methods editor. ## Goal Produce a claim-led research brief where every material assertion is traceable. ## Inputs - research question and decision context - date and geography boundaries - allowed source types - required depth and output length If a required input is missing, ask concise questions or mark the assumpt

Claudeclaude-opus-4.6

Use the attached prompt by replacing its input bullets with the real context. The strongest results come from evidence-bearing inputs and explicit success criteria. The required deliverables are: research plan, sourced findings, uncertainty and conflict log, citation audit table.

Show all 4 messages
4001
COcontext window cat@context_window_cat·1w ago

Best prompt to stop RAG hallucinations

A grounded-answer prompt plus retrieval and validation checks that constrain claims to supplied evidence and expose coverage gaps.

context window cat

# Best prompt to stop RAG hallucinations Act as a retrieval-augmented generation engineer. ## Goal Produce evidence-bounded answers and diagnose whether failures come from retrieval or generation. ## Inputs - user question - retrieved chunks with stable IDs - allowed citation format - abstention and coverage requirements If a required input is missing, ask concise questions or mark the assumption

ChatGPTcodex

Use the attached prompt by replacing its input bullets with the real context. The strongest results come from evidence-bearing inputs and explicit success criteria. The required deliverables are: grounded answer, claim-to-source map, unsupported questions, retrieval improvement recommendations.

Show all 4 messages
4000

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