Explore

Tagged #operations

All AI & Prompt Engineering324 Engineering176 Data & Analytics89 Product4 Design28 Sales2 Marketing4 Finance

I needed a usable answer on a pre-mortem for launch day

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

Mateo Patel

I am stuck on a pre-mortem for launch day. I need to imagine a launch failed and turn likely causes into checks and owners, but my current attempt is getting vague and too big. What would you check first?

Geminigemini-2.5-pro

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. 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

3402.4k

Mateo Patel@mateopatel·1mo ago

a pre-mortem for launch day, minus the vague advice

This started as a messy question about a pre-mortem for launch day. The follow-up made the answer practical.

Mateo Patel

Give me a short checklist for a pre-mortem for launch day. I want something I can run before I call the work done.

Geminigemini-2.5-pro

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] 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

3303.8k

Mateo Patel@mateopatel·2mo ago

ChatGPT was overcomplicating a pre-mortem for launch day, so I reset the question

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

Mateo Patel

Be blunt about my plan for a pre-mortem for launch day. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

ChatGPTgpt-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, write the riskiest assumption down.

Show all 3 messages

3303.8k

Mateo Patel@mateopatel·3mo ago

I stopped guessing about a pre-mortem for launch day

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

Mateo Patel

For a pre-mortem for launch day, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

Claudeclaude-opus-4.5

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 pre-mortem for launch day, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3402.5k

Mateo Patel@mateopatel·3mo ago

The question that cleaned up a pre-mortem for launch day

This started as a messy question about a pre-mortem for launch day. The follow-up made the answer practical.

Mateo Patel

Help me imagine a launch failed and turn likely causes into checks and owners. 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. Otherwise,

Claudeclaude-opus-4.5

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 pre-mortem for launch day, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3301.1k

cache me if u can@cache_me_if_u_can·1w ago

Best prompt for an AI incident response runbook

A containment-first incident prompt for building timelines, testing hypotheses, coordinating communications, and preserving evidence.

cache me if u can

# Best prompt for an AI incident response runbook Act as a incident commander and site reliability engineer. ## Goal Stabilize the service while maintaining a factual decision log and safe recovery path. ## Inputs - alerts and user impact - recent changes - logs, metrics, and traces - owners, escalation paths, and recovery objectives If a required input is missing, ask concise questions or mark th

Geminigemini-2.5-pro

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: status summary, timeline, hypothesis and evidence table, recovery and post-incident checklist.

Show all 4 messages

4000

The pitter@pitter·1w ago

How to build an AI customer support agent

A copy-ready, evidence-first prompt for the timely question: How do we deploy a customer-support AI agent safely?

The pitter

What is the best prompt for this trending question: How do we deploy a customer-support AI agent safely?

ChatGPTgpt-5.6

## Copy-ready prompt ```text Act as a customer support operations leader. Answer this question: “How do we deploy a customer-support AI agent safely?” Objective: design a phased support-agent rollout that improves resolution without damaging customer trust. 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

Open conversation

2000