Kenji Fujita (@kenjifujita)

Forked from@nadiameyer/The question that cleaned up meeting notes into decisions

The question that cleaned up meeting notes into decisions

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

Kenji Fujita

Help me extract decisions, owners, deadlines, and unresolved questions from raw meeting notes. 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 recommenda

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 meeting notes into decisions, 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

Kenji Fujita@kenjifujita·2w ago

Forked from@anyavolkov/What I was getting wrong about reviewing code written by an agent

What I was getting wrong about reviewing code written by an agent

Sharing the correction because the mistake looked reasonable until I tested it.

Kenji Fujita

I want to learn reviewing code written by an agent, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain reviewing code written by an agent in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6100

Kenji Fujita@kenjifujita·2w ago

I finally found a good way to learn checking an A/B test before celebrating

The useful change was doing a small retrieval check before reading more.

Kenji Fujita

I want to learn checking an A/B test before celebrating, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain checking an A/B test before celebrating in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

621284

Kenji Fujita@kenjifujita·1mo ago

I finally found a good way to learn tracking prompt versions and results

The useful change was doing a small retrieval check before reading more.

Kenji Fujita

I want to learn tracking prompt versions and results, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain tracking prompt versions and results in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

621104

Kenji Fujita@kenjifujita·2mo ago

I finally found a good way to learn using property-based tests

The useful change was doing a small retrieval check before reading more.

Kenji Fujita

I want to learn using property-based tests, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain using property-based tests in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6214.6k

Kenji Fujita@kenjifujita·2mo ago

Forked from@zurimensah/The using retrieval practice for diagrams tutor prompt I saved

I finally found a good way to learn prompt injection basics for tool users

The useful change was doing a small retrieval check before reading more.

Kenji Fujita

I want to learn prompt injection basics for tool users, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain prompt injection basics for tool users in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6224.9k

Kenji Fujita@kenjifujita·3mo ago

I finally found a good way to learn reviewing code written by an agent

The useful change was doing a small retrieval check before reading more.

Kenji Fujita

I want to learn reviewing code written by an agent, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Show all 6 messages

6211.6k

Public pits

The question that cleaned up meeting notes into decisions

What I was getting wrong about reviewing code written by an agent

I finally found a good way to learn checking an A/B test before celebrating

I finally found a good way to learn tracking prompt versions and results

I finally found a good way to learn using property-based tests

I finally found a good way to learn prompt injection basics for tool users

I finally found a good way to learn reviewing code written by an agent