Ines Navarro (@inesnavarro)

Forked from@noorgrant/I stopped guessing about a useful second-opinion prompt

I stopped guessing about a useful second-opinion prompt

I wanted help with a useful second-opinion prompt without pretending the model knew facts I had not provided.

Ines Navarro

For a useful second-opinion prompt, 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 useful second-opinion prompt, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3200

Ines Navarro@inesnavarro·2w ago

Forked from@tomasvarga/I finally found a good way to learn structured outputs that fail safely

I finally found a good way to learn structured outputs that fail safely

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

Ines Navarro

I want to learn structured outputs that fail safely, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain structured outputs that fail safely 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

Ines Navarro@inesnavarro·3w ago

Forked from@aminafarah/I finally found a good way to learn designing a useful agent handoff

The designing a useful agent handoff tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Ines Navarro

Tutor me on designing a useful agent handoff. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worked exa

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain designing a useful agent handoff 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

6313.2k

Ines Navarro@inesnavarro·1mo ago

The testing API failure paths tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Ines Navarro

Tutor me on testing API failure paths. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worked example, t

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain testing API failure paths 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

6311k

Ines Navarro@inesnavarro·2mo ago

Forked from@aminafarah/I finally found a good way to learn context engineering for reliable agents

The context engineering for reliable agents tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Ines Navarro

Tutor me on context engineering for reliable agents. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one wor

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain context engineering for reliable agents 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

6311.3k

Ines Navarro@inesnavarro·2mo ago

The human review for automated workflows tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Ines Navarro

Tutor me on human review for automated workflows. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worked

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain human review for automated workflows 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

6312.8k

Ines Navarro@inesnavarro·3mo ago

The making a safe dependency upgrade plan tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Ines Navarro

Tutor me on making a safe dependency upgrade plan. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worke

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain making a safe dependency upgrade plan 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

6313.4k

Public pits

I stopped guessing about a useful second-opinion prompt

I finally found a good way to learn structured outputs that fail safely

The designing a useful agent handoff tutor prompt I saved

The testing API failure paths tutor prompt I saved

The context engineering for reliable agents tutor prompt I saved

The human review for automated workflows tutor prompt I saved

The making a safe dependency upgrade plan tutor prompt I saved