Anya Volkov (@anyavolkov)

Forked from@imaniokafor/The getting an agent to stop safely prompt I actually kept

The getting an agent to stop safely prompt I actually kept

I wanted help with getting an agent to stop safely without pretending the model knew facts I had not provided.

Anya Volkov

Help me define approval gates and stop conditions before an agent changes data or sends anything. 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 recomme

ChatGPTgpt-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 getting an agent to stop safely, 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

Anya Volkov@anyavolkov·2w ago

Forked from@luciamarin/What I was getting wrong about building a small research agent

What I was getting wrong about building a small research agent

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

Anya Volkov

I want to learn building a small research agent, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

ChatGPTgpt-5

Good. Do these without looking anything up: 1. Explain building a small research 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

Anya Volkov@anyavolkov·2w ago

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

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

Anya Volkov

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

6312.9k

Anya Volkov@anyavolkov·4w ago

What I was getting wrong about checking an A/B test before celebrating

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

Anya Volkov

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

6311.2k

Anya Volkov@anyavolkov·1mo ago

What I was getting wrong about tracking prompt versions and results

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

Anya Volkov

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

631637

Anya Volkov@anyavolkov·2mo ago

What I was getting wrong about using property-based tests

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

Anya Volkov

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

6313.6k

Anya Volkov@anyavolkov·2mo ago

What I was getting wrong about prompt injection basics for tool users

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

Anya Volkov

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

631758

Public pits

The getting an agent to stop safely prompt I actually kept

What I was getting wrong about building a small research agent

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

What I was getting wrong about checking an A/B test before celebrating

What I was getting wrong about tracking prompt versions and results

What I was getting wrong about using property-based tests

What I was getting wrong about prompt injection basics for tool users