AI Product Engineer

You change one word in the system prompt and prompt caching breaks. Why?

Distinguish context engineering from prompt engineering in one practitioner's working definition

Translate the 'recipe vs kitchen' analogy into the prompt vs context engineering distinction

How does the ChatGPT style cross-session memory differ from within session rolling summary?

Compare the hard token budget with the soft quality budget of a context window

Why must image tokens be accounted for in the context budget separately from text tokens?

Compute the cost to embed 1 billion tokens with text-embedding-3-small

Compute the cost to embed 1B tokens with text-embedding-3-large via batch API

Which candidate does best of N sampling ship given these reward scores?

Explain why batch embedding APIs cost ~50% less, and when to use them

PremiumCompare best of N…

PremiumHow do you unwind…

PremiumWhat is the data…

Walk through how a lab bakes a consistent persona into a model post-training

PremiumWhen should you NOT…

Explain why context engineering emerged as a distinct discipline

Spot the bug in a safety tuned model that refuses benign coding requests

In a multi-turn conversation, when should you reset history, carry full state, or summarize?

How effective is the soft directive 'be brief' as an output length constraint compared to the hard max_tokens parameter?

You're enabling response_format=json_object (OpenAI) or strict structured output (Anthropic). What's the tradeoff vs prompting for JSON in prose?

Which activity belongs to context engineering rather than prompt engineering?

Which is the right choice between rolling summary and vector store memory for cross-session continuity?

Match each schema validation pattern to the production scenario where it fits best.

Identify every activity below that is context engineering rather than prompt engineering

Fill in the libraries used to measure context size before sending a call