Search Results

Intent Prompt the model to list the assumptions inherent in your prompt, or missing information that’s needed to complete your task, and describe its resolution—or ask you for input. Motivation Software engineers spend significant time on discovering and re...

Intent Don't try to fix everything in one sitting. Tell the model to record open questions so you can focus on a single problem. Motivation Getting accurate results from an LLM-augmented code assistant can feel like an exercise in detailed specification. Yo...

Trust the Tests Intent Trust the tests, and not the agent. Create external quality checks, and ensure that the software you create passes those checks even when the agent reports that it’s “done”. Motivation Software engineers organize quality-checking wor...

Replace Vibes with Tools Intent When a part of your problem is well-specified and deterministic, don’t use a generative approach to try to find a solution. Create a reusable, reproducible tool that your generative assistant can use. Motivation Not all prob...

Build a Model Intent Prompt the language model to build a prototype of your solution. Explore the prototype, then Start Over and incorporate your findings. Motivation No description of a software system—be it a user prompt for a coding assistant to follow,...

Model Reflects Intent Ask the model to identify important changes or inflection points in your interaction. Prompt it to generate suggestions to improve your work with the assistant in future interactions. Motivation While you’re working with your coding a...

Bake Off Intent Give the same prompt to multiple assistants—or to multiple instances of the same assistant. Compare the results and identify whether you need to change your tools, your model, or your prompt. Motivation A coding assistant comprises multiple...