Search Results

Intent When you need to correct the way an agent performs an intermediate task in a process, turn the correction into a prompt that describes the isolated task. Complete the intermediate step by invoking the agent with just the extracted prompt, and use its o...

Intent Get the model to write down what you should have told it, for it to do the job correctly the first time. Motivation The code or text that an agent generates in response to a prompt often differs from your expectation, in small or large ways. One sour...

Intent Get the model to suggest multiple solutions to your problem. Compare benefits and drawbacks, costs and opportunities, and move forward with your preferred solution. Alternatively, create prototypes of the generated alternatives to explore the proposed ...

Intent Prompt the model to describe the code it creates. Generate reading guides that help you understand and modify the code. Generate instruction manuals that describe how to use the code, and that form the basis for acceptance tests. Motivation Relying o...

You Reflect Intent Review the transcript of your interaction with an agent, recall the tense moments, and plan to change your approach and mindset. Motivation Working with an AI coding agent can be fun, and it can be frustrating. At times, you can be surpr...

Chiron Codex makes the pattern language for AI-augmented software development available for free, under the terms of the Creative Commons CC BY-SA 4.0 licence. You can get early access to upcoming patterns, exclusive content, and support this book along with C...

Call Out Error Intent Tell the agent when it does something wrong, before you commit to the mistake. You don't need to describe the fix, just the problem. Motivation The code (or design, or plan) that a large language model generates can vary from your exp...

Clean Slate Intent Clear out the model’s context before continuing a task, or starting a new task. Motivation In transformer models, including large language models (LLMs), the self-attention layer transforms the input text stream first into token vectors,...

There are two companion repositories for this book. The Chiron Codex Agent Skills repository contains agent skills defined in a standard format that you can use with your AI-augmented coding assistant. Consult your tool's documentation for information on how t...

Re-Read Instructions Intent Tell the model to pay attention to its original prompt, and check if it’s digressing from the goal you set. Motivation Large Language Models (LLMs) display “completion bias”, in which they attempt to progress rapidly towards a s...