Simon Willison’s Weblog

--- +++ @@ -32,7 +32,7 @@ ## Isn't this just vibe coding? -The term "vibe coding" was [coined by Andrej Karpathy](https://twitter.com/karpathy/status/1886192184808149383) in February 2025 - coincidentally just two weeks prior to the original release of Claude Code - to describe prompting LLMs to write code while you "forget that the code even exists". +The term "vibe coding" was [coined by Andrej Karpathy](https://twitter.com/karpathy/status/1886192184808149383) in February 2025 - coincidentally just three weeks prior to the original release of Claude Code - to describe prompting LLMs to write code while you "forget that the code even exists". Some people extend that definition to cover any time an LLM is used to produce code at all, but I think that's a mistake. Vibe coding is more useful in its original definition - we need a term to describe unreviewed, prototype-quality LLM-generated code that distinguishes it from code that the author has brought up to a production ready standard.

--- +++ @@ -30,6 +30,12 @@ Used effectively, coding agents can help us be much more ambitious with the projects we take on. Agentic engineering should help us produce more, better quality code that solves more impactful problems. +## Isn't this just vibe coding? + +The term "vibe coding" was [coined by Andrej Karpathy](https://twitter.com/karpathy/status/1886192184808149383) in February 2025 - coincidentally just two weeks prior to the original release of Claude Code - to describe prompting LLMs to write code while you "forget that the code even exists". + +Some people extend that definition to cover any time an LLM is used to produce code at all, but I think that's a mistake. Vibe coding is more useful in its original definition - we need a term to describe unreviewed, prototype-quality LLM-generated code that distinguishes it from code that the author has brought up to a production ready standard. + ## About this guide Just like the field it attempts to cover, *Agentic Engineering Patterns* is very much a work in progress. My goal is to identify and describe patterns for working with these tools that demonstrably get results, and that are unlikely to become outdated as the tools advance.

--- +++ @@ -5,6 +5,10 @@ What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since [at least the 1990s](https://simonwillison.net/2024/Oct/12/michael-wooldridge/) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: <p><center><strong>Agents run tools in a loop to achieve a goal</strong></center></p> + +The "agent" is software that calls an LLM with your prompt and passes it a set of tool definitions, then calls any tools that the LLM requests and feeds the results back into the LLM. + +For coding agents, those tools include one that can execute code. You prompt the coding agent to define a goal. The agent then generates and executes code in a loop until that goal has been met.

--- +++ @@ -4,7 +4,7 @@ What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since [at least the 1990s](https://simonwillison.net/2024/Oct/12/michael-wooldridge/) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: -<center><strong>Agents run tools in a loop to achieve a goal</strong></center> +<p><center><strong>Agents run tools in a loop to achieve a goal</strong></center></p> You prompt the coding agent to define a goal. The agent then generates and executes code in a loop until that goal has been met.

--- +++ @@ -4,7 +4,7 @@ What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since [at least the 1990s](https://simonwillison.net/2024/Oct/12/michael-wooldridge/) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: -**Agents run tools in a loop to achieve a goal** +<center><strong>Agents run tools in a loop to achieve a goal</strong></center> You prompt the coding agent to define a goal. The agent then generates and executes code in a loop until that goal has been met.

--- +++ @@ -2,7 +2,7 @@ What are **coding agents**? They're agents that can both write and execute code. Popular examples include [Claude Code](https://code.claude.com/), [OpenAI Codex](https://openai.com/codex/), and [Gemini CLI](https://geminicli.com/). -What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s (footnote) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: +What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since [at least the 1990s](https://simonwillison.net/2024/Oct/12/michael-wooldridge/) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: **Agents run tools in a loop to achieve a goal**

--- +++ @@ -1,6 +1,6 @@ -I use the term **agentic engineering** to describe the practice of developing software with the assistance of **coding agents**. +I use the term **agentic engineering** to describe the practice of developing software with the assistance of coding agents. -What are coding agents? They're agents that can both write and execute code. Popular examples include [Claude Code](https://code.claude.com/), [OpenAI Codex](https://openai.com/codex/), and [Gemini CLI](https://geminicli.com/). +What are **coding agents**? They're agents that can both write and execute code. Popular examples include [Claude Code](https://code.claude.com/), [OpenAI Codex](https://openai.com/codex/), and [Gemini CLI](https://geminicli.com/). What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s (footnote) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one:

--- +++ @@ -1,6 +1,6 @@ I use the term **agentic engineering** to describe the practice of developing software with the assistance of **coding agents**. -What are coding agents? They're agents that can both write and execute code. +What are coding agents? They're agents that can both write and execute code. Popular examples include [Claude Code](https://code.claude.com/), [OpenAI Codex](https://openai.com/codex/), and [Gemini CLI](https://geminicli.com/). What's an **agent**? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s (footnote) but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one: