I thought this entire premise was obvious? Does it really take an article and a venn diagram to say you should only provide the relevant content to your LLM when asking a question?
The new skill in AI is not prompting, it's context engineering
81–90 of 550 posts
Re: The new skill in AI is not prompting, it's context engineering
#82The only engineering going on here is Job Engineering™
Re: The new skill in AI is not prompting, it's context engineering
#83I wrote a bit about this the other day: https://simonwillison.net/2025/Jun/27/context-engineering/ Drew Breunig has been doing some fantastic writing on this subject - coincidentally at the same time as the "context engineering" buzzword appeared but actually unrelated to that meme. How Long Contexts Fail - https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho... - talks about the various ways in which longer…
Those issues are considered artifacts of the current crop of LLMs in academic circles; there is already research allowing LLMs to use millions of different tools at the same time, and stable long contexts, likely reducing the amount of agents to one for most use cases outside interfacing different providers. Anyone basing their future agentic systems on current LLMs would likely face LangChain fate - built for GPT-3,…
How would "a million different tool calls at the same time" work? For instance, MCP is HTTP based, even at low latency in incredibly parallel environments that would take forever.
Re: The new skill in AI is not prompting, it's context engineering
#84"Wow, AI will replace programming languages by allowing us to code in natural language!" "Actually, you need to engineer the prompt to be very precise about what you want to AI to do." "Actually, you also need to add in a bunch of "context" so it can disambiguate your intent." "Actually English isn't a good way to express intent and requirements, so we have introduced protocols to structure your prompt, and various k…
We should have known up through Step 4 for a while. See: the legal system
Re: The new skill in AI is not prompting, it's context engineering
#85Earlier quoted context omitted.
Those issues are considered artifacts of the current crop of LLMs in academic circles; there is already research allowing LLMs to use millions of different tools at the same time, and stable long contexts, likely reducing the amount of agents to one for most use cases outside interfacing different providers. Anyone basing their future agentic systems on current LLMs would likely face LangChain fate - built for GPT-3,…
Can you link to the research on millions of different terms and stable long contexts? I haven't come across that yet.
You can look at AnyTool, 2024 (16,000 tools) and start looking at newer research from there.
https://arxiv.org/abs/2402.04253
For long contexts start with activation beacons and RoPE scaling.
Re: The new skill in AI is not prompting, it's context engineering
#86There is no need to develop this ‘skill’. This can all be automated as a preprocessing step before the main request runs. Then you can have agents with infinite context, etc.
You need this skill if you're the engineer that's designing and implementing that preprocessing step.
Non-rhetorical question: is this different enough from data engineering that it needs it’s own name?
Re: The new skill in AI is not prompting, it's context engineering
#87I thought this entire premise was obvious? Does it really take an article and a venn diagram to say you should only provide the relevant content to your LLM when asking a question?
"Relevant content to your LLM when asking a question" is last year's RAG.
If you look at how sophisticated current LLM systems work there is so much more to this.
Just one example: Microsoft open sourced VS Code Copilot Chat today (MIT license). Their prompts are dynamically assembled with tool instructions for various tools based on whether or not they are enabled: https://github.com/microsoft/vscode-copilot-chat/blob/v0.29....
And the autocomplete stuff has a wealth of contextual information included: https://github.com/microsoft/vscode-copilot-chat/blob/v0.29....
You have access to the following information to help you make
informed suggestions:
- recently_viewed_code_snippets: These are code snippets that
the developer has recently looked at, which might provide
context or examples relevant to the current task. They are
listed from oldest to newest, with line numbers in the form
#| to help you understand the edit diff history. It's
possible these are entirely irrelevant to the developer's
change.
- current_file_content: The content of the file the developer
is currently working on, providing the broader context of the
code. Line numbers in the form #| are included to help you
understand the edit diff history.
- edit_diff_history: A record of changes made to the code,
helping you understand the evolution of the code and the
developer's intentions. These changes are listed from oldest
to latest. It's possible a lot of old edit diff history is
entirely irrelevant to the developer's change.
- area_around_code_to_edit: The context showing the code
surrounding the section to be edited.
- cursor position marked as ${CURSOR_TAG}: Indicates where
the developer's cursor is currently located, which can be
crucial for understanding what part of the code they are
focusing on.Re: The new skill in AI is not prompting, it's context engineering
#88I wrote a bit about this the other day: https://simonwillison.net/2025/Jun/27/context-engineering/ Drew Breunig has been doing some fantastic writing on this subject - coincidentally at the same time as the "context engineering" buzzword appeared but actually unrelated to that meme. How Long Contexts Fail - https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho... - talks about the various ways in which longer…
[flagged]
Re: The new skill in AI is not prompting, it's context engineering
#89If I need to do all this work (gather data, organize it, prepare it, etc), there are other AI solutions I might decide to use instead of an LLM.
What kind of alternative AI solutions might you use here?
Classifiers to classify things, traditional neural nets to identify things. Typical run of the mill.
In OpenAI hype language, this is a problem for "Software 2.0", not "Software 3.0" in 99% of the cases.
The thing about matching an informal tone would be the hard part. I have to concede that LLMs are probably better at that. But I have the feeling that this is not exactly the feature most companies are looking for, and they would be willing to not have it for a cheaper alternative. Most of them just don't know that's possible.
Re: The new skill in AI is not prompting, it's context engineering
#90There is no need to develop this ‘skill’. This can all be automated as a preprocessing step before the main request runs. Then you can have agents with infinite context, etc.
You need this skill if you're the engineer that's designing and implementing that preprocessing step.
Not at all, just ask the LLM to design and implement it.
AI turtles all the way down.