Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Effective context engineering for AI agents

anthropic.com

Post reply on HN
Print view View original

31–36 of 36 posts

Re: Effective context engineering for AI agents

#31

Post by grim_io »

krystofee wrote: post #13
SOLAR_FIELDS wrote: post #11

These companies all wax on about how important context engineering is yet not one of them has released acceptable tooling for end users to visualize and understand the context window as it grows and shrinks during a session. Best Claude code can do? Warn you when you hit 80% full

try /context in Claude Code

A very crude tool. A good start maybe, but it does not give us any information about the message part of the context, the one that matters.

We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt.

Re: Effective context engineering for AI agents

#32

Post by simonbw »

grim_io wrote: post #31
krystofee wrote: post #13

Earlier quoted context omitted.

try /context in Claude Code

A very crude tool. A good start maybe, but it does not give us any information about the message part of the context, the one that matters. We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt.

> We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt.

I actually think this is pretty useful information. It helps you evaluate whether an MCP server is worth the context cost. Similar for getting a feel for how much context certain tool uses use up. I feel like there's a way you can change the system prompt, and so that helps you evaluate if what you've got there is worth it also.

Re: Effective context engineering for AI agents

#33

Post by grim_io »

simonbw wrote: post #32
grim_io wrote: post #31

Earlier quoted context omitted.

A very crude tool. A good start maybe, but it does not give us any information about the message part of the context, the one that matters. We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt.

> We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt. I actually think this is pretty useful information. It helps you evaluate whether an MCP server is worth the context cost. Similar for getting a feel for how much context certain tool uses use up. I feel like there's a way you can change the system prompt, and so that helps you evaluate if what you've…

Sure, it's useful, once.

What we need is a way to manage the dynamic part of the context without just starting from zero each time.

Re: Effective context engineering for AI agents

#34

Post by SOLAR_FIELDS »

grim_io wrote: post #33
simonbw wrote: post #32

Earlier quoted context omitted.

> We can't really do much with the information that x amount is reserved for MCP, tool calling or the system prompt. I actually think this is pretty useful information. It helps you evaluate whether an MCP server is worth the context cost. Similar for getting a feel for how much context certain tool uses use up. I feel like there's a way you can change the system prompt, and so that helps you evaluate if what you've…

Sure, it's useful, once. What we need is a way to manage the dynamic part of the context without just starting from zero each time.

My theory is that you will never get this from a frontier model provider because as is alluded to in sibling thread the context window management is actually a good hunk of the secret sauce that makes these things effective and companies do not want to give that up

Re: Effective context engineering for AI agents

#35

Post by joshribakoff »

SOLAR_FIELDS wrote: post #11

These companies all wax on about how important context engineering is yet not one of them has released acceptable tooling for end users to visualize and understand the context window as it grows and shrinks during a session. Best Claude code can do? Warn you when you hit 80% full

Cursor has a circular progress bar for context usage.

Re: Effective context engineering for AI agents

#36

Post by kcartlidge »

Why are we hearing that "studies" have "uncovered the concept of context rot as the number of tokens in the context window increases"? It's obvious, and we've always known this.

Agents are stateless, hence the need for context. This means that all they know about the ongoing session is what's in that context (generally speaking). As the context grows any particular element within it becomes a smaller and smaller percentage of the whole. The LLM is not 'losing focus'; it's being diluted with more tokens. But then I suppose anthropomorphism comes naturally to a company named Anthropic, and 'losing focus' does make it sound more human.

They didn't need a study and article, but it likely contributes towards the mystique. Hence the use of phrases like "this results in n² pairwise relationships for n tokens" to make it sound more erudite and revelatory.

Post reply on HN