Context engineering is sleeping on the humble hyperlink

Summary

As we all learn more about Context Engineering for LLMs (see Anthropic’s post for an excellent primer), we’ve identified a few important limitations. Conversations should be append-only to maximize cacheability. Models are typically more responsive to “fresh” context close to the end of the window. Models typically perform worse when overwhelmed with large amounts of context. With this in mind, a key tension comes into focus: the model needs access to all valuable context, BUT ONLY when that context is relevant to the task at hand. Context engineering is effectively the practice of finding ways to manage this tension. Popular solutions include: Retrieval Augmented Generation (RAG), which attempts to dynamically discover and load specific relevant context for the current query proactively. Subagents, which encapsulate specialized instructions and tools to avoid polluting the main thread. get_* Tools, which allow the model to proactively request information that it deems relevant using tool calls. There’s one technique that I feel is woefully underutilized by agents today: the humble hyperlink. The obligatory human analogy If you, a human, need to learn something without an LLM (let’s say something about an open source library), you will probably follow a trajectory that looks something like the following: Do a Google search for the topic you need to understand Click a relevant link to e.g. a docs page, read a high-level guide Depending on your needs, maybe Cmd+Click a few more pages or the reference docs to open them in new tabs to review Refer between your various open tabs as you complete your task Once you found an entrypoint through search, you were able to incrementally explore the topic through discovered links, filling your mental context with relevant information. We can do the same thing with LLMs. HATEOAS in the era of Agents The power of linked data is nothing new. Folks who have been building HTTP APIs for a long time might be familiar with HATEOAS, or “H...