Materialize Blog

Engineers building context pipelines for agents all face the same conundrum: every system must decide where the necessary data transformation work gets done. Whether at read time, at write time, or somewhere in between, a cost must be paid in the form of developer effort, compute, or tokens — and many teams are learning the hard way that agentic systems can be very, very toke...

As we help engineering teams bring more and more context pipelines into production, it's gotten me thinking about a writing principle I've learned and relearned over the years: "be reader-serving."

The natural state of a writer is self-indulgence: put your thoughts down as th...

Large language models reason in language. So the natural way for an agent to ask the world for information is in words: describe the thing it needs, then search for it.

Keyword search and vector search are both versions of this. Keyword search lets the agent ask by exact terms: this ...