BlogJobs

Blog

Thinking traces
The scaling dimensions of keyword search

The scaling dimensions of keyword search

Search has a new user: agents. Longer, programmatic queries change the performance math of keyword retrieval. Here we take a closer look at Block-Max WAND when querying is driven by agents.

Skip Everling
Skip Everling
Feb 6, 2026
Relevance
Mutually Assured Distraction

Mutually Assured Distraction

In agentic systems, retrieval is context injection. Better retrievers produce more convincing distractors; better reasoners trust those distractors more deeply. This is Mutually Assured Distraction.

Lester Solbakken
Lester Solbakken
Jan 30, 2026
Thinking traces
How we build a retrieval engine for agents

How we build a retrieval engine for agents

What happens when retrieval becomes verifiable? Agents stop just querying data and start improving their own context. This post breaks down how Hornet's schema-first, verifiable APIs enable self-optimizing systems built for agentic retrieval.

Skip Everling
Skip Everling
Jan 16, 2026
Thinking traces
The case for a new retrieval engine for agents

The case for a new retrieval engine for agents

The agentic shift is changing infrastructure. Agents need more than access to data; they need highly relevant context at scale. This article makes the case for a new retrieval engine built to power the next generation of agentic systems.

Jo Kristian Bergum
Jo Kristian Bergum
Oct 8, 2025

Stay in the loop

We're hard at work building Hornet. Sign up for updates and get a behind-the-scenes look and an opportunity to shape the future of retrieval for agents.

By subscribing, you accept our Privacy Policy.

BlogJobsPrivacy