The decisions that are hard to reverse, written up properly. Every claim links to the component or the published source behind it.
Prompt injection has no known complete fix. The practical defence is layered: detect what you can, then remove the attacker's payout with sandboxing and default-deny egress. A guide for teams putting agents in front of untrusted content.
Agent memory vendors publish benchmark scores that independent re-runs contradict by up to 30 points. A guide to what memory actually does, when you need a product rather than a table, and how to read the numbers.
A complete AI agent architecture where no component calls out to a third party — for regulated industries, data-residency requirements and air-gapped environments. Every layer, with the open-source option that fills it.
A harness is the loop that runs your agent — reading files, calling tools, managing sessions and approvals. Understanding the difference between a harness and a framework is the first architectural decision, and most guides skip it.
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/guides