Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle
Sep 18, 2026AI Engineer
Summary
This talk presents a novel seven-layer harness engineering framework for agents, arguing that control and memory are paramount, not just the language model itself. It highlights the critical role of physical memory location, advocating for databases over files for transactional consistency in parallel agent execution. The concept of 'Umwelt' is introduced to define an agent's perceptual lens, and 'skill promotion' is proposed as a mechanism for workflow optimization and retirement. A hysteresis variable for controlling model patience is also detailed.
More from the Agent Memory and Harness Engineering trail
- From Context to Memory: Your Agents Need a Real Memory Layer — Anders Swanson, Oracle
- Designing CLIs for Agents, Not Humans — Pedro Lopez, Airbyte
- Building on the Codex Harness — Dominik Kundel, OpenAI
- Stop Prompting — Greg Pstrucha, Sentry
- Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya