Behind the Craft · Sunday, July 12, 2026
Jared Zoneraich, building in residence at Cognition, advises companies building AI agents to focus on leveraging the inherent progress of underlying models rather than relying on complex prompt engineering "hacks." He suggests that as models improve, the need for intricate prompt instructions will diminish, and companies should build their roadmaps accordingly.
“And my general high-level advice is to build your own roadmap in a way that assumes these hacks are going to be less and less important.”
“And that means that if you, if your whole company relies on this fancy prompt that says you need to reason and do this, the models are going to catch up.”