Until today, Deep Agents shipped with a single set of prompts, tools, and middleware aimed to work well across all Large Language Models. With the launch of harness profiles, you can now control these parameters on a per-model basis.
Now in Deep Agents: Harness Profiles. https://lnkd.in/eCsFUueU ✅ Model-specific profiles to adjust prompts, tools, and middleware. 📦 Profiles for OpenAI, Anthropic, and Google models out of the box. 📈 A 10–20 point jump on a subset of tau2-bench over the default harness.
Seeing the full orchestration layer really highlights why building reliable agents is so much harder than just writing a good prompt. Breaking it down into routers and planners makes the whole process feel a lot more tangible for anyone trying to scale these systems.