Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a 'harness profile' API in Deep Agents …

Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a "harness profile" API in Deep Agents as a solution. Profiles adjust system prompts, tool descriptions, names, can add/exclude tools, and more, each keyed on either the (1) provider (all model), (2) model only (within a provider set) We write about performance gains we've see here: https://www.langchain.com/blog/tuning-deep-agents-different-models Docs: https://docs.langchain.com/oss/python/deepagents/profiles @masondrxy $3900/yr saved is real money. catch is the switching cost is hidden: rewriting prompts, retesting tool use, dealing with model quirks. anyone done that migration cleanly?

Source: Harrison Chase (X) | 2026-05-11