I'd start with something research focused like Undermind or Elicit. Although I don't think that the author is comfortable with using a tool that isn't produced by the model lab.
The planning model for tool use sounds something like CaMeL, which someone should really try implementing in a product.
CaMeL, from "Defeating Prompt Injections by Design", <a href="https://arxiv.org/abs/2503.18813" rel="nofollow">https://arxiv.org/abs/2503.18813
See also "CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents", <a href="https://arxiv.org/abs/2601.09923v1" rel="nofollow">https://arxiv.org/abs/2601.09923v1
Leynos · · focus · HN ↗
The planning model for tool use sounds something like CaMeL, which someone should really try implementing in a product.
troelsSteegin · · focus · HN ↗
See also "CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents", <a href="https://arxiv.org/abs/2601.09923v1" rel="nofollow">https://arxiv.org/abs/2601.09923v1