OpenAI deep research use cases on Agents In Use cover Research & knowledge. These linked accounts describe what people asked the agent to do and the outcomes they reported.
Examples include “Deep research gathers an incomplete orchestrion location dataset” (OpenAI deep research).
In “Deep research gathers an incomplete orchestrion location dataset”, Willison inspected the trace and warned that the returned facts still needed verification.
Willison ran o4-mini-deep-research to find surviving orchestrions and return structured location records. The model used web search and code execution; he explicitly considered the resulting list incomplete and unverified.
Examples include “Deep research gathers an incomplete orchestrion location dataset” (OpenAI deep research). Open each entry for the steps and reported outcome.
Do people review OpenAI deep research's work before it acts?
In “Deep research gathers an incomplete orchestrion location dataset”, Willison inspected the trace and warned that the returned facts still needed verification.
What tasks do people use OpenAI deep research for?
The sourced entries here cover Research & knowledge. Examples include “Deep research gathers an incomplete orchestrion location dataset”.
Is it safe to delegate these tasks to OpenAI deep research?
These accounts document particular runs rather than establish safety for every task. The recorded human checkpoints are: In “Deep research gathers an incomplete orchestrion location dataset”, Willison inspected the trace and warned that the returned facts still needed verification. Review the linked source and permissions before trying an adapted prompt.