Deep research System Card
What changed
This report outlines the safety work carried out prior to releasing deep research including external red teaming, frontier risk evaluations according to our Preparedness Framework, and an overview of the mitigations we built in to address key risk areas.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- OpenAI o1 System Card
- OpenAI o3-mini System Card
- ChatGPT agent System Card
Sources
- Deep research System Card (openai-blog)primary