Deep Research with Agents

I’ve been thinking about the new “Deep Research” capabilities released this week. This fundamentally changes the way we have been interacting with AI for the past few years.

It feels like the first serious admission that chat is a poor interface for complex work as it needs constant supervision. It creates friction when the task itself needs focus, time, and synthesis.

The newer agentic models (Gemini’s latest updates, GPT-5.2) change that dynamic.

You give them a goal. They go away for minutes or hours. They return with a concrete artifact you can review, refine, or ship.

This is something which all agentic coding tools are integrating as we speak.

Prompting also changes in this world.

It becomes less about clever wording, more about clear intent, constraints, and the desired state.

It’s about a different workflow altogether.

If your 2026 roadmap is still centered around “chatbots,” there’s a good chance you’re optimizing for a workflow that’s already becoming legacy.