What does it mean when an AI product becomes agentic?
When AI models get access to tools and can plan which ones to use and how, that's when things become agentic. Instead of "you ask something and the AI model responds", the pattern looks more like: you ask something, the model responds with its thinking, it calls a tool and shows you the outcome, it tells you what it thinks about the outcome, it calls another tool...
So in practice, an agentic AI product is one where the model doesn't just generate text — it makes plans, picks tools, configures them, and uses the results to decide what to do next. For instance our AI-powered workspace, Bench, has many tools it can use to retrieve information but also tools to fact-check data, do data analysis, generate Powerpoint decks, create images, and much more. In this type of product experience, people give AI models instructions. Then the models make plans, pick tools, configure them, and make use of the results to move on to the next step or not.
This is a meaningful shift from the earlier chat paradigm. While these kinds of agentic loops dramatically increase the capabilities of AI models, they look a lot more like a long internal monologue than a back and forth conversation between two people. That creates real design challenges — the reasoning traces, tool calls, and multi-step processes can overwhelm a simple chat interface, especially in narrow side panels.
And the trajectory keeps going. Quite quickly, AI products have transitioned from models behind the scenes powering features to people talking directly to models (chat) to models deciding which tools to use and how (agents) to agents orchestrating other agents. Once you have multiple agents coordinating together, you need entirely new UI patterns beyond the conversation thread. As I wrote in January 2026, agent orchestration — coordinating and verifying the work of multiple agents on unified tasks — is the current AI product design challenge.