Notion builds agent orchestration where teams and Claude collaborate on real work

Overview

Notion built agent orchestration on Claude Managed Agents, letting teams delegate work like coding, presentations and client deliverables directly from task boards, with teams able to kick off 30+ concurrent agent tasks at once. Claude also powers Notion's existing AI Writer, Autofill and Enterprise Search features, with prompt caching cutting Notion's infrastructure costs by 90% and latency by up to 85%. Enterprise customer Osaka Gas reports a 35% reduction in time spent searching for information, Remote saves an estimated 10 minutes per search across 300 daily queries, and dbt Labs saved over $35k annually by eliminating the need for separate AI tools.

The challenge

Notion users generate enormous amounts of knowledge - meeting notes, project docs, process guides, product specs - and before Claude, answering questions like troubleshooting steps or brand guidelines meant searching across pages manually or waiting for a colleague who knew where to look. As AI agents became capable of producing real work, a second problem emerged: most agent interactions were one-to-one on a single machine, with no visibility into what agents produced, no approval workflows, and no way for colleagues to step in and iterate together.

The solution

Notion integrated Claude Managed Agents, which can handle long-running sessions, manage memory, and deliver high-quality outputs over time, to let teams create a task, move it to "ready to start," and have Notion invoke a Claude session that picks up context from connected pages, design systems, API docs, and requirements documents. For engineering teams this means prototyping - a meeting note becomes action items and Claude writes the code; for non-technical teams Claude generates client deliverables like presentations, brand strategy decks, and sample websites. Completed tasks feed back into Notion's shared skills database so agent performance improves over time. Separately, Claude also powers Notion's existing AI Writer, Autofill, and Enterprise Search features, with prompt caching cutting infrastructure costs and latency.

Reported business value

Teams can kick off 30+ concurrent agent tasks from a single task board, with results routed to the right people for review. Prompt caching reduced Notion's infrastructure costs by 90% and latency by up to 85%. Osaka Gas estimates a 35% reduction in time spent searching for information, Remote saves an estimated 10 minutes per search across 300 daily queries, and dbt Labs saved over $35k annually by eliminating the need for separate AI tools.