How Notion Built Agent Orchestration on Claude to Cut Costs 90%
Notion is a collaborative AI workspace used by millions of people, from individuals to Fortune 100 companies, where teams organize knowledge, manage projects, and now delegate real work to AI agents. After deploying Claude to power AI writing, search, and database features across the product, Notion extended to agent orchestration using Claude Managed Agents — letting teams kick off dozens of concurrent tasks from a single board and receive finished deliverables, from code to client presentations. Prompt caching alone cut Notion’s infrastructure costs by 90% and latency by up to 85%.
Impact
90%
Infrastructure cost reduction via prompt caching
Up to 85%
Latency reduction via prompt caching
30+
Concurrent agent tasks from single task board
35%
Information search time reduction for Osaka Gas
10 minutes across 300 daily queries
Time saved per search for Remote
$35,000+
Annual AI tool cost savings for dbt Labs
Challenge
Notion’s knowledge base was difficult to search without AI, and even after deploying AI features, agent interactions were isolated to single users with no shared visibility, approval flows, or collaborative interface for team-level agent work.
Solution
Notion integrated Claude for enterprise search, writing assistance, and database autofill, then built agent orchestration on Claude Managed Agents so teams could delegate complex tasks from shared task boards and receive deliverables including code, presentations, and websites.
Tools & Technologies
What Leaders Say
“We want Notion to be the best place for teams to work with agents and get things done. We integrated Claude Managed Agents, which can handle long-running sessions, manage memory, and deliver high-quality outputs over time, to make that possible.”
“We saw that customers were willing to jump through hoops to have a native experience of agents within Notion, and Claude was the one people wanted most.”
“Prompt caching makes Notion AI faster and cheaper, all while maintaining quality. This enables us to create a more responsive user experience for our customers.”
“We’ve found that Opus 4.6 excels at interpreting what users actually want, producing shareable content on the first try.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
Notion started as a workspace where knowledge lives: meeting notes, product specs, process guides, and project docs. As the product grew to serve millions of users including major enterprises, the first AI challenge was making all of that knowledge findable. Customer support teams needed troubleshooting steps on demand. Sales reps needed to find process documentation without waiting. Product designers needed brand guidelines without searching manually. Claude became the engine for Notion’s Enterprise Search, AI Writer, and Autofill features, helping users query their entire workspace in natural language and get answers drawn from connected apps and internal documents.
But as AI agents became capable of producing real work, a second and more ambitious challenge emerged: most agent interactions were one-to-one, a single person with a single agent on a single machine. There was no shared visibility, no approval workflows, no way for colleagues to step in and review or iterate together. Notion wanted to bring agents into its collaborative model. As Product Manager Eric Liu described it: powerful agents were being built for every vertical slice of work — why not bring them all into Notion?
Notion selected Claude Opus for its agent layer after testing multiple providers. Co-founder Simon Last cited Claude’s response quality and instruction-following as decisive, especially for use cases where tone and feel matter. AI Lead Engineer Sarah Sachs highlighted Opus 4.6’s ability to interpret intent accurately and produce shareable outputs on the first attempt. Claude Managed Agents provided the infrastructure for long-running sessions, memory management, and high-quality outputs over time — without requiring Notion to build a custom agent runtime.
The result is a workflow that turns Notion’s existing task boards into an agent dispatch system. A team creates a task, moves it to “ready to start,” and Notion invokes a Claude session that picks up context from connected pages, API docs, design systems, and product requirements. For engineering teams, this produces prototypes and code changes. For non-technical teams, it generates presentations, brand strategy decks, and sample websites. Liu described kicking off 30 prototype tasks at once and returning to find them all completed. On the infrastructure side, prompt caching cut Notion’s costs by 90% and latency by up to 85% across the millions of daily AI interactions.
The measurable enterprise impact has been significant. Osaka Gas reduced time spent searching for information by 35%. Remote saves an estimated 10 minutes per search across 300 daily queries. dbt Labs eliminated the need for separate AI tools, saving over $35,000 annually. For new employees, the AI assistant is used 10-20 times daily in their first weeks. Notion is now building toward a workspace where the same interfaces humans use for collaboration — task boards, suggested edits, version history — also serve as the interface for directing agent work.