NotionArya SajjalaExplainer
How Notion built a Custom Agent workflow to keep Academy content current
Summary
Notion built a Custom Agent workflow in Notion to keep Academy content current as product changes ship. The system uses two databases: an Academy library mapping the curriculum and a maintenance-tasks database tracking work from each product change. Two Custom Agents handle the work: the Academy Drift Agent compares launch docs against the library and flags affected lessons, while the Academy Drafting Agent drafts approved updates using editorial guidance. MCP connects the workflow to Parta, the e-learning platform, so approved content moves into final QA without manual hand-off. The loop includes human review checkpoints before scope approval and before content moves into Parta, reducing content drift and giving the team hours back each week.
Context
Notion Academy gets roughly 1.4 million visits a month and tracks more than 30 product changes monthly that could affect its learning content. The team previously traced each launch manually across the Academy to find affected lessons, a process that did not scale as the product changed.
Approach / What changed
The system uses two Notion databases (an Academy library mapping content and a maintenance-tasks database tracking work) plus two Custom Agents. The Academy Drift Agent reads a new launch doc, compares it with the Academy library, and creates tasks with recommendations and evidence for affected lessons. A reviewer approves the scope, then the Academy Drafting Agent reads the launch context and existing lesson, drafts the update using editorial guidance, and stages it for review. After approval, the same agent uses MCP to move the update from Notion into Parta for final QA and publishing.
Takeaways
Content drift is the gap between a changing product and the content that explains it; Notion Academy organizes lessons around learner goals, so a single product change can affect multiple lessons in different ways.
The workflow uses two Custom Agents: the Academy Drift Agent identifies affected lessons and creates scoped tasks, while the Academy Drafting Agent drafts approved updates using editorial guidance and stages them for publishing.
Human review is built in at two checkpoints—before scope approval and before final copy moves into Parta—so mistakes are caught where they would be hardest to undo.
FAQ
How does the Academy Drift Agent decide which lessons need updating?
The Academy Drift Agent reads a new launch doc and compares it with the Academy library, which inventories each course and lesson along with metadata. It flags lessons that could be affected and explains why each one was surfaced, then creates a task with a recommendation and the evidence behind it.
What role does MCP play in the workflow?
MCP gives the agents controlled access to Parta, the e-learning platform, so they can inspect live lessons and stage approved changes. The Academy Drafting Agent uses MCP to move the approved update from Notion into Parta for final quality checks and publishing.
How does the system handle content maintenance over time?
The system turns content maintenance into a loop that requires only editorial oversight. Every review decision is folded back into the agents, so fewer cases need human judgment over time, and the team can focus on helping customers learn and get more from Notion.
Source and freshness
- Source
- notion.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.