NotionAkshay KothariAnnouncement
What we learned during the Custom Agents beta
Summary
Notion’s Custom Agents launched in beta in February, and more than one million agents were created in two months before the feature moved out of beta. The post reports that teams scaled fastest when they treated agents as internal products, iterated with workflow experts, and shared operational knowledge rather than relying on engineers alone. Teams also redesigned end-to-end processes, such as Braintrust’s agent that scans competitor updates and Gong transcripts, updates a Notion sales one-pager, and flags relevant launches. Usage costs fell by up to 50%, partly through lighter models including Haiku 4.5 and GPT-5.4 Mini, which use up to 10× fewer credits, while new limits, dashboards, alerts, and pause controls support administration. From May 4, usage-based pricing applies through Notion credits at $10 per 1,000 credits for Business and Enterprise plans.
Context
Custom Agents launched in beta in February. Teams’ feedback focused on scaling agents, controlling usage, reducing costs, and supporting adoption across workflows without adding administrative work.
Approach / What changed
The release moves Custom Agents out of beta, introduces usage-based Notion credits, adds per-agent credit limits, workspace visibility, proactive alerts, and pause controls, and uses lighter-weight models and other system improvements to reduce costs.
Takeaways
Teams that scaled fastest started with people who understood the workflow, iterated against success criteria, and shared what they learned across agents.
Custom Agents were used to redesign recurring workflows, including Braintrust’s process for monitoring competitor updates and Gong transcripts, updating a sales one-pager, and flagging relevant launches.
Custom Agents became up to 50% cheaper to run; Haiku 4.5 and GPT-5.4 Mini use up to 10× fewer credits, and pricing is $10 per 1,000 monthly credits.
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.