The AI Record
And not all traffic is equal. It is a huge miss to send all of these to the latest Opus model. Some of these absolutely. Large scale data analysis, when you do it on Notion, will recommend Opus, right? When you triage an email inbox, if we're charging you to do that on Opus, we're ripping you off, and ourselves.

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is arguing that an AI product should route different kinds of requests to different models.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 10:24.

Checked against the source [ Grade B ] Said in the last year Sells AI tools

Filed under

Who is speaking

Sarah Sachs, Manages Notion's core AI capabilities and infrastructure team. Head of AI at Notion, which makes the Custom Agents she discusses; Notion sells AI features and has reason to present them favorably.

Notion sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-04).

Exact match in the whisper transcript (about 10:24), including 'we're ripping you off, and ourselves'. No captions are available to cross-check.

How to cite this passage

Sarah Sachs (Notion), “Notion's Token Town”, AI Engineer (YouTube), 2026-07-23, at 10:24. https://www.youtube.com/watch?v=-I5W5QVAT8E Archived at https://the-ai-record.com/passages/notion-not-all-traffic-equal-triage-email-opus-2026

More from the same source

Notion's auto model does this really well. We have state-of-the-art models available always. But we also have an auto model there at the top that handles about 75% of our traffic, right? We have the ability to switch between models and our product, and we also offer it to our customers … they have access to these models without vendor lock-in.

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is describing how Notion avoids depending on a single AI model provider.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 13:15.

  • 75% auto model traffic share, stated in the 2026 talk. Level not stated

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

That expertise on use cases is also very valuable to Frontier Labs. We find that our evals and our Early Access Program partnerships actually help us a lot with Frontier Labs and it's something that we can exchange instead of extraordinary large commits. And I don't think the discount is ever worth the lost in optionality.

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is describing what Notion offers AI model labs in place of large spending commitments; 'that expertise' refers to Notion's evaluations of models on its own use cases.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 14:39.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

And the last thing is CPUs over GPUs. We've recently launched something at Notion called Workers. I don't think that the GPU is necessary for every job. A lot of the jobs that we have are actually serving discrete pieces of code. Like you don't need an LLM to turn a CSV into a PDF. You don't need an LLM to talk to Notion tool calls if we have a CLI. You definitely don't need an LLM to do deterministic SQL queries. This is where people become token poor very quick.

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is closing a list of ways to lower AI costs.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 16:57.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

This is how it works today internally at Notion. Almost all of our polish and large feedback like this is actually coordinated through our software factories, both in terms of writing to the right teams and also having coding agents take the first step.

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is showing an example of internal product feedback at Notion that she says a colleague agreed she could post.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 22:12.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

We posted this review when we announced our partnership with parallel as our web search provider. If you were to look at just latency of a single call or just cost, parallel might not be the cheapest. But if you have expertise in entire web search trajectories, you'll see how it differs. The granularity of this eval is what lets us make the best decisions for our customers, because we understand all of the trade-offs on entire trajectories

Sarah SachsLeads engineering teams for AI, Notion · Leader, Notion

Context. Sachs is explaining how Notion compares model and tool providers, using its choice of a web search provider as the example.

Talk: Notion's Token Town, AI Engineer (YouTube), July 23, 2026, at 14:07.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/notion-not-all-traffic-equal-triage-email-opus-2026.json