Show Notes
Tokens don't grow on trees. So what are you actually paying for when you pay for AI agents?
In this episode, recorded live in studio, we sit down with Sarah Sachs, Head of AI Engineering at Notion (ex Google, ex Robinhood), to unpack what it means now that Notion is becoming the AI infrastructure real businesses run on. It's a practical conversation for founders, ops leads, chiefs of staff and the accidental systems people who became responsible for how the business actually runs.
What we cover: The $500 AI bill: when agent cost is broken, and when it's the cheapest hire you'll ever make Use AI for reasoning, code for plumbing: why Notion Workers exist and when a token is the wrong tool for the job Permissioned context as the real moat, and Notion as the system of record where humans and agents collaborate Agent sprawl, vendor lock-in, and staying model optional as the frontier moves Observe in prod or live in a hallucination: watching what your agents actually do and actually cost
Timestamps: 00:00 Cold open: "we're over-indexing on tokens" 00:30 Intro and welcome, first episode live in studio 04:05 Sarah's story: Google, Robinhood, and into AI 07:30 What Head of AI Engineering at Notion actually does 08:55 Why Notion, and AI going from add-on to core 11:23 Two years, shipping fast, surfing the wave 13:30 The $500 bill: tokens don't grow on trees 18:38 Reasoning vs plumbing: stop spending tokens to move data 21:41 Workers vs Zapier and Make 23:00 Managed agents, permissioning and model interoperability 25:44 Agent SDK, API and Dev Day 26:30 Agent sprawl and Notion as the system of record 28:50 Vendor lock-in and model optionality 31:31 Building in the open, primitives and reception 34:53 Staying fresh: the hot yoga rule
Five takeaways for your business: Be deliberate about what you hand to AI. Once agents run real workflows, cost stops being abstract. Reserve AI for judgement and ambiguity. Redesign workflows around trusted, permissioned context instead of bolting AI onto the mess. Stay model optional. Keep your context and workflows in a system of record so you can swap models as the frontier moves. Observe agents in production so you catch hallucinations and runaway spend before they hit your bill.
Connect with Sarah Sachs: LinkedIn: linkedin.com/in/sarahmsachs X: x.com/sarahmsachs
Resources: Notion custom agents and Workers: notion.dev Notion MCP docs: developers.notion.com/guides/mcp/overview Claude agents in Notion: notion.com/partners/claude Notion Enterprise Search: notion.com/product/enterprise-search Notion AI Starter Kit: smoothops.consulting/Notion-AI-Starter-Kit-387dbd5e653480f8a275c1dc82b691ad
Connect with your hosts: Jerwin Parker Tim Jeffries
More from Notion in Practice
Flight Centre Travel Group's Matt Upton explains how his automation team uses Notion, Notion Workers and Notion AI skills at enterprise scale, and why nothing gets automated until the process behind it is fixed. Matt is Head of Automation and Innovation for Flight Centre's Asia Pacific corporate brands, leading a team of around 30 across five brands from India and the Middle East to Japan, Australia and New Zealand. Inside a 12,500-person business, the work ranges from multi-step customer onboarding automations to five-minute tasks done 500 times a day. He joins Tim Jeffries and Jerwin Parker on Notion in Practice to walk through how his part of the business made Notion its single source of truth. Information used to be spread across Confluence, Azure DevOps, SharePoint, OneDrive and local files, and nothing joined up. Flight Centre's corporate technology teams now have roughly 1,000 Notion seats. "I tell people if it's not in Notion, it doesn't exist," Matt says, and that rule is what made the change stick. Who this is for Operations, automation and technology leaders fitting Notion, Workers and Notion AI into an existing enterprise stack, and smaller teams who want the same discipline without the headcount. Why can't you automate a bad process? Because automation speeds up whatever process it runs on. Matt's team won't automate anything until it has been through a continuous improvement pass. As Tim puts it, automating a bad process just makes the chaos go faster and the mess grow quicker. How did Notion take hold at Flight Centre? Microsoft Loop opened the door. Notion had been in the business for years with only a handful of real users, and once teams saw collaborative documents working in Loop, a few people pointed out that Notion already did this at scale. How does Matt's team sync Smartsheet and Azure DevOps with Notion? With Notion Workers, small pieces of code deployed to Notion. Matt has seven or eight Smartsheets plus Azure DevOps syncing into Notion databases this way, set up in a short conversation with a coding tool and left to run without babysitting. Most Workers do one plain job like this. How do you build a Notion Worker? Start with a brief. Tim gets clear on the problem with Notion AI, then hands the brief and the Worker docs to Claude Code. His Worker was deployed and working within an hour. Do you have to migrate everything into Notion? No. Smartsheet and Azure DevOps stay where they are as the data layer, Notion becomes the context and reporting layer on top, and Workers keep the two in sync. The episode also covers Notion as "the Switzerland of AI", connecting different models and tools. Three actionable takeaways Run a continuous improvement pass before you automate anything. Leave your system of record where it is and use Notion Workers to sync the data into Notion. Start every Worker with a brief from Notion AI, then point a coding tool at the brief and the Worker docs. Resources mentioned Tim's article "You already have a digital operating system": https://smoothopsconsulting.substack.com/p/you-already-have-a-digital-operating
AI doesn't run in a vacuum. It runs inside a world: the platforms your work lives on, the records that hold the truth, the rules about what happens next. Most AI disappointment isn't a model problem. It's that there was never a world built around it.
In Episode 9 of Notion in Practice, Tim Jeffries and Jerwin Parker tackle the question on every Notion power user's mind: what will custom agents actually cost and is it worth it?
What happens when a former lawyer becomes Head of Operations at a scaling startup and decides to build an entire ops function using Notion agents?
In Episode 7 of Notion in Practice, Jerwin and Tim chat with Darja Nelson, Operating Partner at Bridgewest Ventures: New Zealand's leading deep tech venture capital firm that invests in early-stage deep tech companies.