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 forOperations, 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 takeawaysRun 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 mentionedTim's article "You already have a digital operating system": https://smoothopsconsulting.substack.com/p/you-already-have-a-digital-operatingConnect with Matt Upton.Connect with Jerwin Parker.Connect with Tim Jeffries.

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.Season 1 of Notion in Practice was about AI inside Notion. Season 2 is about building the bigger world that surrounds it: the integrations, automations and structure that decide whether your AI has anything worth thinking about.Tim Jeffries and Jerwin Parker open the season with the frame they use across every build: a digital operating system has four parts, the world, the work, the players and the rules. Inside that world, work splits into deterministic work, where you know the inputs and the outputs and can write the rule, and judgement work, where something has to think. This isn't automation versus AI. It's how you build somewhere both of them can do their best work.Build the world properly and the two compound each other: the plumbing keeps the records true, and the judgement runs on something worth reading. Skip it, and you have a clever model guessing in the dark, and paying a premium to move an email.In this episode:Why most businesses run an archipelago of disconnected platforms, and what that costs in duplicated truthThe two halves of every job (plumbing and judgement), and the three kinds of player that can now do eitherOnboarding a referral, split task by task, so you can see exactly where the line fallsWhy deterministic work is cheap, precise and loud when it fails, and why that's a featureA live look at the email worker that reads a whole Google Workspace domain and files every client email against the right projectWhat it means when the system knows more about a job than any individual on the teamHow small a worker should be, and why one that does five things becomes a mess fastThe run log: 10,000 records, and why observability came before the fleetReal numbers: about a dollar a meeting for deep AI follow-up, versus US$1.20 for 741 automation runsWhat breaks, why bridges collapse, and debugging a worker with a coding agent an hour before recordingThree actionable takeaways:Break the job into tasks before you choose which player should perform it. Label each task plumbing or judgement, then cast the cheapest player that can do it well.Keep each worker small and single-domain. Same process, several triggers is fine. Different workflows in one worker is a mess waiting to happen.Build the log before you build the fleet. If you can't see what ran overnight, you don't have a system, you have a hope.Resources MentionedSeason 1 finale with Notion's Head of AINotion workers / developer platformAI / Personal Agent Starter Kit: https://www.smoothops.consulting/notionaistarterkitSubstack: https://smoothopsconsulting.substack.com/Coming up this season: the businesses actually running this. Law firms, designers, film people. What worked, what didn't, and what it cost.Who this is for: founders, operators and consultants who have the AI part working and now need the connective tissue underneath it to be reliable, cheap and visible.👉 Subscribe wherever you get your podcasts, or on YouTube @NotioninPractice.

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 makeUse AI for reasoning, code for plumbing: why Notion Workers exist and when a token is the wrong tool for the jobPermissioned context as the real moat, and Notion as the system of record where humans and agents collaborateAgent sprawl, vendor lock-in, and staying model optional as the frontier movesObserve in prod or live in a hallucination: watching what your agents actually do and actually costTimestamps:00:00 Cold open: "we're over-indexing on tokens"00:30 Intro and welcome, first episode live in studio04:05 Sarah's story: Google, Robinhood, and into AI07:30 What Head of AI Engineering at Notion actually does08:55 Why Notion, and AI going from add-on to core11:23 Two years, shipping fast, surfing the wave13:30 The $500 bill: tokens don't grow on trees18:38 Reasoning vs plumbing: stop spending tokens to move data21:41 Workers vs Zapier and Make23:00 Managed agents, permissioning and model interoperability25:44 Agent SDK, API and Dev Day26:30 Agent sprawl and Notion as the system of record28:50 Vendor lock-in and model optionality31:31 Building in the open, primitives and reception34:53 Staying fresh: the hot yoga ruleFive 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/sarahmsachsX: x.com/sarahmsachsResources:Notion custom agents and Workers: notion.devNotion MCP docs: developers.notion.com/guides/mcp/overviewClaude agents in Notion: notion.com/partners/claudeNotion Enterprise Search: notion.com/product/enterprise-searchNotion AI Starter Kit: smoothops.consulting/Notion-AI-Starter-Kit-387dbd5e653480f8a275c1dc82b691adConnect with your hosts:Jerwin ParkerTim Jeffries

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?With usage-based pricing for Notion custom agents rolling out, Tim and Jerwin discuss what stays free (personal agent / Nosy, enterprise search, meeting notes) and what gets metered (custom agents). They walk through the three-layer model Smooth Ops uses to architect AI inside Notion: Agents, Skills, and Guides and why this structure keeps costs predictable while making your AI dramatically smarter.In this episode:What you actually pay for in Notion AI (and what's free)The three-layer model: agents as orchestration, skills as SOPs, guides as reference materialA real example: how Tim's calendar-sync custom agent costs ~$150 AUD/month and why it earns its keepHow picking the right LLM (Haiku vs Sonnet vs Opus) per agent changes your billWhy clean databases are the non-negotiable foundation before any AI workWhen to reach for Claude + Notion MCP instead of staying inside NotionMeet Al, Tim's chief-of-staff personal agent, and how he handles every domain via dynamic skill-matchingWhy every skill needs an owner and a verification cadence: governance, not just authoringThree actionable takeaways:Start with your data structure: clean, well-named databases are the foundation everything else relies on.Set up your personal agent (Nosy) with strong custom instructions before you build a single custom agent.Build skills as separate, reusable pages and keep custom agents lightweight: they should orchestrate, not contain logic.Who this is for: New, Intermediate-to-advanced Notion users, consultants and operators who want to use Notion AI without burning through credits: especially anyone planning their custom agent strategy ahead of usage-based pricing.🎁 Tim's special offer for listeners: If you're struggling to set up your personal agent instructions, reach out to Tim directly: he's giving away a free instructions starter kit to anyone who asks. (Mentioned around the takeaways at the end of the episode.)📚 Further reading: Tim's Substack article Structure is the Strategy: open.substack.com/pub/smoothopsconsulting👉 Subscribe wherever you get your podcasts and on YouTube @NotioninPractice for weekly real-world Notion + AI workflows.

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 this episode, George from Calcs joins Tim and Jerwin to share how she's using Notion AI agents to automate document hygiene, recruitment, onboarding, OKR reporting, and even Slack channel governance. After scaling Linktree from 40 to 160 people on Notion, George knows what foundational building blocks matter and why they matter even more in the age of AI.We dig into:🔹 The AskOps Agent - A Slack-based bot that answers operational questions, surfaces missing policies, and tracks how often questions are asked so the team knows where documentation gaps exist.🔹 Database Hygiene at Scale - How George uses verification agents that run weekly checks on document ownership, last-edited dates, and software renewals - so nothing falls through the cracks.🔹 Recruitment Without a TA Tool - Calcs runs its entire applicant tracking process inside Notion: Zapier brings in applications, a Notion agent manages candidate progression, and all communication is captured in one profile.🔹 OKR Summaries on Autopilot - A fortnightly agent scans the scorecard, summarises what's on track and off track, and posts the update to Slack - a task George used to do manually in slide decks.🔹 The Agent Org Chart Problem - As the number of agents grows, George shares what's missing: visibility into what agents are doing, better failure notifications, and a way to see the orchestration layer.🔹 AI Tool Sprawl - Notion agents vs. Slack AI vs. Claude vs. Zapier: how a small company decides where to build without paying for everything.Three Actionable Takeaways:Build agents to meet people where they work - if your team lives in Slack, bring Notion's power to them there.Invest in your foundational context layer first - clean databases with ownership, verification, and hygiene agents make everything else (including AI) work better.Experiment now, structure later - the free agent window is closing, so build, test, and learn before pricing forces discipline.Resources Mentioned:Notion · Calcs · Linktree · Slack · Linear · Claude · Zapier 🎧 This episode is for ops leaders, founders, Notion power users, and anyone building AI-powered workflows in a small team.