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

1. Run a continuous improvement pass before you automate anything.
2. Leave your system of record where it is and use Notion Workers to sync the data into Notion.
3. 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

Connect 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 truth
• The two halves of every job (plumbing and judgement), and the three kinds of player that can now do either
• Onboarding a referral, split task by task, so you can see exactly where the line falls
• Why deterministic work is cheap, precise and loud when it fails, and why that's a feature
• A live look at the email worker that reads a whole Google Workspace domain and files every client email against the right project
• What it means when the system knows more about a job than any individual on the team
• How small a worker should be, and why one that does five things becomes a mess fast
• The run log: 10,000 records, and why observability came before the fleet
• Real numbers: about a dollar a meeting for deep AI follow-up, versus US$1.20 for 741 automation runs
• What breaks, why bridges collapse, and debugging a worker with a coding agent an hour before recording

Three actionable takeaways:

1. 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.
2. Keep each worker small and single-domain. Same process, several triggers is fine. Different workflows in one worker is a mess waiting to happen.
3. 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 Mentioned

• Season 1 finale with Notion's Head of AI
• Notion workers / developer platform
• AI / Personal Agent Starter Kit: https://www.smoothops.consulting/notionaistarterkit
• Substack: 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 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:

1. Be deliberate about what you hand to AI. Once agents run real workflows, cost stops being abstract.
2. Reserve AI for judgement and ambiguity.
3. Redesign workflows around trusted, permissioned context instead of bolting AI onto the mess.
4. Stay model optional. Keep your context and workflows in a system of record so you can swap models as the frontier moves.
5. 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

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 material
• A real example: how Tim's calendar-sync custom agent costs ~$150 AUD/month and why it earns its keep

  How picking the right LLM (Haiku vs Sonnet vs Opus) per agent changes your bill

• Why clean databases are the non-negotiable foundation before any AI work
• When to reach for Claude + Notion MCP instead of staying inside Notion
• Meet Al, Tim's chief-of-staff personal agent, and how he handles every domain via dynamic skill-matching
• Why every skill needs an owner and a verification cadence: governance, not just authoring

Three actionable takeaways:

1. Start with your data structure: clean, well-named databases are the foundation everything else relies on.
2. Set up your personal agent (Nosy) with strong custom instructions before you build a single custom agent.
3. 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:

1. Build agents to meet people where they work - if your team lives in Slack, bring Notion's power to them there.
2. Invest in your foundational context layer first - clean databases with ownership, verification, and hygiene agents make everything else (including AI) work better.
3. 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.

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.

Darja shares how her team of six uses Notion to manage a pipeline of 300+ pitches a year, support five active portfolio companies, and produce investor reporting all while she spends six to seven hours a day in meetings.

This episode covers the real, practical impact of AI meeting notes, how custom agents are starting to automate pipeline updates, and why the skills that matter for new hires are fundamentally changing.

Three Actionable Takeaways

1. Own your system as a team: Don't treat your Notion workspace as a one-off project. Hold regular sessions to review, improve, and build onboarding guidance - the team that owns the system gets the most out of it.
2. Hire for wisdom, not just analysis: AI handles the traditional grind. Look for people who can critically evaluate output, ask the right questions, and make good decisions with the information AI surfaces.
3. Make meetings your institutional memory: Store meeting notes centrally, make them searchable, and use custom agents to automate follow-up - so nothing falls through the cracks, even on six-call days.

If you enjoyed the episode, subscribe for more real-world Notion workflows. More deep dives into custom agents, onboarding workflows, and how teams are building governance around their Notion systems.

Resources mentioned

• Tim Jeffries' article: Why Your Notion Workspace Design Matters for AI
• Notion AI Meeting Notes
• Notion Custom Agents
• Notion Skills (new AI feature in workspace settings)
• Hosts
  • Jerwin Parker Roberto: LinkedIn: http://www.linkedin.com/in/jerwinparker
  • Tim Jeffries: LinkedIn: https://au.linkedin.com/in/timjeffries

Custom Agents are the next step for Notion AI: not just answering questions, but running real workflows in the background.

In this hosts-only deep dive, Tim Jeffries and Jerwin Parker break down what Custom Agents are, how they differ from the “regular” Notion AI experience, and how to think about implementing them safely in a team.

Tim and Jerwin walks through the Custom Agents interface, including triggers, activity logs, permissions, and integrations, then shares a set of practical agents Smooth Ops has been using to reduce admin overhead and increase project context.

• Custom Agents vs Notion AI: what changes when AI can run autonomously
• Personalized instructions and playbooks: the foundation for consistent outputs
• Triggers: schedule-based runs, property-based triggers, and Slack/Calendar/Mail possibilities
• Permissions and governance: what the agent can access, and how sharing agents can extend access
• Real examples (Tim): meeting follow-up, Slack context capture, email-to-CRM logging, lead intake automation, and project status updates
• Real example (Jerwin @ TrustOnCloud): a meeting triage custom agent for a marketing leader to capture actions, track accountability, and keep momentum after internal calls
• Ambient context: why Tim rebuilds a daily context page overnight so AI stays “stateful” across conversations

1. Takeaway #1: Start with personalized instructions + playbooks before you build agents.

   Build a reliable “baseline assistant” first, then turn repeatable playbooks into agents once you trust the workflow.

2. Takeaway #2: Treat agents like employees: define the job, grant minimal access, then audit regularly.

   Good outcomes come from clear instructions, tight permissions, and reviewing activity logs.

3. Takeaway #3: Use agents to capture context automatically (meetings, Slack, email) so work stays “stateful.”

   The more structured context lives in Notion, the less the AI has to guess, and the better the outputs become.

• Hosts:
  • Tim Jeffries — Website · LinkedIn · Instagram · YouTube
  • Jerwin Parker — Website · LinkedIn · Instagram · YouTube

• Resource Tim mentioned (Episode gift): https://www.notion.com/templates/how-to-build-ai-playbooks

Operators, consultants, founders, and Notion power users who want to automate repeatable work, reduce cognitive load, and keep project context up to date without relying on memory.

Subscribe for more practical episodes on building real systems in Notion, with workflows you can copy and adapt.

In Episode 5 of Notion in Practice, Jerwin and Tim sit down with Nick Tucker. He is an experienced management consultant, psychologist and people leader, driven by a desire to make the world a better place to work.

Nick shares how he uses Notion as the operating system for his consulting practice: a “second brain” that captures context, keeps the admin tidy, and makes work easier to deliver with partners.

This is not a hype episode. It’s a practical look at where AI is genuinely creating leverage, what still needs human judgment, and why adoption remains the hard part.

• Nick’s background (strategy, culture change, organisational psychology) and how he discovered Notion
• Notion as a “second brain” that “keeps receipts”: admin + context + delivery
• Why AI challenges the traditional consulting leverage model (and what replaces it)
• The 4 workflow shifts: project management, meeting notes, pipeline/commercials, and IP management
• Using AI for feedback/coaching via custom rubrics (discovery calls)
• Adoption is still the hardest part: tools get deployed, but usage stays low
• AI as a thinking partner (mental models + frameworks like Pyramid Principle)
• What surprised Nick: inconsistency (“hungover graduate” days)
• What’s next: “get the reps in” and keep feeding context as the system grows

1. AI changes the consulting advantage: The differentiator moves from producing repeatable “deck work” to using good judgment. The real skill is deciding what’s useful from endless AI output.
2. Notion works best as an operating system (not another tool): A flexible “second brain” that keeps your delivery, context, and admin in one place, built around how you think and work.
3. Four workflow upgrades drive leverage: Project management (single source of truth), meeting capture (searchable conversations), pipeline/commercial tracking (accountability), and IP management (drafting guides faster).
4. Use AI for feedback and coaching, not just tasks: Call-review rubrics and automatic retros help people improve without the social friction of “I’ve got feedback for you.”
5. Adoption is the real bottleneck: The tools can be there, but if people do not use them, nothing compounds. Systems that make work easier win adoption.

• Nick Tucker on LinkedIn: https://au.linkedin.com/in/nick-tucker-
• Buoyant Partners (company): https://www.buoyant.partners/
• Hosts
  • Jerwin Parker Roberto: LinkedIn http://www.linkedin.com/in/jerwinparker
  • Tim Jeffries: Instagram https://au.linkedin.com/in/timjeffries
• AI call-review rubrics (concept): https://smoothopsconsulting.notion.site/AI-Thinking-Partner-Playbook-Setup-Guide-1c0149969f724589a840a541fa434a75?source=copy_link (AI Thinking Partner Playbook, Setup Guide)
• Pyramid Principle (framework mentioned)

Daniel Taylor runs a criminal and child protection law firm in Victoria, Australia, handling 800+ clients a year. When every client is in crisis and needs to be heard, there's no room for admin overhead or missed details.

In this episode, Daniel shares his journey from paper files and mega spreadsheets to a fully systematized Notion workspace that's evolved over 6+ years with consultant Tim Jeffries and Jerwin Parker.

We explore:

From Paper to Digital:

• How Daniel discovered Notion through a fellow law firm owner
• The challenge of moving from Google Drive + spreadsheets to one source of truth
• Change management: navigating the cycle of denial, anger, bargaining, and acceptance with staff

AI Transcription as a Game-Changer:

• Why clients come to lawyers to be heard, not lectured
• Using live transcription to stay fully present in client conversations
• Drafting letters that reflect clients' own words back to them ("98% done" from the transcript)

The Next Frontier: Custom Agents:

• Automated file audits that catch billing gaps and missing documents
• Intake and outtake processes that run in the background when you're too busy
• Training junior lawyers through AI feedback on client interview transcripts

Three Actionable Takeaways:

1. AI lets you be more human, not less. Transcription handles admin so you can focus on listening.
2. The client's words land better than yours. Draft from transcripts using their language.
3. Agents will catch the stuff that falls off when you're busy. Automate the tasks that should happen but don't.
   
   🎁 Free Resource from This Episode 📞

   Call Review Playbook — Your Free Gift

   Daniel's workflow for using AI to review call transcripts inspired us to create a ready-to-use playbook you can adapt for your business.

   ✅ A structured framework for defining your own review criteria

   ✅ Three different approaches to developing criteria

   ✅ AI-ready instructions that turn transcripts into actionable coaching feedback

   ✅ Real examples across different contexts (sales, support, consulting)

   Link: https://www.notioninpractice.com/Call-Review-Playbook-Setup-Guide-2fbdbd5e653480898b60d4adc27db738?source=copy_link

Show Notes

Resources Mentioned:

Guest: Daniel Taylor Criminal and child protection law firm owner, Victoria, Australia

Subscribe to Notion in Practice:

🎵 Spotify • Apple Podcasts • YouTube

Contact:

💼 LinkedIn

🌐 www.notioninpractice.com

🪄[email protected]

In this episode of Notion in Practice, Tim and Jerwin sit down with Matthew Shaw and Dave Merriweather from Ionix Digital to unpack how they rebuilt their entire sales-to-delivery process on Notion and Notion AI.

Ionix work with time-poor clients across construction, infrastructure, mining, rail and services – people who can close deals in a room but hate the admin it takes to get there. Traditionally, their sales team would run long discovery calls and pitches, then try to “re-say” everything in a handover meeting with copywriters, designers and developers.

Important context slipped through the cracks, projects dragged out, and rewrites piled up.

Now, every discovery conversation is captured as a transcript, stored in Notion, and becomes a shared source of truth. Notion AI sits on top of those 70–80 page transcripts, letting the delivery team:

• Ask detailed questions and get instant, accurate answers
• Understand the client’s goals and language as if they’d been in the room
• Write content and design assets that hit the brief on the first pass

Matthew and Dave share:

• Why tools like Monday.com and Wrike weren’t the right fit for their workflow
• How they designed a single client page that connects sales, delivery, tasks and transcripts
• The real impact on quality: fewer complaints, fewer rewrites, and more consistent outputs
• How Notion AI helps them halve overall delivery timelines without cutting corners
• The internal AI tools they’ve built to critique client collateral and train the sales team
• What they learned about change management when rolling Notion out to two very different teams

If you run a services business, agency or consulting firm and struggle with handovers, inconsistent delivery or time-poor clients, this episode will give you a concrete example of how to:

• Turn conversations into assets
• Build a living knowledge base out of transcripts
• Use Notion AI as a partner for both sales and delivery

1. Turn every client conversation into a searchable asset.

   Record discovery and pitch calls, store the transcripts in Notion, and let Notion AI answer detailed questions later instead of relying on one person’s notes and memory.

2. Design a single shared workspace for sales and delivery.

   Create a unified client page that links deals, transcripts, briefs, tasks and assets so delivery can start with full context instead of fresh questionnaires and repeat conversations.

3. Use AI to cut waiting time, not quality.

   Let AI reduce back-and-forth, rewrites and clarifications so the team can spend their time on higher-quality writing, design and strategy – which is where the real value is.

• Dave Merriweather:
• Matthew Shaw:
• Ionix Digital

• Tim Jeffries:
• Jerwin Parker: