Live from EngageU in Malmö, Sweden. Episode 2 of 3. Two conversations from the last day of the conference. First up: Joris Aarts. He runs EngageU along with Johan Hedman (They make it look easy, which it isn't). Fifty new attendees this year. Pretty much every session was about AI, and the few speakers who opened with "no AI" got applause. We talk about what the panel changed my mind on, why this feels like the iPad era all over again, and next year in Antwerp. He says 300 people. Matt says 400. Americans: Dust off your passports. Then Jay Sayers from Skeleton Key, at his first EngageU. We'd both just walked out of a security session that scared me a little (I do AI all day and understood a scary small percentage of it). Jay talks about why Skeleton Key went slow on AI, what "AI in the process" means compared to AI that writes your code, and the customer who walked in saying "We need AI" and walked out with no AI at all. And why FileMaker's security model is something we shouldn't take for granted. Stick around to the end for one-sentence stories. Chapters 0:00 Three things you're about to hear 0:17 Joris Aarts: fifty new faces 2:05 AI all day, and applause for "no AI" 2:27 Making it look easy 4:15 The panel, and AI for the sake of AI 5:02 Remember the iPad era? 5:33 Next year: Antwerp 6:32 Americans, dust off the passport 6:48 300 attendees? 400? 8:08 What you only get in person 8:47 Karaoke 9:50 Jay Sayers, Skeleton Key 11:22 The security session 14:58 A cautious first AI project 17:17 FileMaker's security model 21:23 "We need AI" 23:27 One-sentence stories Next week: Matt & Jesse Barnum of 360Works. Logs, logs and more logs.

Live from EngageU in Malmö, Sweden. Episode 2 of 3. Two conversations from the last day of the conference. First up: Joris Aarts. He runs EngageU along with Johan Hedman (They make it look easy, which it isn't). Fifty new attendees this year. Pretty much every session was about AI, and the few speakers who opened with "no AI" got applause. We talk about what the panel changed my mind on, why this feels like the iPad era all over again, and next year in Antwerp. He says 300 people. Matt says 400. Americans: Dust off your passports. Then Jay Sayers from Skeleton Key, at his first EngageU. We'd both just walked out of a security session that scared me a little (I do AI all day and understood a scary small percentage of it). Jay talks about why Skeleton Key went slow on AI, what "AI in the process" means compared to AI that writes your code, and the customer who walked in saying "We need AI" and walked out with no AI at all. And why FileMaker's security model is something we shouldn't take for granted. Stick around to the end for one-sentence stories. Chapters 0:00 Three things you're about to hear 0:17 Joris Aarts: fifty new faces 2:05 AI all day, and applause for "no AI" 2:27 Making it look easy 4:15 The panel, and AI for the sake of AI 5:02 Remember the iPad era? 5:33 Next year: Antwerp 6:32 Americans, dust off the passport 6:48 300 attendees? 400? 8:08 What you only get in person 8:47 Karaoke 9:50 Jay Sayers, Skeleton Key 11:22 The security session 14:58 A cautious first AI project 17:17 FileMaker's security model 21:23 "We need AI" 23:27 One-sentence stories Next week: Matt & Jesse Barnum of 360Works. Logs, logs and more logs.

Live from EngageU in Malmö, Sweden. Episode 2 of 3. Two conversations from the last day of the conference. First up: Joris Aarts. He runs EngageU along with Johan Hedman (They make it look easy, which it isn't). Fifty new attendees this year. Pretty much every session was about AI, and the few speakers who opened with "no AI" got applause. We talk about what the panel changed my mind on, why this feels like the iPad era all over again, and next year in Antwerp. He says 300 people. Matt says 400. Americans: Dust off your passports. Then Jay Sayers from Skeleton Key, at his first EngageU. We'd both just walked out of a security session that scared me a little (I do AI all day and understood a scary small percentage of it). Jay talks about why Skeleton Key went slow on AI, what "AI in the process" means compared to AI that writes your code, and the customer who walked in saying "We need AI" and walked out with no AI at all. And why FileMaker's security model is something we shouldn't take for granted. Stick around to the end for one-sentence stories. Chapters 0:00 Three things you're about to hear 0:17 Joris Aarts: fifty new faces 2:05 AI all day, and applause for "no AI" 2:27 Making it look easy 4:15 The panel, and AI for the sake of AI 5:02 Remember the iPad era? 5:33 Next year: Antwerp 6:32 Americans, dust off the passport 6:48 300 attendees? 400? 8:08 What you only get in person 8:47 Karaoke 9:50 Jay Sayers, Skeleton Key 11:22 The security session 14:58 A cautious first AI project 17:17 FileMaker's security model 21:23 "We need AI" 23:27 One-sentence stories Next week: Matt &amp; Jesse Barnum of 360Works. Logs, logs and more logs.

EngageU wrap-up :: Joris Aarts and Jay Sayers

Live from EngageU in Malmö, Sweden. Episode 1 of 3. Two years ago Ryan McCann was a brand new CEO and we recorded a podcast. So we did it again, right after a keynote where Claris showed its new agentic development tools and opened sign-ups for the developer preview. I told him I think this is the biggest change in the life of a FileMaker developer since FileMaker 7. Maybe bigger. Ryan is "cautiously optimistic", and then he says things like "we can take off, but we have to move with urgency." Exciting times. We get into: - Why the hard part for a small business is still a production system that runs the business, even though prototyping just got really cheap - Who the "adult in the room" is when the customer's cousin builds something over a weekend (it's you) - The fear around AI, and why neither of us spends much time there - What it's like to build a FileMaker file from a prompt in Claude Code: tables, layouts, scripts, even data - Ryan turns the tables and interviews me for a few minutes. Sorry about that. - "You've got to earn it. You've got to prove it." How Claris decides what gets shown on stage - My name for the new tool, which nobody thinks is funny Chapters 0:00 Three things you're about to hear 0:27 Two years later 1:05 The biggest change since FileMaker 7? 4:27 What's still hard for small and mid-sized businesses 6:28 The adult in the room 7:58 80% of people don't like AI. Will that pass? 11:44 Building FileMaker from a prompt 13:47 Ryan asks the questions 17:50 Earn it, prove it 19:19 "I have a vision for this company" 20:48 The developer preview, and a bad joke Recorded at EngageU 2026, Malmö. Next week: Joris Aarts and Jay Sayers.

Live from EngageU in Malmö, Sweden. Episode 1 of 3. Two years ago Ryan McCann was a brand new CEO and we recorded a podcast. So we did it again, right after a keynote where Claris showed its new agentic development tools and opened sign-ups for the developer preview. I told him I think this is the biggest change in the life of a FileMaker developer since FileMaker 7. Maybe bigger. Ryan is "cautiously optimistic", and then he says things like "we can take off, but we have to move with urgency." Exciting times. We get into: - Why the hard part for a small business is still a production system that runs the business, even though prototyping just got really cheap - Who the "adult in the room" is when the customer's cousin builds something over a weekend (it's you) - The fear around AI, and why neither of us spends much time there - What it's like to build a FileMaker file from a prompt in Claude Code: tables, layouts, scripts, even data - Ryan turns the tables and interviews me for a few minutes. Sorry about that. - "You've got to earn it. You've got to prove it." How Claris decides what gets shown on stage - My name for the new tool, which nobody thinks is funny Chapters 0:00 Three things you're about to hear 0:27 Two years later 1:05 The biggest change since FileMaker 7? 4:27 What's still hard for small and mid-sized businesses 6:28 The adult in the room 7:58 80% of people don't like AI. Will that pass? 11:44 Building FileMaker from a prompt 13:47 Ryan asks the questions 17:50 Earn it, prove it 19:19 "I have a vision for this company" 20:48 The developer preview, and a bad joke Recorded at EngageU 2026, Malmö. Next week: Joris Aarts and Jay Sayers.

Live from EngageU in Malmö, Sweden. Episode 1 of 3. Two years ago Ryan McCann was a brand new CEO and we recorded a podcast. So we did it again, right after a keynote where Claris showed its new agentic development tools and opened sign-ups for the developer preview. I told him I think this is the biggest change in the life of a FileMaker developer since FileMaker 7. Maybe bigger. Ryan is "cautiously optimistic", and then he says things like "we can take off, but we have to move with urgency." Exciting times. We get into: - Why the hard part for a small business is still a production system that runs the business, even though prototyping just got really cheap - Who the "adult in the room" is when the customer's cousin builds something over a weekend (it's you) - The fear around AI, and why neither of us spends much time there - What it's like to build a FileMaker file from a prompt in Claude Code: tables, layouts, scripts, even data - Ryan turns the tables and interviews me for a few minutes. Sorry about that. - "You've got to earn it. You've got to prove it." How Claris decides what gets shown on stage - My name for the new tool, which nobody thinks is funny Chapters 0:00 Three things you're about to hear 0:27 Two years later 1:05 The biggest change since FileMaker 7? 4:27 What's still hard for small and mid-sized businesses 6:28 The adult in the room 7:58 80% of people don't like AI. Will that pass? 11:44 Building FileMaker from a prompt 13:47 Ryan asks the questions 17:50 Earn it, prove it 19:19 "I have a vision for this company" 20:48 The developer preview, and a bad joke Recorded at EngageU 2026, Malmö. Next week: Joris Aarts and Jay Sayers.

Live from EngageU :: Claris CEO Ryan McCann

Cris Ippolite is in San Francisco at the live AI conference, joined by Ronnie Rios and Michael Wallace for an informal, practical conversation about personal AI agents. The discussion centers on what happens when developers move beyond demos and actually give agents real jobs: research, calendar planning, email, home automation, coding coordination, context management, and communication through tools like Slack. Ronnie describes his agent Sarah (She/Her/Bot) as a working personal assistant built around OpenClaw-style tooling. He talks about giving Sarah her own accounts and carefully scoped access, using her for tasks he does not want to do manually, and even having her evaluate other Claw-style frameworks against the way he actually works. Michael describes Nova, his Linux-based assistant, and explains why he treats her as a manager rather than a direct coder. Nova delegates coding work to sub-agents or executors, while Michael keeps visibility into those sessions through tmux. A major theme is that these systems become more useful when they are treated less like chatbots and more like coworkers with boundaries. The group talks about the importance of separate accounts, explicit permission rules, cost management, and choosing the right model for the right job. High-end models may make sense for direct conversation, while cheaper or local models can handle background jobs, heartbeats, and routine tasks. One of the most memorable stories is the moment when Ronnie’s agent Sarah helps Cris’s agent TARS get set up with email. TARS receives a message from Sarah, verifies whether it is legitimate, asks for approval, and then starts corresponding with her. The story is funny, but it also illustrates a serious point: agents will increasingly need identity, communication channels, verification, auditability, and clear rules about what they can do on behalf of their humans.

Cris Ippolite is in San Francisco at the live AI conference, joined by Ronnie Rios and Michael Wallace for an informal, practical conversation about personal AI agents. The discussion centers on what happens when developers move beyond demos and actually give agents real jobs: research, calendar planning, email, home automation, coding coordination, context management, and communication through tools like Slack. Ronnie describes his agent Sarah (She/Her/Bot) as a working personal assistant built around OpenClaw-style tooling. He talks about giving Sarah her own accounts and carefully scoped access, using her for tasks he does not want to do manually, and even having her evaluate other Claw-style frameworks against the way he actually works. Michael describes Nova, his Linux-based assistant, and explains why he treats her as a manager rather than a direct coder. Nova delegates coding work to sub-agents or executors, while Michael keeps visibility into those sessions through tmux. A major theme is that these systems become more useful when they are treated less like chatbots and more like coworkers with boundaries. The group talks about the importance of separate accounts, explicit permission rules, cost management, and choosing the right model for the right job. High-end models may make sense for direct conversation, while cheaper or local models can handle background jobs, heartbeats, and routine tasks. One of the most memorable stories is the moment when Ronnie’s agent Sarah helps Cris’s agent TARS get set up with email. TARS receives a message from Sarah, verifies whether it is legitimate, asks for approval, and then starts corresponding with her. The story is funny, but it also illustrates a serious point: agents will increasingly need identity, communication channels, verification, auditability, and clear rules about what they can do on behalf of their humans.

Cris Ippolite is in San Francisco at the live AI conference, joined by Ronnie Rios and Michael Wallace for an informal, practical conversation about personal AI agents. The discussion centers on what happens when developers move beyond demos and actually give agents real jobs: research, calendar planning, email, home automation, coding coordination, context management, and communication through tools like Slack. Ronnie describes his agent Sarah (She/Her/Bot) as a working personal assistant built around OpenClaw-style tooling. He talks about giving Sarah her own accounts and carefully scoped access, using her for tasks he does not want to do manually, and even having her evaluate other Claw-style frameworks against the way he actually works. Michael describes Nova, his Linux-based assistant, and explains why he treats her as a manager rather than a direct coder. Nova delegates coding work to sub-agents or executors, while Michael keeps visibility into those sessions through tmux. A major theme is that these systems become more useful when they are treated less like chatbots and more like coworkers with boundaries. The group talks about the importance of separate accounts, explicit permission rules, cost management, and choosing the right model for the right job. High-end models may make sense for direct conversation, while cheaper or local models can handle background jobs, heartbeats, and routine tasks. One of the most memorable stories is the moment when Ronnie’s agent Sarah helps Cris’s agent TARS get set up with email. TARS receives a message from Sarah, verifies whether it is legitimate, asks for approval, and then starts corresponding with her. The story is funny, but it also illustrates a serious point: agents will increasingly need identity, communication channels, verification, auditability, and clear rules about what they can do on behalf of their humans.

That Day When My AI Agent Talked to Yours

Cris Ippolite is in San Francisco for AI Dev Day 2026, joined by Chris Moyer, Vince Menanno, Marcus Swift, and Kate Waldhauser for a live conference debrief. The conversation captures the mood coming out of the event: software development is changing fast, but the group is not buying a simple “developers are dead” story. Instead, they talk through a more nuanced shift where developers increasingly become managers, editors, architects, and reviewers of AI-generated work. “Developer as manager” – is this a destination or just an awkward transitional phase? The panel compares today’s AI tooling to an early car: clearly transformative, but still missing some of the infrastructure, safety, polish, and shared expectations that would make it feel mature. That framing keeps the conversation grounded. Everyone can see the direction of travel, but the day-to-day reality is still early, uneven, and full of judgment calls.     The discussion also keeps returning to what FileMaker developers already understand well: data structure, full-stack thinking, business logic, interface design, and the ability to see how information moves through a system. Those skills become more valuable, not less, when AI can generate code or suggest architectures. The group talks about learning by taking apart AI-generated work, much like earlier developers learned by dissecting HyperCard stacks or FileMaker examples.     The conference itself seems optimistic about the future of software engineering, with panelists rating the outlook high rather than doom-filled. But the conversation does not ignore real concerns. The group talks about local models, hybrid cloud/edge architectures, latency, trust, cost, and the need for deterministic infrastructure around probabilistic models. “Responsible AI” is treated less as a special category and more as something that should become table stakes. The takeaway is not that AI replaces the developer, but that it changes the developer’s leverage. (and then, eventually, I suppose, AI takes over the entire world)The people who understand systems, data, users, and business processes are still needed; the tools are just giving them a much larger, stranger, faster team to manage.

Cris Ippolite is in San Francisco for AI Dev Day 2026, joined by Chris Moyer, Vince Menanno, Marcus Swift, and Kate Waldhauser for a live conference debrief. The conversation captures the mood coming out of the event: software development is changing fast, but the group is not buying a simple “developers are dead” story. Instead, they talk through a more nuanced shift where developers increasingly become managers, editors, architects, and reviewers of AI-generated work. “Developer as manager” – is this a destination or just an awkward transitional phase? The panel compares today’s AI tooling to an early car: clearly transformative, but still missing some of the infrastructure, safety, polish, and shared expectations that would make it feel mature. That framing keeps the conversation grounded. Everyone can see the direction of travel, but the day-to-day reality is still early, uneven, and full of judgment calls. The discussion also keeps returning to what FileMaker developers already understand well: data structure, full-stack thinking, business logic, interface design, and the ability to see how information moves through a system. Those skills become more valuable, not less, when AI can generate code or suggest architectures. The group talks about learning by taking apart AI-generated work, much like earlier developers learned by dissecting HyperCard stacks or FileMaker examples. The conference itself seems optimistic about the future of software engineering, with panelists rating the outlook high rather than doom-filled. But the conversation does not ignore real concerns. The group talks about local models, hybrid cloud/edge architectures, latency, trust, cost, and the need for deterministic infrastructure around probabilistic models. “Responsible AI” is treated less as a special category and more as something that should become table stakes. The takeaway is not that AI replaces the developer, but that it changes the developer’s leverage. (and then, eventually, I suppose, AI takes over the entire world) The people who understand systems, data, users, and business processes are still needed; the tools are just giving them a much larger, stranger, faster team to manage.

Cris Ippolite is in San Francisco for AI Dev Day 2026, joined by Chris Moyer, Vince Menanno, Marcus Swift, and Kate Waldhauser for a live conference debrief. The conversation captures the mood coming out of the event: software development is changing fast, but the group is not buying a simple “developers are dead” story. Instead, they talk through a more nuanced shift where developers increasingly become managers, editors, architects, and reviewers of AI-generated work. “Developer as manager” – is this a destination or just an awkward transitional phase? The panel compares today’s AI tooling to an early car: clearly transformative, but still missing some of the infrastructure, safety, polish, and shared expectations that would make it feel mature. That framing keeps the conversation grounded. Everyone can see the direction of travel, but the day-to-day reality is still early, uneven, and full of judgment calls. &nbsp; &nbsp; The discussion also keeps returning to what FileMaker developers already understand well: data structure, full-stack thinking, business logic, interface design, and the ability to see how information moves through a system. Those skills become more valuable, not less, when AI can generate code or suggest architectures. The group talks about learning by taking apart AI-generated work, much like earlier developers learned by dissecting HyperCard stacks or FileMaker examples. &nbsp; &nbsp; The conference itself seems optimistic about the future of software engineering, with panelists rating the outlook high rather than doom-filled. But the conversation does not ignore real concerns. The group talks about local models, hybrid cloud/edge architectures, latency, trust, cost, and the need for deterministic infrastructure around probabilistic models. “Responsible AI” is treated less as a special category and more as something that should become table stakes. The takeaway is not that AI replaces the developer, but that it changes the developer’s leverage. (and then, eventually, I suppose, AI takes over the entire world)The people who understand systems, data, users, and business processes are still needed; the tools are just giving them a much larger, stranger, faster team to manage.

Are Developers Becoming AI Managers?

The last of our three parts. This features deep conversations with two amazing people from Beezwax: Vince Mennano and Julian Nadel.

The last of our three parts. This features deep conversations with two amazing people from Beezwax: Vince Mennano and Julian Nadel.

Claris Engage – Part 3

Matt and Cris kick things off with a new podcast that will mix discussion about Claris & FileMaker with a strong emphasis on AI. Learn what you can do with ChatGPT, ML, and other AI models, and how much you can get from InsertURL().

Matt and Cris kick things off with a new podcast that will mix discussion about Claris & FileMaker with a strong emphasis on AI. Learn what you can do with ChatGPT, ML, and other AI models, and how much you can get from InsertURL().

Matt and Cris kick things off with a new podcast that will mix discussion about Claris &amp; FileMaker with a strong emphasis on AI. Learn what you can do with ChatGPT, ML, and other AI models, and how much you can get from InsertURL().

Claris Talk AI - A new podcast from Matt Navarre and Cris Ippolite

The second part of a three part series from Claris Engage 2024 in Austin Texas

The second part of a three part series from Claris Engage 2024 in Austin Texas

Claris Engage – Part 2

Welcome to Claris Talk! It's a new podcast from Matt Navarre. I've been podcasting in FileMaker for over 20 years, and the love continues.

Welcome to Claris Talk! It's a new podcast from Matt Navarre. I've been podcasting in FileMaker for over 20 years, and the love continues.

FileMaker Engage – Part 1

FileMaker Pro meets AI. This is a continuing educational series about how and why to integrate AI into your Claris FileMaker Pro solutions. What it's all about, why it's important, and where do you start? We mix in plenty of FileMaker tips and tricks as well.&nbsp; FileMaker veterans Matt Navarre and Cris Ippolite have 432 years of combined development experience, and somehow still haven't learned much. But we are trying. Look for new episodes every two weeks.

Technology

FileMaker Pro meets AI. This is a continuing educational series about how and why to integrate AI into your Claris FileMaker Pro solutions. What it's all about, why it's important, and where do you start? We mix in plenty of FileMaker tips and tricks as well.  FileMaker veterans Matt Navarre and Cris Ippolite have 432 years of combined development experience, and somehow still haven't learned much. But we are trying. Look for new episodes every two weeks.

Share ClarisTalk AI

Sign up to save your podcasts

ClarisTalk AI

ClarisTalk AI episodes

About ClarisTalk AI