ClarisTalk AI

Hosted by Matt Navarre & Cris Ippolite

TechnologyInterviews guests

Website RSS feed

Episodes

Latest episode

May 2026

Language

EN-US

About the show

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.

Listen to episodes

46 recent

May 30, 2026Episode 461 hr 13 min

Reporting from the Vienna Calling FileMaker Conference

Reporting live from the Vienna Calling unconference: five conversations from the only European FileMaker unconference, recorded on the ground in Vienna. Organizer Philipp Puls on why the format works, Charles Delfs on rebranding to Klai and what an actual AI strategy looks like, Johan Hedman on the next big European conference, Vincenzo Menanno on technical debt and using AI to analyze your code, and a turnabout where Javier Durá puts Matt in the hot seat.⏱ CHAPTERS0:00 — Welcome: what is the Vienna Calling unconference0:24 — Philipp Puls (72solutions): inside the unconference format13:50 — Charles Delfs (Klai): the rebrand & an AI strategy that isn't just "chat"36:42 — Johan Hedman (Square Moon): EngageU goes three days41:33 — Vincenzo Menanno (Beezwax): technical debt, iteration & AI code analysis1:00:52 — The tables turn: Javier Durá interviews Matt Navarre🎙 IN THIS EPISODE• Why an unconference is capped at ~100 people, and the "if three people care, make a session" ethos• FileMaker's collaborate-over-compete culture• Charles on why "code as product" is fading in the AI era, and governed, observable AI access for non-technical staff• Semi-deterministic / hybrid apps, FileMaker as a scalable backend, and the new Klai Run (on-prem, partly open source)• Johan on EngageU expanding to three full days in Malmö with a business track• Vincenzo on defining technical debt, putting complexity at the right layer, and recursively analyzing whole script trees with an MCP• Measuring real performance: the hidden cost of open-record and set-field steps• Javier interviews Matt: the Navarre.ai rebrand, free weekly AI classes, and why insert-from-URL + the web viewer are the real AI unlock• What's next: OpenClaw / Hermes as an "ultra robot" with a FileMaker database as its memoryLinks72solutions (Philipp Puls): https://www.72solutions.euKlai (Charles Delfs): https://klai.studioSquare Moon (Johan Hedman): https://www.squaremoon.seEngageU conference (Malmö, Sept 30 – Oct 2): https://engageu.euBeezwax (Vincenzo Menanno): https://www.beezwax.netAfterdata (Javier Durá): https://www.afterdata.esFileMaker Magazine ES: https://www.filemakermagazine.es

May 22, 2026Episode 4530 min

That Day When My AI Agent Talked to Yours

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.

May 17, 2026Episode 4427 min

Are Developers Becoming AI Managers?

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.

May 5, 2026Episode 431 hr 3 min

Changes in the world of Value Pricing in the land of AI with Jonathan Stark

Apologies for my audio!! Somehow, Zoom lost the setting and nice quality Mic was off, and the awful mic in my monitor took over, so there is a ton of room noise. Jonathan sounds great though. --Jonathan Stark is an author and expert that helps developers (and others) think about pricing projects and helping clients differently than the usual hourly billing approach. Now that AI tools like Claude Opus 4.7 and OpenAI Codex allow app creation in tools other than FileMaker at vastly increased rates of speed, what does it mean for FileMaker developers who work with clients?https://jonathanstark.com

April 23, 2026Episode 421 hr 7 min

Dimitris Kokoutsidis announces ai2fm.com - a new way to write FileMaker scripts in an IDE.

Matt and Dimitris talk about a new tool for the community that allows coding FileMaker scripts in an IDE. It's a totally different dev environment, and also completely familiar.

April 5, 2026Episode 411 hr 9 min

Stathis Askaridis shows AI Built front-end with FileMaker on back

Matt talks with Stathis Askaridis (We Know Data and Pineapple.gr) about his method of developing with FileMaker. Stathis shows examples of this workflow, which is a very simple FileMaker database with just a few scripts, NO RELATIONSHIPS, and a layout with a WebViewer. All the dev is done/assisted by Claude Code, Codex, etc. which delivers HTML / CSS / JavaScript. Data edits? Easily done with FileMaker card windows, or also in JavaScript.But this isn't the cool part (well, it's kind of cool) It's the logging and bug tracking that are amazing. Stathis uses a tool that captures the user session and actually contains more metadata by far than the FileMaker database. This allows him and his team to see exactly what a user did when the bug (like writing data to a locked or invalid field, or any error at the UI or data level).What impressed most is that the possibility exists for this bug to be routed to a tool that analyzes the layout, the data, the bug experienced, and actually fixes it! This is perhaps then deployed to the dev server and tested by a meat puppet (that's how SciFi AI thinks of humans) can review and confirm before putting into production – also with automated tools.Stathis is an Otto evangelist, and rightly so. For any type of deployment that uses this level of sophistication, it's a must.

March 25, 2026Episode 401 hr 21 min

Ian Jempson – New tool: Transcribr for FileMaker.

Ian Jempson demonstrates an immediately usefully AI tools for FileMaker developers that transcribes video and audio files.Maybe even bigger: Ian shows his workflow for not only writing script with complex code that can be pasted into Script Workspace (close to the Holy Grail here). Also he shows a way to prompt-into-existence entire database files with tables, layouts, scripts and relationships. Our world has changed!Key Tools & Resources1. Transcribr - Local AI Transcription Tool (Price TBD)Download: transformingdigital.AI/transcriber100% local Mac application (Linux version in development)Single-file Swift executable - drag and drop installationFeatures: Real-time transcription, batch processing, folder watchingUses Whisper models (version 1.1 will add Nvidia Parakeet for 90x real-time speed)Multilingual support with speaker separation coming in v1.1Webhook functionality for automated notificationsReturns structured JSON data to FileMaker via insert from URL2. Extractr – Document Data Extraction Tool (Preview)Extracts structured data from PDFs, Word, Excel, PowerPoint, and imagesUses JSON schema to define output format100% local processing, similar flow to Transcribr3. AI-Assisted FileMaker Script GenerationUses Claude Code in terminal for script developmentCustom skills for handling FileMaker's XML script formatAutomated script creation from API specifications using FM upgrade toolGenerates complete database schemas including tables, fields, relationships, and layoutsInstallation & SetupClaude Code Terminal Setup:brew install --cask claude-codeorcurl -fsSL [https://claw.ai/install.sh](https://claw.ai/install.sh) | shMBS Plugin: Required for copying FileMaker script steps in pasteable XML formatKey Techniques DemonstratedUsing Claude skills to improve FileMaker insert from URL scriptsGenerating FileMaker databases from ERD diagramsCreating complete FileMaker patch schemas from Swagger documentationAutomating error handling and code quality checksUsing context windows and hooks in Claude CodeSystem RequirementsRecommended: Mac M1 or newer with 16GB+ RAMLarge Whisper models may require more RAM than available on 8GB systemsLinks & ResourcesTranscriber Tool: transformingdigital.AI/transcriberFileMaker Upgrade Tool: Official Claris developer toolSaliant Patch Lab: GitHub repository for FileMaker patch format researchFree AI Training Classes: Weekly Thursday sessions with Matt NavarreGitHub: Ian will share the fminsert from URL skill on GitHubProduction Deployment ConsiderationsMac app runs locally on developer machinesLinux version can run on servers for batch processingWebhook integration enables automated workflowsWatch folder functionality for asynchronous processingNote: The above was AI generated.

February 18, 2026Episode 391 hr 2 min

Something Big Is Happening...

Something is shifting in software.We’re not in a moment of collapse. We’re in a moment of re-architecture. Agents, persistent memory, autonomous workflows, database acceleration, and AI-native software creation are all converging at once.This episode connects those signals — from legacy database platforms potentially getting a new engine, to developers building production-grade software in hours, to AI agents that don’t just respond but operate. The tools are changing. The leverage is changing. The interface is changing. Something big is happening.This episode explores the signals suggesting we’re not just seeing incremental AI progress — we’re witnessing a structural change in how software is built, operated, and experienced.A Big Signal for the FileMaker World?We discuss recent news that could have major implications for the FileMaker ecosystem.Apple’s parent company made an acquisition that may signal faster, more flexible databases coming to FileMaker or iWork.If true, this could represent one of the most meaningful infrastructure shifts for that world in years. Cris has the scoop.Article discussed:https://appleinsider.com/articles/26/02/11/faster-more-flexible-databases-could-be-coming-to-filemaker-or-iworkHow Software Is Being Built NowA recent viral post sparked conversation across the tech world about how software creation is changing.The idea: the way software engineering works today is fundamentally different than even a week ago.Cris shares how he built https://www.isolutionsai.com in just three hours using modern AI workflows.Not hype.Not “replace engineers.”But a real shift in leverage.Viral post discussed:https://x.com/mattshumer_/status/2021256989876109403?s=20OpenClaw, Agents & the Next Interface LayerWe break down what OpenClaw is, why it exploded, and what it signals about where AI is headed.Not just chat.Not just prompts.But persistent, always-on AI operators.In this segment, we cover:What OpenClaw actually doesWhy the Ralph Wiggum loop matteredHow persistence, cron jobs, and memory change everythingWhat happened when we ran it ourselvesWhat a potential OpenAI acquisition could meanThis isn’t doom.It’s design evolution.Links discussed:OpenClaw: https://github.com/openclaw/openclawRalph Wiggum repo: https://awesomeclaude.ai/ralph-wiggumConnect with Crishttps://www.isolutionsai.comFollow Matthttps://www.navarre.trainingCris' StackConvex: https://convex.dev/referral/CRISB43294Reactive backend database that keeps app state synced in real time without managing servers.Clerk: https://clerk.comAuthentication and user management for modern apps including sign-in, sessions, and roles.Context7: https://context7.comContext retrieval that helps developers understand and navigate codebases faster.Vercel: https://vercel.comFrontend deployment platform optimized for fast, scalable web applications.Resend: https://resend.comDeveloper-focused email API for sending transactional and product emails.Supabase: https://supabase.comOpen-source backend platform providing Postgres, authentication, storage, and APIs.Railway: https://railway.comCloud platform that simplifies deploying and managing backend services and databases.iSolutionsAIiSolutionsAI — Your Partner in the New Frontiers of AICustom AI solutions, machine learning models, and intelligent assistants.X (formerly Twitter)Matt Shumer (@mattshumer_) on XSomething Big Is Happeninghttps://x.com/mattshumer_/status/2021256989876109403?s=20Awesome ClaudeRalph Wiggum - Iterative AI Development LoopOfficial Anthropic plugin for iterative AI coding. Ship 6 repos overnight. $50k contract for $297 in API costs.

February 10, 2026Episode 381 hr 29 min

Fear, Trust, and the Playbook for Successful AI Deployments

In this episode, Cris Ippolite sits down with Kate Waldhauser, Founder of Violet Beacon, to unpack why so many enterprise AI efforts stall—and what it actually takes to make them work.Together they examine how fear-driven headlines and surface-level interpretations have distorted the AI conversation, from reactions to Salesforce’s generative AI strategy to the widely cited MIT “GenAI Divide” research.Rather than debating whether AI is good or bad, the conversation focuses on execution discipline: designing pilots for production, embedding AI into real workflows, defining acceptance criteria instead of chasing perfection, and treating AI as an organizational transformation rather than a technical experiment.The episode closes with a practical playbook for leaders who want measurable ROI from AI in 2026—grounded in trust, accountability, and strong data foundations.Companion ReadingHow Serious Companies Are Turning AI Into Measurable Business Advantage — Cris Ippolitehttps://isolutions.medium.com/how-serious-companies-are-turning-ai-into-measurable-business-advantage-216b2d8fb743A deeper written exploration of the themes discussed in this episode, expanding on execution discipline, pilot design, integration, ROI measurement, and why data-first organizations consistently outperform.Resources Mentioned(Listed in order of first mention in the episode; timestamps indicate when first referenced.)1. The Algorithm of Fear: Unpacking Prejudice Against AIhttps://digitalcommons.lindenwood.edu/cgi/viewcontent.cgi?article=1709&context=faculty-research-papersReferenced ~03:03.2. The Rise of Artificial Intelligence Phobia (ResearchGate)https://www.researchgate.net/publication/393689899_The_Rise_of_Artificial_Intelligence_Phobia_Unveiling_News-Driven_Spread_of_AI_Fear_Sentiment_using_ML_NLP_and_LLMsReferenced ~03:03.3. Signal vs. Hype — Custom GPT Tool (Violet Beacon)https://chatgpt.com/g/g-697049186b388191824ee9f0d6677212-signal-vs-hype-by-violet-beaconReferenced ~08:47.4. Salesforce Executives Say Trust in Generative AI Has Declined (The Information)https://www.theinformation.com/articles/salesforce-executives-say-trust-generative-ai-declinedReferenced ~12:06.5. William Phelps Eno (Creator of the Stop Sign)https://en.wikipedia.org/wiki/William_Phelps_EnoReferenced ~41:53.6. Superagency: What Could Possibly Go Right with Our AI Future — Reid Hoffmanhttps://amzn.to/4r3JMWHReferenced ~50:19.7. NIST AI Risk Management Framework (AI RMF) Playbookhttps://airc.nist.gov/airmf-resources/playbook/Referenced ~56:02.8. ISO/IEC 42001:2023 — Artificial Intelligence Management Systemshttps://www.iso.org/standard/42001Referenced ~56:02.9. State of AI in Business 2025 Report (MIT / Project NANDA)https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdfReferenced ~59:37.10. Tata Consultancy Services — AI for Business Studyhttps://www.tcs.com/content/dam/global-tcs/en/pdfs/insights/global-studies/report/north-america-report-tcs-ai-for-business-study.pdfReferenced ~1:19:22.Contact InformationGuestKate WaldhauserFounder & Chief StrategistViolet BeaconElevating productivity through responsible AI and automation designed to save time.• Website: https://violetbeacon.com/• Human Intelligence blog: https://violetbeacon.com/welcome-to-human-intelligence/HostCris Ippolite• YouTube: https://www.youtube.com/@iSolutionsAI• LinkedIn: https://www.linkedin.com/in/crisippolite/• Twitter/X: https://twitter.com/ISolutionsai• Website: https://www.isolutionsai.com

December 31, 2025Episode 371 hr 28 min

2025 Year in Review – What happened? And what's next?

Show NotesPodcast segment that summarizes recent paper:Microsoft Copilot Usage Report 2025It’s About Time: The Copilot Usage Report 2025 (PDF): https://microsoft.ai/wp-content/uploads/2025/12/What_people_do_with_Copilot-8.pdf Microsoft AIOpenAI State of Enterprise AI 2025 — State of Enterprise AI 2025 Report (PDF): https://cdn.openai.com/pdf/7ef17d82-96bf-4dd1-9df2-228f7f377a29/the-state-of-enterprise-ai_2025-report.pdfOpenAI CDNPerplexity / Harvard AI Agents Paper — The Adoption and Usage of AI Agents: Early Evidence from Perplexity(ArXiv): https://arxiv.org/abs/2512.07828 arXiv • • Anthropic Claude Productivity Report — Estimating AI Productivity Gains from Claude Conversations (PDF): https://assets.anthropic.com/m/28fda2ad148e2bf5/original/Estimating-AI-productivity-gains-from-Claude-conversations.pdf Anthropic Brand PortalarXiv.org--Matt mentioned a book called Outlive by Dr. Peter Attiahttps://www.amazon.com/Audible-Outlive-Science-Art-Longevity/dp/B0B64WL9PK/ref=sr_1_1?crid=R3V5TNWIXZTO&dib=eyJ2IjoiMSJ9.mUiQmJW1Y0MX8JDvmiVmUMPwDD8vg5OFSW7WS9b5Rk-CopHssXKrA-4bDgGxooIcBUyulMr3g_ivC_46YYgBu7JQx1F8NFTYsBXHsMMZl9TxY0A2fejxyovq40qF1V7lgkPk436e9W5t1uyzkCBQeM540x-a_7iC17mRFmQJPouc0mYGAw-fZdBOmldwtzzdYdUydR0-iHYDpcSyd2_wBi0aNPJP4om0Ub-XZfbKflA.QwjKeavWW9YbQu2ZUW51b6DXuLkxXRaWEAUqlADEGSE&dib_tag=se&keywords=outlive&qid=1767207562&sprefix=outli%2Caps%2C336&sr=8-1