Past the Pilot

Stefan Born

Past the Pilot is a series where Stefan Born and Jonny McFadden go beyond the proof-of-concept to explore what agentic AI looks like in real-world business contexts. New episodes drop regularly — subscribe so you don’t miss what’s coming next.

Episodes

  1. Oct 28

    Rover, Agent, Assistant

    This episode got a little out of hand — in the best way. 🚀Jonny and Stefan are joined by special guest Charles Morman, lead engineer on the Vertesia Assistant team, who shows up with a surprise: a fully 3D-printed, AI-agent-built rover that maps rooms in real time using a LiDAR sensor salvaged off a Roomba. From there, the conversation goes deep on what Vertesia Assistant actually is, why "it's not just a chatbot," why AI hallucinations aren't random, how agents are now writing their own tools inside a secure sandbox, what MCP really unlocks, and how self-healing workflows are quietly ending 2am pager-duty nightmares. In this episode: 🤖 Charles's pet-project rover — built, coded, and debugged almost entirely by AI agents (Claude + Codex) 🧠 What Vertesia Assistant actually is, and why Studio ≠ Assistant 💬 Why Assistant is "not just a chat" — and why some customers ask to remove the chat box entirely 📄 Why AI hallucinations aren't random (and how documents fix it) 🛠️ The agent sandbox — watch an agent write its own code, build its own API connector, and generate a chart, fully self-directed 🔌 MCP (Model Context Protocol) — the "universal plug" that's changing how agents connect to the world 🧬 Model flexibility across the "Lumiverse" — GPT, Claude, Gemini, DeepSeek, and more ⚙️ "Processes" — Charles's current project blending deterministic workflows with autonomous agents, including self-healing supervised mode 🐛 Jonny's 2am pager-duty horror story — and how self-healing workflows make it a thing of the pastGuest: Charles Morman — Lead Engineer, Vertesia (Platform & Vertesia Assistant)Hosts: Stefan Born & Jonny McFadden 📖 Read the full recap blog: [link] 🔗 Learn more about Vertesia: https://vertesiahq.com 🎥 Watch a live demo: https://vertesiahq.com/video-demo

    Rover, Agent, Assistant
  2. Oct 15

    Agent's Do the Math? Humans Make the Call!

    10,000 AI agents helped crack a hard problem in fluid dynamics this week. We also built a document editor that edits one paragraph instead of rewriting your whole contract — and we're giving you a first look at DataForge, our new AI data analyst Watch the Show on Youtube or X .🧮 AI in Mathematics — OpenAI reportedly used ~10,000 agents to help produce a proof connected to the Navier-Stokes equations. We talk about what that really means — and why human judgment still matters more than ever. 📝 LIVE DEMO: Collaborative Document Editing — New in Vertesia Studio. Paragraph-level edits, specialist agents per document type, multi-edit in one pass, built-in approvals and version comparison. No full-document rewrites, no lost work. 📊 SNEAK PEEK: DataForge — Our upcoming data analysis app. Connect your data sources, get automatic data modeling, and generate dashboards that adapt as your data changes. Turns weeks of analyst time into a 20-minute conversation.The thread connecting all three: AI isn't here to replace expertise — it's here to remove the friction around it. ⏱️ Timestamps 00:00 – Intro 00:29 – This week in AI: the 10,000-agent proof 05:39 – Collaborative document editing, explained 12:17 – Live demo: Edit with AI in Vertesia Studio 24:12 – Sneak peek: DataForge 34:03 – The common thread🔗 Blog post: [link] • Get a demo: [link] • Subscribe: [link]#PastThePilot #Vertesia #AgenticAI #AIAgents #EnterpriseAI #DataForge #FutureOfWork #AIDemo #GenerativeAI #TechPodcast

    Agent's Do the Math? Humans Make the Call!
  3. Sep 24

    The Content Guessing Game

    Uploading a document is easy. Understanding it—and knowing whether you can trust what AI extracted—is the hard part.In this episode of Past the Pilot, Stefan and Jonny explore Vertesia’s new Intelligent Document Processing (IDP) capabilities and the intake policies behind reliable, agent-ready document workflows. Read the blog here Watch this episode on Youtube Watch this episode on X They walk through the three questions every incoming document should answer: What kind of document is this? What processing policy should apply? Can AI prove what it found? Watch the live demos as they show how Vertesia can: - Classify incoming documents automatically - Apply document-type-specific intake policies - Extract structured information from forms and repeatable fields- Interpret visually rich reports with charts, tables, and narrative context - Ground extracted values in their original page and source region- Use confidence thresholds to route only uncertain cases to human review - Create durable, auditable outputs for agents and downstream workflows From conference registration forms and campaign-performance reports to clean and degraded invoice scans, this episode shows why the future of document intake is not upload, OCR, and hope.It is governed, evidence-based document intelligence—designed for automation people can trust.Topics: Intelligent Document Processing, IDP, document intake, AI document classification, intake policies, grounded extraction, OCR, visual document understanding, human-in-the-loop review, AI agents, enterprise automation. #PastThePilot #Vertesia #IntelligentDocumentProcessing #DocumentAI #AgenticAI #EnterpriseAI #Automation #AIagents

    The Content Guessing Game
  4. Sep 15

    ABACadabra

    Your AI agent has access to everything it needs. That also means access to everything it shouldn't. Here's how to fix it.In this episode of Past the Pilot, Stefan Born (Co-Founder & CEO, Vertesia) and Jonny McFadden go deep on Attribute-Based Access Control (ABAC) — the access control model that makes AI agents actually safe to run in production.Most enterprise AI deployments rely on Role-Based Access Control (RBAC). It works fine for humans. It quietly falls apart for AI agents — because roles are static, and agents are dynamic. The result? A security gap that doesn't show up in your demo and only reveals itself when something goes wrong in production.Stefan and Jonny break down why ABAC is the missing piece, how it differs from RBAC at a philosophical level, and what Vertesia built to close the write-path gap that even most security-conscious teams miss.In this episode:🔑 Why RBAC breaks down when AI agents enter the picture 🔑 The "intern with a master key" problem — and why it's more common than you think 🔑 ABAC vs. RBAC: it's not just a feature upgrade, it's a different way of thinking about identity 🔑 The nurse analogy — same person, different context, different access 🔑 Why the write path was the critical missing piece in AI security 🔑 What it takes to go from 10 users to 10 agents without losing your mind (or your compliance posture) 🔑 Why Jonny thinks this should have been Episode 1⏱ Timestamps00— Introduction 02— Why access control matters more than ever for AI 06— RBAC: what it is and where it breaks 12— Enter ABAC: attributes, context, and dynamic access 18— The nurse analogy explained 24— The write-path gap: what it is and why it's dangerous 31— What Vertesia built with FEAT-060 38— Scaling from users to agents without operational chaos 44— "This should have been Episode 1" 48— Wrap-up and where to learn more🎙 About Past the PilotPast the Pilot is the show for enterprise teams building real AI — not demos, not prototypes, but production-grade systems that actually work. Hosted by Stefan Born and Jonny McFadden, each episode tackles one of the hard problems standing between your AI pilot and something you can actually ship.New episodes drop regularly. Subscribe so you don't miss one.🌐 Vertesia: https://vertesiahq.com 📄 Read the full blog post: https://medium.com/@sborn_63068/abacadabra-why-abac-is-the-missing-piece-that-gets-your-ai-past-the-pilot-77aec500be66 🔔 Subscribe to Past the Pilot

    ABACadabra
  5. Sep 3

    AI Watermarks & Scope Creep

    Anthropic can now watermark AI-generated text. Smart. One problem: edit a single sentence and the watermark disappears. Writing in pencil. That's where Episode 13 starts — and it doesn't slow down from there. Also make sure you read the blog here Watch the episode on Youtube Jonny and I run a live workflow demo we built for a finance client. A chaotic client meeting goes in. Structured developer tickets, user stories, and epics come out — automatically, straight into ClickUp. But the part that changed the room? A Scope-of-Work validation node that reads the actual contract and flags every ticket: in scope or out. Scope creep caught before a single line of code gets written. We also get into why pure LLM agents fail at scale — the 9-out-of-10 problem — and why process engines are the answer. Plus the governance layer that makes this safe for regulated industries: role-based access, audit trails, model switching. The stuff nobody talks about until it's too late. But here's what I really want you to take from this episode. You're not building individual tools anymore. You have an agentic platform — a master tool — that lets you improve processes you've never been able to automate. Not just replace things. Improve them. Smarter. Faster. More auditable. More reliable. Nobody gets excited about a pile of LEGO bricks. Show them the finished fire station and they get it immediately. That's what Past the Pilot is about. Not AI in the abstract. The fire station. #PastThePilot #EnterpriseAI #AgenticAI #AIWatermarking #WorkflowAutomation #ScopeCreep #AIInProduction #DigitalTransformation #LLM #FutureOfWork

    AI Watermarks & Scope Creep

About

Past the Pilot is a series where Stefan Born and Jonny McFadden go beyond the proof-of-concept to explore what agentic AI looks like in real-world business contexts. New episodes drop regularly — subscribe so you don’t miss what’s coming next.