What are the key takeaways from this Practical AI episode?

Key insights include: **Computer-Use for form automation:** Any web form — government portals, travel bookings, registrations — can be delegated to a computer-use agent without requiring API access. Demetrios uses this to handle German DMV appointments, flight check-ins, and boarding pass delivery automatically. The trigger: whenever you encounter a web form manually, that task is a candidate for computer-use delegation.; **Autonomous flight management workflow:** A practical multi-step agent workflow handles travel end-to-end — searching flights, pre-filling passenger details from a stored document, monitoring inbox for check-in windows, completing check-in, and sending boarding passes to your phone. The only human touchpoint is the final payment confirmation click, keeping financial control while eliminating all surrounding friction.; **LinkedIn outreach without API access:** LinkedIn's API is effectively locked down, but computer-use agents can trigger LinkedIn's native data export, monitor your inbox for the 48-hour delivery window, analyze DM history to identify two-way conversations, generate a shortlist of contacts, write personalized outreach messages, and create individualized media kit landing pages — all without any API credentials.

What did Demetrios Brinkmann discuss on Practical AI?

Demetrios Brinkmann, founder of MLOps Community and head of development experience at the Agentic AI Foundation, joins Chris Benson to explore computer-use agents in daily workflows, the blurring boundary between AI harnesses and models, and how agentic commerce may restructure online shopping and payment infrastructure. Key topics include: **Computer-Use for form automation:** Any web form — government portals, travel bookings, registrations — can be delegated to a computer-use agent without requiring API access. Demetrios uses this to handle German DMV appointments, flight check-ins, and boarding pass delivery automatically. The trigger: whenever you encounter a web form manually, that task is a candidate for computer-use delegation.; **Autonomous flight management workflow:** A practical multi-step agent workflow handles travel end-to-end — searching flights, pre-filling passenger details from a stored document, monitoring inbox for check-in windows, completing check-in, and sending boarding passes to your phone. The only human touchpoint is the final payment confirmation click, keeping financial control while eliminating all surrounding friction..

How long is this episode of Practical AI?

This episode is 56 minutes long. SignalCast provides an AI-generated summary so you can get the key insights in about 3 minutes.

Practical AI

Computer-Use Agents and the Future of the Agentic Internet

September 10, 2026

56 min episode · 2 min read

Demetrios Brinkmann

Episode

56 min

Read time

2 min

Topics

Career Growth, Startups, Leadership

AI-Generated Summary

Published Sep 11, 2026

Key Takeaways

✓Computer-Use for form automation: Any web form — government portals, travel bookings, registrations — can be delegated to a computer-use agent without requiring API access. Demetrios uses this to handle German DMV appointments, flight check-ins, and boarding pass delivery automatically. The trigger: whenever you encounter a web form manually, that task is a candidate for computer-use delegation.
✓Autonomous flight management workflow: A practical multi-step agent workflow handles travel end-to-end — searching flights, pre-filling passenger details from a stored document, monitoring inbox for check-in windows, completing check-in, and sending boarding passes to your phone. The only human touchpoint is the final payment confirmation click, keeping financial control while eliminating all surrounding friction.
✓LinkedIn outreach without API access: LinkedIn's API is effectively locked down, but computer-use agents can trigger LinkedIn's native data export, monitor your inbox for the 48-hour delivery window, analyze DM history to identify two-way conversations, generate a shortlist of contacts, write personalized outreach messages, and create individualized media kit landing pages — all without any API credentials.
✓Harness-model boundary erosion: As labs like Anthropic accumulate user behavior data, system prompts grow longer across model generations, then get compressed into the next model via reinforcement learning. This creates unpredictable behavior — Claude Code's current verbosity and inconsistency with Opus reflects this cycle. Users can counteract this with specific skills: invoke "bro skill" for plain-language explanations and "show me" for visual outputs instead of text walls.
✓Agentic commerce disruption: When shopping agents bypass human-facing UX — ignoring upsells, pop-ups, and recommendation engines — 25 years of ecommerce optimization becomes irrelevant. Merchants will need to build agent-readable interfaces rather than human-optimized storefronts. The open question is whether platforms like OpenAI become payment processors and marketplaces, creating conflicts of interest if they simultaneously know user preferences and profit from transactions.

What It Covers

Demetrios Brinkmann, founder of MLOps Community and head of development experience at the Agentic AI Foundation, joins Chris Benson to explore computer-use agents in daily workflows, the blurring boundary between AI harnesses and models, and how agentic commerce may restructure online shopping and payment infrastructure.

Key Questions Answered

•Computer-Use for form automation: Any web form — government portals, travel bookings, registrations — can be delegated to a computer-use agent without requiring API access. Demetrios uses this to handle German DMV appointments, flight check-ins, and boarding pass delivery automatically. The trigger: whenever you encounter a web form manually, that task is a candidate for computer-use delegation.
•Autonomous flight management workflow: A practical multi-step agent workflow handles travel end-to-end — searching flights, pre-filling passenger details from a stored document, monitoring inbox for check-in windows, completing check-in, and sending boarding passes to your phone. The only human touchpoint is the final payment confirmation click, keeping financial control while eliminating all surrounding friction.
•LinkedIn outreach without API access: LinkedIn's API is effectively locked down, but computer-use agents can trigger LinkedIn's native data export, monitor your inbox for the 48-hour delivery window, analyze DM history to identify two-way conversations, generate a shortlist of contacts, write personalized outreach messages, and create individualized media kit landing pages — all without any API credentials.
•Harness-model boundary erosion: As labs like Anthropic accumulate user behavior data, system prompts grow longer across model generations, then get compressed into the next model via reinforcement learning. This creates unpredictable behavior — Claude Code's current verbosity and inconsistency with Opus reflects this cycle. Users can counteract this with specific skills: invoke "bro skill" for plain-language explanations and "show me" for visual outputs instead of text walls.
•Agentic commerce disruption: When shopping agents bypass human-facing UX — ignoring upsells, pop-ups, and recommendation engines — 25 years of ecommerce optimization becomes irrelevant. Merchants will need to build agent-readable interfaces rather than human-optimized storefronts. The open question is whether platforms like OpenAI become payment processors and marketplaces, creating conflicts of interest if they simultaneously know user preferences and profit from transactions.

Notable Moment

Demetrios demonstrated computer-use to his non-technical wife by having it fully close and replace her PayPal account through natural voice input alone. Her immediate reaction shifted from tech avoidance to active curiosity — illustrating how this interface removes the skill barrier that has kept general users from adopting AI tools.

Know someone who'd find this useful?

Episode Transcript

Narrator: Welcome to the Practical AI Podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work, and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind the scenes content, and AI insights. You can learn more at practicalai.fm. Now onto the show. Chris: Hey. Welcome to another episode of the Practical AI Podcast. I am Chris Benson, your cohost. Daniel is out today, and he's really gonna miss this one because we have an old friend of the podcast who has been on multiple times, Demetrios Brinkmann, who is okay. Let's get the title right here, Demetrios. Head of development experience and a member of the nontechnical staff at the Agentic AI Foundation. And he's also, by the way, as most folks who have seen shows with us before, he's the founder of the MLOps community. Oh my god. That's the longest title, Demetrios, I think I've had to do on the show. Demetrios: I made it hard on you. Chris: You made it real I'll tell you what, I just read a paragraph. So great to have you back. I've lost count of how many times we've done this together. For those who are joining us that are not familiar with you, in addition to all these hats that you wear, amazing thought leader in the world of AI, I know we're gonna have some really good stuff to talk about today, and I know that the viewers and the listeners will enjoy this as much as I do. And before we start, I have to say, so after the last time we talked, you had sent me It's a super cool t shirt. It's one of my favorite bum around the house t shirts. I'm wearing it right now. For those who are watching us on YouTube, it says, I hallucinate more than chat GPT. So my wife is completely sick of seeing me wear it. It's faded red now. I'm sorry, man. Looked good when you gave it to me, but it doesn't look good anymore because it's all faded out. But that's because it's a fun t shirt to wear. Demetrios: I'm send you the next one. Anytime I wear it Chris: out, have to tell people. Everyone asks me about the hallucination thing. Then I have to also say, and just because there are people at my real job, I'm not hallucinating. Just so you know, there's no drug test required or anything. No hallucinating here whatsoever. So with all the fun start, this is probably not the show most viewers were expecting that we'd start with, but we always have fun. How are you doing? Things …

Get the full transcript (9,653 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Practical AI transcripts →