DOP 359: Demos in the Age of AI Agents

Episode 359

Show Notes

#359: When was the last time you sat through a 30-minute product demo and walked away actually knowing anything? You would learn more from five minutes hands-on than an hour of watching someone else drive.

Now you have help. An agent can watch the 30-minute video, play in the sandbox, read every page of the docs, and come back before you finish your coffee with a verdict - tried it, does not work, next. The agent is the new tire kicker. So if you are a vendor, an open source maintainer, or the person building the internal app nobody outside the building ever sees, the demo you have been giving is aimed at a buyer who already left the room.

Your job now is to make life easier for agents. An MCP server, a CLI, skills, an AGENTS.md file, not blocking your own site with Cloudflare when someone’s agent tries to read your pricing. Everything that makes a product easy for an agent would have made it easier for a human all along. We just never bothered, because we had months to burn. Now the clock runs in minutes and every corner we cut is suddenly on fire.

Three kinds of demo, three different answers. The vendor sales demo is off-putting before it starts - if a website says book a call to try it, Viktor is already gone. Open source barely needs a demo at all: a good README, a quick start, an AGENTS.md, and the agent assembles a demo tailored to your stack, your database, your questions, instead of some generic happy path. Internal is where it gets good, and it might be the one that matters most since exactly zero apps ship without customization. Viktor’s bar: stop showing me plans, show me the thing running. Sit the stakeholder down and build it live while you talk. Three days to a prototype instead of 300 pages of PRD.

Sandboxes first, demos second - if you cannot spin up a sandbox, you did not build it right. And demo the failure modes, not the happy path, because resiliency is the real selling point now. Disks still fill up. No amount of AI magic empties them for you.

Frequently Asked Questions

Are product demo videos still worth making?

Viktor Farcic says on DevOps Paradox episode 359 that he rarely watches one and mostly runs demos himself. For an open source project he argues a good README, a quick start, and an agents.md file cover it. Darin Pope keeps a place for video but caps it tightly: five minutes for a technical viewer trying to solve one thing, ten at the outside, and only if it stays tight throughout.

What does making a product agent-friendly actually mean?

Viktor Farcic’s answer on DevOps Paradox episode 359 is that every level of a product should make life easier for agents, whether that means an MCP server, a CLI, skills, or simply not blocking your own site from them. He describes asking Claude to gather one cloud provider’s pricing shortly before recording and getting back a Cloudflare block. Darin Pope adds clean markdown, llms.txt, and a published OpenAPI spec.

Do AI agents need different documentation than humans?

Viktor Farcic argues on DevOps Paradox episode 359 that the rules are the same for both for now, and puts an equals sign between them. He rates agent-specific documentation as good rather than critical, since sifting through HTML costs more tokens but changes little he notices. What did change is speed: thin documentation was survivable when the work around it was measured in months.

Why do AI-assisted contributions to an open source project go badly?

Viktor Farcic turns that question back on maintainers in DevOps Paradox episode 359, asking whether the repository was made agent-ready or simply left to let an agent fantasize. A maintainer who works well with agents on their own project usually knows the right instructions but has never codified them for anyone else. Darin Pope adds that codifying them matters because the project outlives whoever maintains it today.

What should an internal demo show?

Viktor Farcic says on DevOps Paradox episode 359 that he no longer wants to see plans from anybody. Pitching a new feature means showing the feature working, and it does not have to be production ready or written the way he would write it. Darin Pope frames the payoff as a demo tailored to whoever is asking, so a stakeholder focused on accounts payable and one focused on HR see different things.

Is it too expensive to run an AI agent live during a customer meeting?

Viktor Farcic’s answer on DevOps Paradox episode 359 is no, and the comparison he reaches for is the salaries in the room. A single agent running continuously could not approach what one attendee costs a company over a year, so an hour of it is trivial against the meeting itself. For a prepared demo, with environment, skills and CLIs already set up, he rates Haiku as overpowered.

What is the DevOps Paradox podcast?

DevOps Paradox is a weekly podcast co-hosted by Darin Pope and Viktor Farcic, covering DevOps, platform engineering, and modern software delivery. Episode 359, “Demos in the Age of AI Agents,” works through what happens to vendor demos, open source onboarding, and internal stakeholder demos once the thing evaluating your product is an agent. Every episode page carries the audio, the video, and a full transcript.

Share and Download

Hosts

Viktor Farcic

Viktor Farcic

Viktor Farcic is a member of the Google Developer Experts and Docker Captains groups, and published author.

His big passions are DevOps, Containers, Kubernetes, Microservices, Continuous Integration, Delivery and Deployment (CI/CD) and Test-Driven Development (TDD).

He often speaks at community gatherings and conferences.

He has published DevOps Paradox and Test-Driven Java Development.

His random thoughts and tutorials can be found in his blog The DevOps Toolkit.