---
title: AI Agents in Practice -Beyond the Prototype (slides and video from my AI Fokus talk)

date: 2026-06-04
excerpt: Making an impressive prototype is easy. But what about the icky stuff that comes after - real-life deployment, scaling, monitoring, optimization, data architecture, safety? 

---

# AI Agents in Practice -Beyond the Prototype (slides and video from my AI Fokus talk)



> Making an impressive prototype is easy. But what about the icky stuff that comes after - real-life deployment, scaling, monitoring, optimization, data architecture, safety? 

On May 19 I gave a talk at [AI Fokus 2026](https://www.ai-fokus.se/schedule.html) in Stockholm, titled “AI Agents in Practice - Beyond the Prototype”, using real-life examples from agents on the Abundly platform.

- [Slides](https://www.dropbox.com/scl/fi/jb8efza6w8ktgtjbmfs6y/2026-05-19-AI-Fokus-AI-Agents-in-Practice.pdf?rlkey=f6lxx73834or7urw7qqr2gvfe&dl=0)
- [Video recording](https://www.youtube.com/watch?v=clKvOQrxj8Q)
![Henrik speaking at AI Fokus](image-788521235c082cab8ea0b79d07d79e78f220d9c2-4200x2801-jpg)


**Key points from the talk:**

- **Team-based agents > personal assistants.** Abundly agents are designed to work as team members, rather than personal assistants. They work in the same tools you do — Slack, GitHub, Notion — and communicates with other team members and not just you.
- **Impressive ≠ useful.** Building a cool agent demo is easy now. Making one that's actually useful day-to-day takes more time and persistence than you'd expect — but it pays off big time.
- **Finding golden use cases takes experimentation.** Look for tasks that waste your time, take a lot of effort, and don't require much creativity. That's where agents shine. For every home run, expect a bunch of duds.
- **The post-prototype blues are real.** After the initial wow, you sometimes hit a valley where the agent makes mistakes or costs too much. Don't give up — keep iterating. Agents aren't built, they're grown.
- **Think of your agent as a super intern.** It needs clear context, the right tools, feedback, and supervision — at least in the beginning. When it messes up, don't blame it. Figure out what context it was missing.
- **Context management is the #1 optimization lever.** Not too little (it guesses), not too much (it gets confused). Use progressive disclosure — let the agent fetch what it needs, when it needs it.
- **Agents can self-improve, with guardrails.** Let them update themselves based on feedback, but not autonomously. Predictability matters.
- **Safety is a design trade-off.** Broader scope and more tools = more power but more risk. Use hard guardrails (whitelists, approval flows) instead of relying on the LLM to remember instructions.

**Here are some sample slides:**


![Personal assistant vs Team member](image-51a283c52d2b7f1ebc8783a9f91e8dfba185cc77-2496x1438-png)

![Data architecture](image-8ca67dd69b5d62ef5c7de0626fa9a334a8dca36b-3104x1620-png)

![Growing your agent org](image-e618dd3c88c3fa4e732c37e4d806645f40af235e-2994x1784-png)

![Think of your agent as a super trainee](image-c1247e1aa0d3f22219e3bb18c8c91af7b19bcfc9-3126x1758-png)

![Lagom amount of context](image-de761e4f590b779338b1499fd9da185bcce50f20-2986x1644-png)

![Key points](image-c5b2b59c2d7a62e9301c0eac74a5ffb3e2a7c4b9-3204x1798-png)

---

*Read the full article at [https://www.abundly.ai/blog/20260519-ai-agents-in-practice](https://www.abundly.ai/blog/20260519-ai-agents-in-practice)*