Category: Blog

When people talk about Generative AI, the focus is usually on:

• Prompting
• LLMs
• Chatbots
• Proofs of Concept (POCs)

But what I am missing a lot in those conversations are:

1. Try classic automation first
2. Process integration: Can I add it into a process so that it fixes a problem?
3. Data privacy
4. Security
5. Works council/employee representation (if applicable)
6. Observability (not just the usual observability but also prompts and responses)
7. Robust data pipelines (a.k.a ETL)
8. Model Selection
9. Model decay & re-evaluation (How often will you need to update? Currently about ~1x / year)
10. Regulatory Compliance AI Act (EU)
11. Costs (Tokens, maintenance, scaling — over years, not demo days)
12. Scalability
13. Latency & Performance:
14. Testing (“it works in demo” ≠ “it works in production with real users”)
15. Human-in-the-Loop (HITL):
16. The other 95% of the app (The “boring” software stack around the AI)
17. APIs (If it’s meant to automate, it needs to talk to other systems)

If there’s a user interface:

• Interface design & UX (no one uses what they can’t understand)

And the elephant in the room:

• How do you address the fear—justified or not—that you might be innovating people out of their jobs?

---