FDE Műhely
HU Let's talk

Learn

Blog

How an AI idea becomes a system that actually runs in production: process discovery, evals, exception handling, ROI and deployment in real enterprise environments.

  • For leaders
  • Discovery
  • Evals
  • Deployment
  • Fundamentals
  • Career
  1. Discovery The documented process and the real one Every company has two processes: the one written down, and the one that runs. AI deployments build on the first. Here is how to capture the second. 3 min read
  2. Discovery How an AI discovery works, step by step What an FDE does during the two to four weeks of discovery, who they talk to, what they pull from your systems, and exactly what you get at the end. 3 min read
  3. Discovery What is worth automating, and what is not Not every process deserves attention. How we rank workflows on volume, recoverable time, risk and feasibility, and why the first project isn't the biggest one. 3 min read
  4. Evals How to measure whether your system really works “Looks good” isn't a result. How a non-deterministic system becomes a measurable number, and how you find out where the errors really come from. 2 min read
  5. Evals Building a golden dataset in practice How to assemble a measurement set from your own historical cases that genuinely tells you whether the system works, and the mistakes to avoid. 3 min read
  6. Evals How to evaluate a task with no single right answer A summary or a deck can be done well a thousand ways. It's still measurable: break it into criteria and build in human feedback from the start. 2 min read
  7. Deployment Where approval should stay with a human Human-in-the-loop isn't a compromise, it's a design decision. Where to keep a person in the process, and how to stop approval degrading into rubber-stamping. 2 min read
  8. Deployment Everything rides on the unhappy paths A process goes right one way and wrong several hundred ways. Build only for the happy path and you've built a demo, not a system. 3 min read
  9. Deployment If you can't see what it did, you won't trust it An audit trail isn't a nice-to-have, it's a precondition for going live. What to log in an agent, in what form, and what people actually do with it. 2 min read
  10. Deployment Don't replace your ERP. Build on it. A company that spent two years migrating doesn't want another migration. Why building on existing systems is the only viable route, and how we do it. 2 min read
  11. Deployment Going live without anyone carrying the risk The system runs but doesn't decide. Why this is the most useful six weeks of a deployment, what to measure during it, and when you can move on. 2 min read
  12. Fundamentals Which model should you use? Wrong question. Model choice is a measurement, not a belief. How to build so the model stays swappable, and when switching is actually worth the effort. 2 min read
  13. For leaders How to burn a year's inference budget in three months Handing everything to the model is more expensive, slower and less reliable than code would have been. Where the money goes, and what to do instead. 2 min read
  14. For leaders How to measure AI ROI so finance accepts it Three groups of metrics matter: cost savings, risk reduction and revenue impact. How to turn each into defensible numbers without cheating. 2 min read
  15. Career A 30-day plan to become a forward deployed engineer Four weeks, week by week: build a real agent, make it survive reality, measure it, and learn to defend it in business language. With concrete checkpoints. 3 min read
  16. Fundamentals Six situations where AI is the wrong answer One of the most valuable sentences an FDE can say is “no model belongs here”. Six situations where AI is a worse answer than a rule or a better form. 2 min read
  17. Career The two sides an FDE has to master An FDE isn't the average of a consultant and a developer, but the best of both. What that means in skills, and how to build the weaker side. 2 min read

Prefer a reader? RSS feed.