> Markdown version of [/events/world-congress-2026-europe/sessions/1113-rules-heuristics-or](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1113-rules-heuristics-or). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Rules, Heuristics, or LLMs? Lessons from Solving the Same Problem Twice


- **Date:** Thursday, Jul 9, 2026
- **Time:** 14:50–15:20 (30 min)
- **Room:** Stage 6 - powered by Microsoft
- **Event:** World Congress 2026 Europe

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/100112-rules-heuristics-or-llms-lessons-from-solving-the-same-problem-twice)

## Description

Not every problem needs an LLM. But at the same time some problems are asking for LLMs as the solution. So, when to choose which?

I ran into this while working on a subjective text transformation problem. It’s hard to specify and hard to test. That made it into a brilliant grey zone. When the answer to the regular regular question "can it be done without LLM" is "yes, but...". 

To understand the trade-offs, I built two solutions to the same problem. Both of them produce similar result, they just work in a very different way.

One is a "just code and math": rule-based stochastic system using Markov chains, edit-distance mutations and so on. The other is a LoRA fine tuned LLM trained on the examples.

In this talk, I'll share what I learned, so that you could build just one system, instead of two: 

Where deterministic models offer better control
Where LLMs produce more natural results
How the results are different
Maintenance cost

As the problems sits in a grey zone and hard to properly measure, I will show a result of blind comparison between rule-based output and LLM output to determine whether LLM solution was necessary or overkill.

This is not a tutorial or an AI demo. You’ll leave with a practical way to understand and decide when the problem is LLM-worthy and when to stick to the good old code and algorithms.
It's a case study on how over-engineering once on purpose can save future effort and resources.

## Speaker

### [Artur Naumenko](https://www.wearedevelopers.com/@artur-naumenko)

Senior Software Engineer at Softeta


## Related talks at this congress

- [Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1158-cutting-llm-costs) — Viktoria Semaan
- [From Hallucination to Justification: Hands-On Explainability for LLMs](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1239-from-hallucination) — Lucía Conde-Moreno, Tessel Haagen
- [The LLM Evolution: From Sequence Imitation to Verifiable Reasoning](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1377-the-llm-evolution) — Kamen Petroff
- [Teaching an LLM to review code … like a Senior Engineer!](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1367-teaching-an-llm-to) — Kesha Mykhailov