> Markdown version of [/events/world-congress-2026-europe-virtual-stage/sessions/1609-taming-the-beast](https://www.wearedevelopers.com/events/world-congress-2026-europe-virtual-stage/sessions/1609-taming-the-beast). 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).

---

# Taming the Beast: Building Autonomous Agents to Solve German Tax Bureaucracy


- **Event:** World Congress 2026 Europe - Virtual Stage

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/1965-taming-the-beast-building-autonomous-agents-to-solve-german-tax-bureaucracy)

## Description

German accounting is notoriously complex, running on a "deprecated backend" of physical paper, rigid bureaucratic rules, and a shrinking workforce of tax advisors—30% of whom are retiring soon. For developers, this presents the ultimate "legacy refactoring" challenge: How do you replace a manual, high-stakes human process with an autonomous agent without causing legal failures?

In this session, we dive into the architecture of Mika, an AI financial autopilot that has moved from 70% to 95% automation. We will move beyond the hype to examine the specific engineering patterns used to solve a domain where a 0.1% error rate is unacceptable.We will dissect three core components of our architecture:
- The Multi-Agent Document Swarm: How we orchestrate specialized agents (Classifiers, Validators, and Knowledge Base RAGs) to navigate the nuances of German tax law better than a human.
- The "Todo Firewall": A self-learning feedback loop that utilizes structured memory to determine when to disturb the user and when to autonomously overrule strict validation errors.
- Solving the O(N^2) Matching Problem: A deep dive into our 3-layer transaction matching engine. We will show how we combine classical ML ensembles with semantic LLM agents to match thousands of invoices to bank transactions with a 91.8% F1 score—all while adhering to strict Serverless memory constraints.

Join us to learn how to build "Agentic Workflows" that are not just chatty, but capable of handling the heavy lifting of a real-world complex use case.


## Speaker

### [Mohamed Dhiab](https://www.wearedevelopers.com/@mohamed-dhiab)

Senior Software & AI Engineer at Mika


## Related talks at this congress

- [Your AI Agent is just a while loop with an API call. Let me prove it](https://www.wearedevelopers.com/events/world-congress-2026-europe-virtual-stage/sessions/1655-your-ai-agent-is) — Michał Michalczuk
- [MAD About Software Design - When AI Architects Argue](https://www.wearedevelopers.com/events/world-congress-2026-europe-virtual-stage/sessions/1569-mad-about-software) — Lior Schejter
- [AI Agents & Agentic AI](https://www.wearedevelopers.com/events/world-congress-2026-europe-virtual-stage/sessions/1481-ai-agents-agentic-ai) — Xavier Sala Presas
- [Same Words, Different Worlds: Who's in Control?](https://www.wearedevelopers.com/events/world-congress-2026-europe-virtual-stage/sessions/1594-same-words-different) — Christina Rohrmoser, Stefan Wöhrer