© Mapbox, © OpenStreetMap
Sergiu Wittenberger

Sergiu Wittenberger

Founder · Agentic Automation & IDP @ Wittenberger Industries

Cluj-Napoca, Romania

Actions

I build production AI agents and intelligent document processing for operational enterprises — banking, payments, government, and finance — from Cluj-Napoca and Timișoara.

Wittenberger Industries ships agentic automation where judgment and unstructured input matter, and RPA where the steps are fixed. Recent work includes hyperscale IDP on Kubernetes (5,000 docs/hour, ~14× faster than a robot fleet), agentic voucher validation (~71% faster, 72h → 18h cycles), a Teams-native ERP assistant (Mia), and an Outlook-embedded sales agent grounded in internal precedent.

Previously at UiPath I led technology services teams on Document Understanding and Human-in-the-Loop. I still speak and build at the intersection of UiPath, Python, agents, and cloud scale.

Site: https://wittenberger.io
LinkedIn: linkedin.com/in/sergiu-wittenberger
GitHub (HyperDU early public cut): github.com/UiPath-Services/HyperDU

Area of Expertise

  • Business & Management
  • Information & Communications Technology

Topics

  • RPA
  • Agentic automation
  • Orchestration
  • UiPath
  • AI Agents
  • Kubernetes / hyperscale
  • Document Understanding
  • Human-in-the-Loop
  • Cloud (Azure / AWS)
  • Intelligent Document Processing (IDP)

Hyperscale IDP without a robot fleet

One robot = one licence does not survive 5,000 documents an hour. We replaced a UiPath robot fleet with a containerised Python service calling Document Understanding APIs, then put it on Kubernetes with KEDA on Azure and AWS. Same 100-doc test: 21 minutes → 1 minute 30 seconds (~14×). Lessons on licence economics, autoscaling, and when to leave the robot path entirely. Early public cut: github.com/UiPath-Services/HyperDU

How to scale your IDP process on Azure or AWS using UiPath APIs and Python

Enterprise examples of Agentic Automation

Concrete production stories of agents in the enterprise: voucher processing with Claude + UiPath (~3,500 tx/month, rule-perfect validation, 72h → 18h), an Outlook sales agent grounded in internal precedent, and Mia — a Teams-native agent that replaced Workday/Jira timesheets with chat. Where agents win, where pure RPA still wins, and how we evaluate and guardrail them before they touch real work.

Agents vs RPA: pick the boring tool on purpose

A decision framework from shipping both. Fixed steps + structured inputs + stable UI → pure RPA. Judgment, unstructured docs, or unstable UI → agents. Mixed stacks and how we keep cost, audit, and first-pass accuracy (98%+) under control when you combine them.

Witloop: from conversation to open PR across Cursor, Claude, Copilot, and Grok

Most agent coding demos stop at a chat transcript. Witloop is an open plugin that runs a Spec-driven loop from idea to pull request on four hosts: Cursor, Claude Code, GitHub Copilot CLI, and Grok Build. One install, five entry points — setup, scan, Dev, RPA, add-issues — with you speaking at brainstorm and a design gate; research, plan, build, check, and ship run autonomously after that. I'll show how /wit:dev routes feature vs bug-fix vs investigation, how /wit:rpa turns a UiPath PDD into REFramework or Maestro work, what lands in .wit/ on a project, and lessons from shipping the same skills across four agent hosts. Repo: https://github.com/Wittenberger-Industries/witloop

PeakIT

April 2025 Braşov, Romania

Sergiu Wittenberger

Founder · Agentic Automation & IDP @ Wittenberger Industries

Cluj-Napoca, Romania

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top