WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • May 26, 2021

Intelligent Automation using Machine Learning

Boris Krumrey , Andreas Palfi , Radu Pruna

Are brittle selectors breaking your automated workflows? Discover how machine learning models replace hardcoded logic to deduce rules, handle exceptions, and drive definitive business actions.

Pause
Mute Enter Fullscreen
#1 about 8 min

Introduction to UiPath and robotic process automation

The platform evolved from basic screen scraping algorithms to intelligent interface understanding using complex computer vision models.

#2 about 10 min

How machine learning approximates reality through mathematical functions

Algorithms estimate the best mathematical function from historical data sets to describe relationships between inputs and outputs.

#3 about 2 min

Deducing rules from data instead of manual programming

Machine learning models automatically learn decision rules from data characteristics instead of requiring explicitly coded logic statements.

#4 about 5 min

Overview of supervised, unsupervised, and reinforcement learning

The major categories of machine learning solve discrete business use cases through structured classification and regression approaches.

#5 about 5 min

Core stages of training and managing machine learning models

Real data science efforts heavily involve data processing pipelines and engineering tasks rather than simply tuning state-of-the-art algorithms.

#6 about 7 min

Moving machine learning models into production automation flows

Integrating prediction engines into user applications enables operational teams to act upon predictions and continuously retrain models.

#7 about 10 min

Using automation as the foundation for digital transformation

Companies scale digitization efforts by deploying automation flows that generate the metadata required for subsequent artificial intelligence initiatives.

#8 about 11 min

Building an end-to-end platform for automation and AI

Extending rule-based robotics with integrated cognitive capabilities enables robust task optimization across complex enterprise software environments.

#9 about 4 min

Processing unstructured data through intelligent document understanding

Combining robotic process automation with continuously trained models allows accurate data extraction from customized forms and handwritten papers.

#10 about 3 min

Uncovering automation opportunities via process and task mining

Machine learning tools analyze system logs and desktop interactions to visualize poorly standardized manual tasks that need optimization.

#11 about 11 min

Operationalizing custom and pre-built machine learning models securely

Connecting various narrow intelligence tools via application programming interfaces expedites secure model deployment for non-technical software developers.

#12 about 7 min

Break and automated assistant feature recorded demonstrations

Recorded system demonstrations show a locally running automation assistant handling resume screening and new employee onboarding flows.

#13 about 4 min

Selecting context-appropriate performance metrics for prediction models

Applying highly imbalanced training sets requires robust accuracy metrics like F1 scores rather than naive overall capability measurements.

#14 about 8 min

Predicting overdue invoices to improve accounts receivable collection

Classifying historical customer payment behaviors helps financial teams flag late payments before their assigned scheduling due dates.

#15 about 10 min

Transforming tabular metrics into meaningful business value dashboards

Structuring complex gradient boosted output into monetary confusion matrices enables operational stakeholders to prioritize financial payment collection efforts.

#16 about 13 min

Building a comprehensive accounts receivable cash collection application

A backend virtual machine triggers system scripts that pull client invoice data to predict delinquencies via deployed machine-learning backends.

#17 about 9 min

Executing independent automation workflows outside browser environments

Connected endpoint robots execute localized backend processes rather than utilizing client-side web browser compute processing constraints.

#18 about 5 min

Identifying appropriate business use cases for deploying artificial intelligence

Ideal automation targets involve high-volume, variable workflows where traditional deterministic rule-based logics become practically impossible to maintain accurately.

#19 about 7 min

Calculating return on investment and comparative software advantages

Dedicated evaluation portals synthesize operational effort requirements against monetary benefits while supporting both localized and cloud-deployed orchestration software methods.

Matching moments

4:01 min

Transitioning artificial intelligence into operational business environments

Stefan Donsa Stefan Donsa +1 · LIVE

2:05 min

Enhancing case matching with integrated machine learning tools

Clemens Schwaiger · LIVE

4:37 min

Introduction to the speakers and process automation transformation journey

Kevin Kaiser Kevin Kaiser +1 · WWC 2025

1:12 min

Building intelligent applications and enhancing developer productivity experiences

Alexander Wallner Alexander Wallner +3 · WWC 2024

4:15 min

Introduction to artificial intelligence driven development

Natalie Pistunovich · LIVE

2:54 min

Mapping AI integration across the software development lifecycle

Mike Mike · WWC 2025

More from WeAreDevelopers LIVE

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail
5:43
5 days ago

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail
1:08:30
5 days ago

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail
1:10:26
12 days ago

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail
1:02:34
19 days ago

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail
1:07:59
26 days ago

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail
5:55
about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

Open session

World Congress 2026 North America

AI ROI: The Hard Unit Economics of AI-Native Engineering

Manu Gurudatha

Manu Gurudatha, VP of Engineering at PagerDuty

Manu Gurudatha
Open session

World Congress 2026 North America

Building Pragmatic AI: 10 AI Features Your Users Actually Want

Jonathan "J." Tower

.NET Foundation Board | 12x Microsoft MVP | Founder & Consultant

Jonathan "J." Tower
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Beyond the Code: Human-AI Synergies in Product Development

Ajita Kanchivakam Ananth

Staff Technical Program Manager at Google

Ajita Kanchivakam Ananth
Open session

World Congress 2026 North America

AI Decision Observability: Enabling Transparency and Trust in Intelligent Systems

Amjad Shaikh, Soumil Mandal

Amjad Shaikh
Soumil Mandal

Related videos

Detecting Money Laundering with AI thumbnail
29:37
LIVE • over 5 years ago

Detecting Money Laundering with AI

Stefan Donsa, Lukas Alber

When AI Runs the Business: The Reality of Enterprise-Wide Automation thumbnail
29:53
WWC Europe 2026 • about 1 month ago

When AI Runs the Business: The Reality of Enterprise-Wide Automation

Axel Schell, Michael Ameling, Ines Erker

Hard Problems Hide in Boring Places: Turning Accounting Workflows into AI Products thumbnail
21:52
WWC Europe 2026 • about 1 month ago

Hard Problems Hide in Boring Places: Turning Accounting Workflows into AI Products

Oleksandr Korotkykh, Tolga Sümer

The Limits of LLMs in Real-World Applications thumbnail
31:07
WWC Europe 2026 • about 1 month ago

The Limits of LLMs in Real-World Applications

Deivids Vilkinsons, Guillaume Esnou, Laura Moritz, Mariam Hakobyan

How to achieve web automation with UiPath thumbnail
2:01:35
JS Congress • over 4 years ago

How to achieve web automation with UiPath

Alp Uguray

The Deichmann RPA journey: Step by step with low-code automation to success thumbnail
28:53
WWC 2025 • 12 months ago

The Deichmann RPA journey: Step by step with low-code automation to success

Niklas Blumenthal, Tobias Bernhardt

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.