Training - Build and Test a Document Assistant with IBM watsonx.ai
About This Event
Learn how to build a working AI document assistant that extracts key details from contracts, checks them against business rules, and tests the accuracy of its results.
After this course you can
- 01- Extract five key contract fields into a defined JSON structure using a foundation model.
- 02- Validate JSON output, show supporting clause text and mark missing information without inventing values.
- 03- Use simple Python rules to flag differences from a procurement playbook.
- 04- Measure field accuracy and JSON validity, and compare two prompt versions on the same test documents.
- 05- Explain how scanned-PDF text extraction with Docling can affect the assistant’s results.
Use code LAUNCH100 for free access.
Industry experts sharing their knowledge
Saleem Pothiwala
CEO
KERMIT TECH AS
28+ years in data. Built Kermit Tech to help Nordic and Middle East enterprises turn data into competitive advantage. He helps teams build and use data and AI solutions, with hands-on experience across finance, research, and nonprofit organizations. An IBM StreamSets Black Belt, Saleem teaches through practical examples and guided exercises. His courses help learners turn technical concepts into skills they can use at work.
LinkedIn
Eman Fatima
AI Engineer
KERMIT TECH AS
Syeda Eman Fatima is an AI/ML Engineer working across the full machine learning lifecycle. She builds data pipelines as code, with version control.
LinkedInEvent Agenda
Training Modules 1-4
Lunch Break
Training modules 5-6
Brought to you by
