ABBYY Hackathon 2025 Winners Showcase AI Solutions for Enterprises
ABBYY Hackathon 2025 winners demonstrated innovative Document AI, AI Agents, and GenAI solutions to tackle enterprise challenges, with teams from Deloitte, McKinsey, and Telstra taking top honors.
ABBYY hosted its third annual AI Pulse Developer Conference and Hackathon on July 9-10, 2025, in Bengaluru, India. The event brought together 35 entrants who developed innovative solutions using Document AI, AI Agents, and Generative AI to solve real-world enterprise challenges. Four teams stood out, winning categories such as Best Overall App, Best Use of an ABBYY Product, Best Integration of Third-Party AI, and an honorary Student Excellence Award.
AI Pulse by ABBYY Developers Conference was held July 9-10, 2025, in Bengaluru, India.
Winning Teams and Innovations
Best Overall App: Team Deloitte
- Solution: Spend Guard – Automated expense receipt scanning, interpretation, and validation.
- Tech Used: ABBYY Vantage for data extraction and Gemini for agentic AI to ensure policy compliance.
- Impact: Accelerated expense claim processing, reduced manual effort, and minimized errors.
Quote from Rithi M (Team Deloitte):
"Participating in the ABBYY Developer Conference was an incredible opportunity to push the boundaries of what’s possible with AI-driven document processing."
Best Use of an ABBYY Product: Team McKinsey
- Solution: Smart Translator – Broke language barriers in global document processing.
- Tech Used: ABBYY Vantage for data extraction and ChatGPT for context-aware translation.
- Impact: Eliminated manual data entry and translation, saving time and reducing errors.
Quote from Sathish Kumar Murugan (Team McKinsey):
"Building Smart Translator showed us how AI and intelligent OCR can come together to solve real-world challenges."
Best Integration of Third-Party AI: Team Telstra
- Solution: Insurance AIdvisor – Simplified health insurance policies using AI.
- Tech Used: ABBYY Vantage, spaCY, OpenAI Embeddings, ChromaDB, LangChain Agents, and Gradio.
- Impact: Helped users avoid denied claims and financial shocks due to complex policy jargon.
Quote from Madhu Shankar (Team Telstra):
"ABBYY’s strategic evolution positions it as a key enabler in the development of autonomous, decision-capable AI systems."
Student Excellence Award: Team CMRIT
- Solution: SILO AI – Unified document automation toolkit for workflows like invoices and contracts.
- Tech Used: ABBYY models, n8n workflow, and MCP server for Slack/Gmail integration.
Quote from Sarvottam Bhagat (Team CMRIT):
"We competed with companies like Tech Mahindra, Wipro, and Deloitte. It was a phenomenal learning experience."
ABBYY’s Vision and Resources
Neil Murphy, ABBYY Chief Revenue Officer, emphasized the event’s goal:
"We wanted to build a global community where developers could reimagine what’s possible with AI and documents."
Resources:
- Download the playbook: Next-Generation Document Automation
- Subscribe to the AI Pulse podcast and e-newsletter.
About ABBYY: A global leader in Process AI and Document AI, serving over 10,000 customers, including Fortune 500 companies. Learn more at www.abbyy.com/company.
Editorial Contact: Gina Ray | gina.ray@abbyy.com | +1 949-370-0941
Related News
Zscaler CAIO on securing AI agents and blending rule-based with generative models
Claudionor Coelho Jr, Chief AI Officer at Zscaler, discusses AI's rapid evolution, cybersecurity challenges, and combining rule-based reasoning with generative models for enterprise transformation.
Human-AI collaboration boosts customer support satisfaction
AI enhances customer support when used as a tool for human agents, acting as a sixth sense or angel on the shoulder, according to Verizon Business study.
About the Author

Alex Thompson
AI Technology Editor
Senior technology editor specializing in AI and machine learning content creation for 8 years. Former technical editor at AI Magazine, now provides technical documentation and content strategy services for multiple AI companies. Excels at transforming complex AI technical concepts into accessible content.