A Singapore Government Agency Website
How to identify
Official website links end with .gov.sg
Government agencies communicate via .gov.sg websites (e.g. go.gov.sg/open). Trusted websites
Secure websites use HTTPS
Look for a lock () or https:// as an added precaution. Share sensitive information only on official, secure websites.
LogoLogoHomeAboutFAQsEventsProblem Statements
LogoLogo
Sign up here

{build} Hackathon & Incubator

Are you ready to be part of the next {build}?

Contact UsReport VulnerabilityPrivacy StatementTerms of Use
GovTech 10th AnniversaryGovTech 10th Anniversary

© 2026 Government Technology Agency of Singapore | GovTech

Projects/Data & AI
ASK-O-MATIC

ASK-O-MATIC

A Multi-modal Local LLM designed for Digital Business Analysts to bridge knowledge gap

Booth DA14

ASK-O-MATIC

Team Members

Raymond Kwan, Terence Yap, Terence Lim, Jack Zhang, Roland See and Huang Ming Kang

Project Description

ASK-O-MATIC: Bridging the Knowledge Gap for Digital Business Analysts

Introduction

In the fast-paced digital landscape, businesses often waste countless hours deciphering legacy system documentation. This inefficiency leads to frustration, incorrect implementations, and missed policy timelines, ultimately costing organizations up to $360K per year.

The Solution: Ask-O-Matic

Ask-O-Matic is a local multi-modal Large Language Model (LLM) designed to help digital business analysts interpret complex, outdated, and poorly written documentation. Unlike standard LLMs, which struggle with structured formats like tables and flowcharts, or AI assistants that lack support for confidential documentation, Ask-O-Matic excels at both. It leverages an advanced multi-modal LLM capable of processing both text and images, running locally to ensure compliance with Confidential (High) security standards.

Key Impacts

Ask-O-Matic delivers tangible benefits, including:

  1. Faster Time to Market
    By improving the efficiency of policy interpretation, Ask-O-Matic accelerates policy implementation by 25%, reducing implementation timelines from 4 months to 3 months.

  2. Cost Reduction
    By minimizing policy rework and reducing knowledge gaps, Ask-O-Matic helps prevent policy service requests (SR) from unnecessary revisions, saving an estimated $120K to $360K per year.

  3. Enhanced Documentation, Better Outcomes
    Well-documented code fosters better collaboration, attracting 47% more contributions, reducing knowledge gaps, and mitigating frustration caused by rework.

Technology Stack

Ask-O-Matic is built using cutting-edge technologies, including:

  • LLM Model: LLaMA 3, Florence-2 Large, and Nomic Embedded Text
  • LLM Server: Optimized for secure local deployment
  • Front-End: Fast and interactive UI powered by modern frameworks
  • Back-End: Efficient data processing and API support

Conclusion

With its multi-modal processing capabilities and secure local deployment, Ask-O-Matic provides a robust solution for digital business analysts. By bridging knowledge gaps, it significantly reduces operational inefficiencies, enhances documentation quality, and optimizes policy implementation.

Back to all projects