HKPUG #94 - Controlling Reality: Tests & AI Memory

Date: 13 February 2026 (Fri)
Time: 19:20 - 21:00 *HKT
Coordinator: Alex Au

Light Refreshments will be available! Please also tell us whether or not you will join our pizza night 🍕!

Please fill in the form for admission:
https://forms.gle/r8zHKak5cnZxpQ1V9

Topics:

Taming Regression – Real-World PyTest (Alex Au)

• Learn to write tests that catch real issues, not just satisfy mocks.
• Learn how to design-for-testability and why "integration is truth"
• VCR proxy pattern, Environment State management (freezing time & hacking DNS!) and AI-driven spec development

Long Term Memory for Google ADK Agents (Tarun Jain)

• Learn why Long Term memory of Agentic Workflow is needed
• Knowledge-graph-based memory (using Cognee), multi-hop reasoning and temporal state tracking
• Short demo using Google ADK, Cognee and Qdrant

Capacity: 80

Venue Info:
City University of Hong Kong, Kowloon Tong (Exact location will be updated)

Rundown:

• 19:20 - 19:30 Opening Remarks / Upcoming Events
• 19:30 - 20:00 Taming Regression – Real-World PyTest (Alex Au)
• 20:00 - 20:10 Break & Networking
• 20:10 - 20:50 Long-Term Memory for Google ADK Agents (Tarun Jain)
• 20:50 - 21:00 Closing & Pizza Night

Speakers Bio:

Alex Au
Alex is a Cloud Platform Engineer with experience in backend development and machine learning systems. He works on AI and cloud-native platforms and contributes to open-source projects. Alex is active in the Hong Kong Python community (coordinating meetups & PyCon HK) and is passionate about writing robust, testable code and efficient system designs.

Linkedin: https://www.linkedin.com/in/alex-au-cloudeng

Tarun Jain
Tarun is a Founding Engineer, and Content Creator at AI with Tarun. He is also a Google Developer Expert AI. He was a maintainer to open source AI projects like OpenAGI and BeyondLLM and has spoken at international conferences. Tarun enjoys building intelligent systems, knowledge graphs, and long term memory solutions for AI agents.

Linkedin: https://www.linkedin.com/in/jaintarun75/

Audience pre-requisite:

• Recommended having intermediate-level knowledge about Python (1 or more year of experience)

How to join?

• Fill in the form for admission: https://forms.gle/r8zHKak5cnZxpQ1V9
• Click "Attend" in this page