Artificial Intelligence

We interrupt our usual programming - to bring you [adisbladis](https://blad.is/), our sometime resident [Nix](https://github.com/nixos/nix) expert at Dim Sum Labs - for this HackJam. Nix is a powerful package manager that can help you setup your OS and environment exactly the way you want it, with perfect reproducibility, reliability and easy rollback. It's not the easiest to setup however. So Adam is here to help. Whether you are curious about Nix and want to see it in action, have specific problems that need help with, or just want to talk shop with other Nix enthusiasts, this is your chance to work with one of the world's foremost expert in Nix! More about adisbladis: [Adisbladis](https://blad.is) is a freelance Nix consultant & nixpkgs committer, where he mostly enjoys working on lower level plumbing such as lib & stdenv. He is most well known in the Nix community from his work on various Nix tooling such as: * [uv2nix](https://github.com/pyproject-nix/uv2nix) * [pyproject.nix](https://github.com/pyproject-nix/pyproject.nix) * [poetry2nix](https://github.com/nix-community/poetry2nix) * [gomod2nix](https://github.com/nix-community/gomod2nix) * [nix-eval-jobs](https://github.com/nix-community/nix-eval-jobs) * [nix-unit](https://github.com/nix-community/nix-unit) \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- This is Dim Sum Labs' Public HackJam meet. Free! Everyone is welcome to join us. If you are an engineer, designer, programmer, artist, creator, innovator, visionary, entrepreneur, or inventor, join us for an evening of thought-provoking conversations. Or better yet, bring your projects, ask for help, and show them off. This is also your chance to test the space before becoming a member. Members have access to the space and all the [equipment within](https://www.dimsumlabs.com/equipment/), 24/7 for a very reasonable price! For details, [please see our website](https://www.dimsumlabs.com/become-a-member-of-dim-sum-labs/). Calling for show-and-tell: if you want to share your projects on coding, making, art, and tech venture projects, come jam with us on HackJam. We can accommodate and help you promote here. Contact us here or via the means listed below. Being Hong Kong's longest-running Hackerspace (since 2011), we are happy to host you, who may: * Be coming from out-of-town * Be from other Hacker/Maker/co-working spaces * Want to get hands-on and create * Wish to network with high-quality, friendly, like-minded people * Be curious about what all this is about * Just want to have a drink while coding. Can't arrive at the start time? Drop in when you can make it :) For more information, check out our website at [https://www.dimsumlabs.com](https://www.dimsumlabs.com), or chat with us (we are happy to chat with you): * Telegram: https://t.me/dimsumlabs * IRC Chat: #dimsumlabs on https://libera.chat/

Booked 2 Tables, 4-6 People, 20HKD/Person - Playing for 2 hours looking for practice or games. NOT SUITABLE FOR BEGINNERS. No coaching available yet.

有時候，會想找陌生人談談，可以是工作、家庭、情感，互為樹洞，互相取暖。 認識一個人，聽一個故事。

**德州撲克**（Texas hold'em，有時也簡稱為Hold'em或Holdem），簡稱**德撲**，是世界上最流行的公牌[啤](http://%5Bhttps://zh.wikipedia.org/wiki/%E6%92%B2%E5%85%8B%5D(https://zh.wikipedia.org/wiki/%E6%92%B2%E5%85%8B) "啤")衍生遊戲，也是國際啤比賽的正式競賽項目之一。[世界撲克大賽](http://%5Bhttps://zh.wikipedia.org/wiki/%E4%B8%96%E7%95%8C%E6%89%91%E5%85%8B%E5%A4%A7%E8%B5%9B%5D(https://zh.wikipedia.org/wiki/%E4%B8%96%E7%95%8C%E6%89%91%E5%85%8B%E5%A4%A7%E8%B5%9B) "世界撲克大賽")（World Series of Poker, [WSOP](http://%5Bhttps://zh.wikipedia.org/wiki/WSOP%5D(https://zh.wikipedia.org/wiki/WSOP) "WSOP")）和[世界啤巡迴賽](http://%5Bhttps://zh.wikipedia.org/wiki/%E4%B8%96%E7%95%8C%E6%92%B2%E5%85%8B%E5%B7%A1%E8%BF%B4%E8%B3%BD%5D(https://zh.wikipedia.org/wiki/%E4%B8%96%E7%95%8C%E6%92%B2%E5%85%8B%E5%B7%A1%E8%BF%B4%E8%B3%BD) "世界啤巡迴賽")（World Poker Tour，[WPT](http://%5Bhttps://zh.wikipedia.org/wiki/WPT%5D(https://zh.wikipedia.org/wiki/WPT) "WPT")）的主賽事（Main Event）項目即是「無限注德州撲克」[\[1\]](https://zh.wikipedia.org/zh-hk/%E5%BE%B7%E5%B7%9E%E6%92%B2%E5%85%8B#cite_note-1)。 德州撲克是位置順序影響最大的啤衍生遊戲之一，每一輪的下注順序維持不變，它也是[美國](http://%5Bhttps://zh.wikipedia.org/wiki/%E7%BE%8E%E5%9C%8B%5D(https://zh.wikipedia.org/wiki/%E7%BE%8E%E5%9C%8B) "美國")多數[賭場](http://%5Bhttps://zh.wikipedia.org/wiki/%E8%B3%AD%E5%A0%B4%5D(https://zh.wikipedia.org/wiki/%E8%B3%AD%E5%A0%B4) "賭場")內最受歡迎的[啤](http://%5Bhttps://zh.wikipedia.org/wiki/%E6%92%B2%E5%85%8B%5D(https://zh.wikipedia.org/wiki/%E6%92%B2%E5%85%8B) "啤")牌類遊戲，在美國以外的地區也十分流行，與[橋牌](http://%5Bhttps://zh.wikipedia.org/wiki/%E6%A1%A5%E7%89%8C%5D(https://zh.wikipedia.org/wiki/%E6%A1%A5%E7%89%8C) "橋牌")的流行程度相當。理論上，一桌同時最多可容納22位（若不銷牌則為23位）牌手，但一般是2〜10人一桌。 🔔 呢一局係自助局, 參加者需輪流take turn派牌! 我地唔玩錢, 冠軍有小回贈. 地址: 觀塘駿業里8號世貿大樓605室 難度: 容易 (會教你哋玩法). 費用: [$105, Meetup報名$100] Pay at entrance. 包飲品一盒, extra飲品每盒$5. 🔔 人多, 或員工/主持忙於教玩遊戲時可能沒暇收取場費, 請利用櫃面PayMe code/Ali Pay /FPS號碼自行支付. 如發現有故意走數情況, 會被放進Meeple Tree 黑名單. 🔔 場地沒有食物提供, 但歡迎帶外賣上來食. 🔔 宣傳其他場地/放飛機/遊戲過程中態度惡劣者會被放進黑名單. 🔔 入埸請除鞋. 埸內拖鞋祗供店內用, 請勿著出店外. 🔔 報名參加Meetup活動, 當系統問你"Are you bringing anyone"時, 如果你祗是一個人來, 毋須㩒+1 (+1代表會帶朋友來的意思). 🔔 我哋嘅活動主持人有時會因為工作或者學業關係臨時嚟唔到，Meeple Tree 保留臨時更換主持嘅可能性。🙏 🔔 本會因放飛機(活動開始前24小時內退出者)被移除人數: 102 🔔 Meeple Tree保留參加者名單最後決定權. 🔔 Follow我哋IG: mtboardgame / boardgame_hk \*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\* 📣 我地成業街超抵Deal場地‼️ 星期一至四，$400 book 場玩6個鐘，book 晒成個場, 600尺空間自由玩！ 歡迎約埋啲朋友仔一齊上去玩啦！查詢預約：Whatsapp 6️⃣7️⃣9️⃣4️⃣1️⃣1️⃣6️⃣6️⃣

We’re excited to partner with AgentCon Hong Kong, the global developer conference focused on AI Agents and autonomous AI! Our community will be hosting a full day of workshops and talks alongside the AgentCon Hong Kong program. Below is the full agenda for our sessions. Come learn, build, and explore the future of AI Agents with us! **Activities:** 1. AI IDE - Kiro Hands-on Workshop x AgentCon Hong Kong 2. Building Multi-Agent Systems in Finance with Strands Agents and Bedrock AgentCore on AWS. 3. Governing AI Agents in Production: From Experiment to Engineering System 4. Empower Team Wide Vibe Coding with LLM Gateway and Security-First MCPs 5. What can go wrong when you ask your agent to go naughty? **AI IDE - Kiro Hands-on Workshop x AgentCon Hong Kong** *[Haowen Huang](https://www.linkedin.com/in/haowenhuang/) \- Senior Developer Advocate\, Amazon Web Services* *[Jacky Wu](https://www.linkedin.com/in/jackywu1/) \- Sr\. Solutions Architect\, Amazon Web Services* Time: 10:40 am Generative AI tools have democratized software development, enabling both developers and non-technical users to build applications efficiently. However, these tools struggle with enterprise-level challenges: inadequate project planning, unstructured workflows, poor enterprise integration, and inconsistent code quality. Kiro, AWS's AI IDE tool, addresses these gaps by integrating specification-driven development, structural design, test validation, and automated execution into a standardized, traceable workflow. At re:Invent 2025, AWS launched “Kiro Powers”—extensible capability packages that inject domain-specific expertise into Kiro AI agents. Each Power provides: \- Domain guidance via steering files \(POWER\.md\) \- Tool integration \(MCP services for databases\, payments\, deployment\) \- Automated Hooks for event\-driven actions \(API testing\, infrastructure code generation\) Unlike traditional coding assistants, Kiro + Powers covers the entire development lifecycle—from requirements to deployment—while reducing token costs and ensuring consistent code quality. We'll demonstrate Kiro's capabilities by building a game using Specs, Powers, and Hooks, showcasing its enterprise-grade advantages in planning, automation, and quality assurance. **First come, first served if the number of attendees exceeds capacity!** **To join this workshop, you need to register at [AWS AI User Group Hong Kong](https://www.meetup.com/aws-ai-user-group-hong-kong/)** https://www.meetup.com/aws-ai-user-group-hong-kong/events/313334952/ **Building Multi-Agent Systems in Finance with Strands Agents and Bedrock AgentCore on AWS.** *[Haowen Huang](https://www.linkedin.com/in/haowenhuang/) \- Senior Developer Advocate\, Amazon Web Services* *[Jacky Wu](https://www.linkedin.com/in/jackywu1/) \- Sr\. Solutions Architect\, Amazon Web Services* Time: 1:15 pm This session explores practical implementations of AI agents for financial services on AWS. Discover how to design multi-agent systems with the Strands Agents framework and Bedrock AgentCore for complex financial workflows—from quantitative backtesting to AI fund manager. You'll learn multi-agent patterns, and agent orchestration techniques. Walk away with concrete architectural patterns and implementation strategies for building production-ready AI agents in finance. **Governing AI Agents in Production: From Experiment to Engineering System** *[Mike Ng](https://www.linkedin.com/in/ngsinching/) \- ex\-AWS Community Builder* Time: 2:30 pm Most AI governance discussions assume AI will "do the right thing" with properguidelines. This talk takes a different approach: assume drift, error, and misalignment by default, then design mechanical structures that make bad behavior expensive. The core idea: systems are defined by what they refuse to do, not what they can do. For AI in production, governance means explicit rejection zones, constitutional constraints that cannot be bypassed, and separation between decision-making and execution. Five governance patterns: constitutional constraints (forbidden states and behaviors), rejection zones (where AI cannot operate), separation of powers (decision ≠ execution ≠ validation), retrieval-led reasoning (grounding over pre-training), and mechanical enforcement (architecture over policy). Developed while preparing experimental multi-agent systems for production deployment in FinTech, where mistakes are irreversible and governance is survival, not choice. **Empower Team Wide Vibe Coding with LLM Gateway and Security-First MCPs** *[Gabriel Koo](https://www.linkedin.com/in/gabrielkoo/) \- AWS Community Builder & Senior Lead Engineer at Bowtie Life Insurance* *[Rakshit Jain](https://www.linkedin.com/in/rakshit-jainn/) \- AI Engineer II* *Bowtie Life Insurance* Time: 3:00 pm Scaling AI-assisted development from a few enthusiasts to 50+ software engineers isn't just about API keys - it's about governance, trust, and standardized workflows. How do you prevent "shadow AI" and budget chaos while granting safe access to production context? At Bowtie, we adopted a layered security-first approach: First, control the traffic; second, secure the tools; third, standardize the behavior. This session covers our journey building a production-grade Vibe coding platform: Layer 1: The AI Gateway (LiteLLM on AWS Fargate + Amazon RDS) We established a centralized choke point for all AI traffic. This enables cost attribution, DLP detection, and usage visibility. Crucially, we enforce this at the network level - blocking direct access to non-official API providers to ensure all usage is visible and governed. Layer 2: Security-First MCP servers We treat AI agents as "CLI versions" of our internal web apps. By building custom Model Context Protocol (MCP) servers that reuse existing permissions and authentications - using Amazon Cognito for internal APIs and OAuth for official SaaS MCP servers - the AI acts as a delegate of the developer with human approvals. No new service accounts, no "god-mode" bots - if you can't do it in the existing user interfaces, the Agent can't do it via MCPs. Layer 3: Custom Skills for Standardization Beyond just tools, we write custom Skills to guide the model's behavior, ensuring generated code aligns with our engineering standards and SOPs (e.g. grab a ticket, fetch knowledge base, apply a fix, close the ticket) before a PR is even opened. Walk away with an architectural blueprint for democratizing AI access that satisfies the strictest security requirements while giving developers the friction-free vibe coding experience they crave. **What can go wrong when you ask your agent to go naughty?** *[Richard Fan](https://www.linkedin.com/in/richardfan1126/) \- AWS Hero \| An independent security researcher* Time: 3:30 pm We security folks all want to secure the AI agents, restricting their capability, putting guardrails, using system prompts, ... just to make sure the agents don't go rogue. But what if the AI agent is specifically designed to do bad things? Suddenly, the rule is changed. The instructions are encouraging agents to make harm, and the guardrails are half-opened, so as to allow the agent to do its job. In this scenario, what can go wrong? In this session, Richard will talk about AWS Security Agent, an AI agent designed to do automated penetration tests. He will share the security issues he found on the agent and highlight the challenges when building agents that simulate harmful actions. **Important notes:** We’re partnering with AgentCon Hong Kong! Our community will join **AgentCon Hong Kong**, a global developer conference focused on AI Agents and autonomous AI organized by the Global AI Community. To attend this workshop, **you must register on the official AgentCon page by the Global AI Hong Kong chapter as well!** Registration on this User Group page **does not** grant venue access. **Official Registration (Required):** [https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/](https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/) **Important Notes for All Attendees** **1️⃣ Registration Required for Entry** All participants **must** register on the official AgentCon Hong Kong. Venue access will only be granted to people who appear on the official attendee list. **2️⃣ Lunch Ticket Eligibility** Attendees who: * **Check in during the morning session**, and * **Stay for and join the keynote** will receive a **lunch ticket**. **3️⃣ First‑Come‑First‑Served (If Over Capacity)** In case of high demand, lunch tickets will be distributed **on a first‑check‑in, first‑served basis**. Arrive early to secure your ticket. **Join AgentCon and learn about agents. We are happy to have a workshop that day.**

👉 Official Registration (Required): **https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/** Hong Kong Python User Group & Open Source Hong Kong were invited to be the partners of AgentCon Hong Kong. There are 2 sessions we will presenting in AgentCon Hong Kong 2026 Conference Date: 11-April-2026 Time: 10:00am - 05:00pm Venue: **Hong Kong Institute of Information Technology (HKIIT) (VTC Tsing Yi Complex) ,** 20A Tsing Yi Road Tsing Yi Island, New Territories Hong Kong Session 1: **[Workshop] Jailbreaking the Ghost: Anatomy of a Secure Agent** Speaker: Alex Au, Henry Wong Time: 1:45pm - 2:40pm Location: Cybersecurity Ctr 412, 413 Session 2: **[Speech] From Idea to Impact: A Realistic 90-day Roadmap for Launching Your First Business AI Agent** Speaker: Eric Chan Time: 4:00pm - 4:25pm (25 min) Location: Computer Room 511 Language: Cantonese -- Registration: Please visit https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/ and register for the event. Partner: Hong Kong Python User Group https://www.meetup.com/pythonhk/ & Open Source Hong Kong https://opensource.hk/zh/ Agenda Details: [1] **Jailbreaking the Ghost: Anatomy of a Secure Agent** Time: **1:30pm - 2:30pm** Speakers: **Henry Wong - Data Scientist** **Alex Au - Cloud Engineer, Hong Kong Economic Times** Language: **Cantonese** Model: **Workshop** Description: We told developers "Don't paste API keys," but then we gave Agents full Python execution environments and access to production databases. The uncomfortable truth is that most AI Agents today are just Remote Code Execution (RCE) vulnerabilities with a friendly personality. In this session, we will dismantle a standard "Production Ready" Agent live on stage, demonstrating how a simple prompt injection can exfiltrate secrets. Then, we will rebuild it using Defense in Depth: 1\. Code: block malicious imports\, prompt injections\. 2\. Compute: Sandboxing for isolated workloads\. 3\. Identity: Zero Trust tool usage without worrying leakage of credentials\. Stop building chatbots. Start building secure autonomous systems. [2] **From Idea to Impact: A Realistic 90-day Roadmap for Launching Your First Business AI Agent** Time: **4:00pm - 4:25pm** Speakers: **Henry Wong - Data Scientist** **Alex Au - Cloud Engineer, Hong Kong Economic Times** Language: **Cantonese** Model: **Speech** Description: A roadmap that takes a business from initial AI agent idea to a live, value-creating deployment in 90 days, designed for SMBs, mid-market teams and departments. This talk walks through 4 phases: rapid scoping and prep, fast prototyping, controlled piloting with metrics, and safe production launch. \*\*\* Important notes: 🎉 We’re partnering with AgentCon Hong Kong! Our community will join AgentCon Hong Kong, a global developer conference focused on AI Agents and autonomous AI organized by the Global AI Community. To attend this workshop, you must register on the official AgentCon page by the Global AI Hong Kong chapter as well! Registration on this User Group page does not grant venue access. 👉 Official Registration (Required): **https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/** 📌 Important Notes for All Attendees 1️⃣ Registration Required for Entry All participants must register on the official AgentCon Hong Kong. Venue access will only be granted to people who appear on the official attendee list. 2️⃣ Lunch Ticket Eligibility Attendees who: Check in during the morning session, and Stay for and join the keynote will receive a lunch ticket. 3️⃣ First‑Come‑First‑Served (If Over Capacity) In case of high demand, lunch tickets will be distributed on a first‑check‑in, first‑served basis. Arrive early to secure your ticket.

**\*\*品牌・創意・交易・# AI ・#知識產權 💡📋🔐 創業講堂** # Artificial Intelligence and Intellectual Property **✨SCC 大灣區青年創業（智慧城市）計劃 - 免費講堂✨** **《青年創業 IP 攻略：品牌・創意內容與交易（知識產權）》開講啦 🎓** *** **⚡ 講堂重點 ⚡** 📌 **香港知識產權法規精要** 📌 **青年創業核心痛點：品牌與創意內容保護及 AI 時代新挑戰** * AI 生成作品版權誰屬？ * 相關風險與合約安排要點 📌 **知識產權交易及商業應用的核心概念** * 商業化工具箱：轉讓、許可授權、科研合作簡介 📌 **知識產權資產審計、盡職調查及估值基礎入門** 📌 **香港知識產權交易相關稅務優惠及最新政策（適合創業團隊）** *** **⏰ 時間：2026 年 4 月 10 日（星期五）18:30 – 20:00** **📍 地點：中環皇后大道中 99 號中環中心地下 H6 Conet 活動室 C** **📍 形式：現場或線上 Zoom 參與（亦歡迎線上參加）** **🎟️ 費用：免費（名額有限，先到先得）** **🗣 語言：廣東話（輔以英語專業術語）** *** **講者介紹 🎤 Ms. Anita Leung（梁丙焄**律師） ✅顧問律師（David Lo and Partners） ✅超過三十年知識產權及科企法律經驗 ✅專長品牌、IP 交易、內部 IP 審計及 pre‑IPO 盡調 ✅覆蓋品牌授權、特許經營、數據私隱與網絡安全 ✅中國許可貿易工作者協會香港分會現任理事及前主席 ✅香港貿發局亞洲知識產權營商論壇策劃委員會成員 ✅香港版權審裁處副主席 ✅為本港中小企提供免費知識產權諮詢服務的法律顧問 *** **📝 報名連結：** [https://forms.gle/wcVAnh2idxxZA6Xb6](https://forms.gle/wcVAnh2idxxZA6Xb6) *** **📞 查詢：3905 0906（聯絡生先生 / 余小姐）** **✉️ 電郵：[hyab.funding@smartcity.org.hk](mailto:hyab.funding@smartcity.org.hk)** 計劃由民政及青年事務局及青年發展委員會的「青年發展基金」豁下「民青局粵港澳大灣區青年創業資助計劃」資助 ![]()

Hong Kong Python User Group & Open Source Hong Kong are delighted to be invited as a partner of AgentCon Hong Kong 2026! **Please note that registration on this User Group page does not grant venue access.** 👉 Official Registration (Required): [https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/](https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/) **Conference Date**: 11-April-2026 **Time**: 10:00am - 05:00pm **Venue**: Hong Kong Institute of Information Technology (HKIIT) (VTC Tsing Yi Complex) **,** 20A Tsing Yi Road Tsing Yi Island, New Territories Hong Kong Session 1: **[Workshop] Jailbreaking the Ghost: Anatomy of a Secure Agent** Speaker: Alex Au, Henry Wong Time: 1:45pm - 2:40pm (55 min) Location: Cybersecurity Ctr 412, 413 Language: English Session 2: **[Talk] From Idea to Impact: A Realistic 90-day Roadmap for Launching Your First Business AI Agent** Speaker: Eric Chan Time: 4:00pm - 4:25pm (25 min) Location: Computer Room 511 Language: Cantonese Registration: Please visit https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/ and register for the event. Partner: • [Hong Kong Python User Group](https://www.meetup.com/pythonhk/) • [Open Source Hong Kong](https://opensource.hk/zh/) **Agenda Details:** 1️⃣ **Jailbreaking the Ghost: Anatomy of a Secure Agent** **Time**: 1:30pm - 2:30pm **Speakers**: **•** Henry Wong - Data Scientist **•** Alex Au - Cloud Engineer, Hong Kong Economic Times **Language**: English **Model**: Workshop **Description**: We told developers "Don't paste API keys," but then we gave Agents full Python execution environments and access to production databases. The uncomfortable truth is that most AI Agents today are just Remote Code Execution (RCE) vulnerabilities with a friendly personality. In this session, we will dismantle a standard "Production Ready" Agent live on stage, demonstrating how a simple prompt injection can exfiltrate secrets. Then, we will rebuild it using Defense in Depth: 1\. Code: block malicious imports\, prompt injections\. 2\. Compute: Sandboxing for isolated workloads\. 3\. Identity: Zero Trust tool usage without worrying leakage of credentials\. Stop building chatbots. Start building secure autonomous systems. 2️⃣ **From Idea to Impact: A Realistic 90-day** **Roadmap for Launching Your First Business AI Agent** **Time**: 4:00pm - 4:25pm **Speakers**: • Eric Chan **Language**: Cantonese **Model**: Talk **Description**: A roadmap that takes a business from initial AI agent idea to a live, value-creating deployment in 90 days, designed for SMBs, mid-market teams and departments. This talk walks through 4 phases: rapid scoping and prep, fast prototyping, controlled piloting with metrics, and safe production launch. 📌 **Important Notes for All Attendees** 1️⃣ Registration Required for Entry All participants must register on the official AgentCon Hong Kong. Venue access will only be granted to people who appear on the official attendee list. 2️⃣ Lunch Ticket Eligibility Attendees who: • Check in during the morning session, and • Stay for and join the keynote will receive **a free lunch ticket**. 3️⃣ First‑Come‑First‑Served (If Over Capacity) In case of high demand, lunch tickets will be distributed on a first‑check‑in, first‑served basis. **Arrive early to secure your ticket.**

**Speakers:** Haowen Huang - Senior Developer Advocate, Amazon Web Services Jacky Wu - Sr. Solutions Architect, Amazon Web Services **Language:** Cantonese **Important notes:** We’re partnering with AgentCon Hong Kong! Our community will join **AgentCon Hong Kong**, a global developer conference focused on AI Agents and autonomous AI organized by the Global AI Community. To attend this workshop, **you must register on the official AgentCon page by the Global AI Hong Kong chapter as well!** Registration on this User Group page **does not** grant venue access. **Official Registration (Required):** [https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/](https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/) *** **Important Notes for All Attendees** **1️⃣ Registration Required for Entry** All participants **must** register on the official AgentCon Hong Kong. Venue access will only be granted to people who appear on the official attendee list. **2️⃣ Lunch Ticket Eligibility** Attendees who: * **Check in during the morning session**, and * **Stay for and join the keynote** will receive a **lunch ticket**. **3️⃣ First‑Come‑First‑Served (If Over Capacity)** In case of high demand, lunch tickets will be distributed **on a first‑check‑in, first‑served basis**. Arrive early to secure your ticket. **Join AgentCon and learn about agents. We are happy to have a workshop that day.** **Description:** Generative AI tools have democratized software development, enabling both developers and non-technical users to build applications efficiently. However, these tools struggle with enterprise-level challenges: inadequate project planning, unstructured workflows, poor enterprise integration, and inconsistent code quality. Kiro, AWS's AI IDE tool, addresses these gaps by integrating specification-driven development, structural design, test validation, and automated execution into a standardized, traceable workflow. At re:Invent 2025, AWS launched “Kiro Powers”—extensible capability packages that inject domain-specific expertise into Kiro AI agents. Each Power provides: \- Domain guidance via steering files \(POWER\.md\) \- Tool integration \(MCP services for databases\, payments\, deployment\) \- Automated Hooks for event\-driven actions \(API testing\, infrastructure code generation\) Unlike traditional coding assistants, Kiro + Powers covers the entire development lifecycle—from requirements to deployment—while reducing token costs and ensuring consistent code quality. We'll demonstrate Kiro's capabilities by building a game using Specs, Powers, and Hooks, showcasing its enterprise-grade advantages in planning, automation, and quality assurance. **First come, first served if the number of attendees exceeds capacity!**

此活動中不可進行任何商業銷售行為 因為在其他平臺也有發布，所以實際人數可能會比報名人數多 不進行簡單的閒聊，而是專注於深度對話，旨在提供能夠獲得知識並對您有所幫助的交流。 這裡可能有AI實踐者、心理學專家、哲學家、說故事的高手，或只是想聽故事的人。 我們將圍繞一個或多個主題進行辯論與學習，互相成長，共同進步，讓每一次交流都能助您提升與成長。 週日的深度討論，不管你想聊聊ai還是敘事學心理學還是哲學，不管你是否是這方面的新手還是老手，哪怕只是來聽聽，甚至想談談其他也可以 本聚會嚴格上不是專業討論，更像是深度聊天 時間：週日（4月12號）14：00 地點：（報名後會告知具體地點） 注意： 此活動有人數限制，活動過程中請保持友善，務必遵守相關法規，本活動及主辦單位不對參加會員安全負任何責任，請大家為自己安全負責。 活動中不討論政治，宗教等。 本活動安排可能會臨時發生變化，請大家留意 本活動不收取任何費用，活動過程中可以隨時離開 如不同意或違反以上內容，不可參加本次活動或可能會被要求離開活動 Due to the possibility of publishing on other platforms, the actual number of participants may exceed the registered number. do not engage in simple small talk; instead, we focus on deep conversations aimed at providing knowledge that can be helpful to you. Here, you may find AI practitioners, psychology experts, philosophers, storytelling masters, or simply those who wish to listen to stories. We will debate and learn around one or multiple themes, growing and progressing together, ensuring that each exchange contributes to your growth and improvement. On Sunday, we invite you to join a deep discussion. Whether you want to chat about AI, narrative studies, psychology, or philosophy, it doesn't matter if you're a beginner or an expert—feel free to come just to listen, or even to discuss other topics. This gathering is not a professional discussion, but rather a space for deep conversation. **Time:** Sunday (April 12th) at 14:00 **Location:** (Specific location will be provided after registration) **Note:** - This event has a participant limit. Please maintain friendliness during the event and adhere to relevant regulations. The event and the organizers are not responsible for the safety of participants; everyone is responsible for their own safety. - Political and religious discussions are not allowed during the event. - Arrangements for this event may change unexpectedly, so please stay tuned. - There is no fee for this event, and you can leave at any time during the process. - If you disagree with or violate any of the above content, you may not participate in this event or may be asked to leave. **The event content is subject to the Chinese version.**

Fee 7ppl $75 5~7pm court 2 請大家遵守以 1:請大家不要在遊戲其間進行羽毛球技術指導. 2:男與女閒聊時請保持一隻手距離. 3:遊戲已例明 羽毛球等級(ab,li,i 等等), 請按照自己所屬等級參與遊戲. 4:各下參加左的活動有指定場號, 如果自行走向其他埸由我們舉辦的活動的埸地打波, 我地可能會給予警告, 請不要挑戰我們的忍耐力。 5:如果少於48小時內取消出值, 都請交出值應付之金額。 如有違反, 一律blacklist. If you join my game for first time please send me your mobile no. to confirm your spot. Tel: 97843661 Coming Please Whatsapp or message me through meetup as soon as possible if you can't come. ‧ We will be playing 21 points doubles match ‧ Strictly NO BEGINNER ‧ The event is not first come first serve, I will pick suitable players in order to balance the level of the game. So if you are not on the attending list, please don't feel being offended, thanks for understanding ‧ Cancellation policy: Cancellation deadline is 48 hours prior to the start time of the game. Cancellation past the deadline will be marked as no-show.11

**Important time note:** Please plan on arriving between 5:30 and 6:00 as the elevators lock after 6 and you'll need to message us and we'll need to come get you. The building address is 4450 Bridge Park The entrance is 6620 Mooney St, Suite 400 You will need to scan your ID at the door to get a visitor badge. **Abstract** GitHub Copilot is powerful, but what if you could scale from a solo AI assistant to an entire team of specialized agents working in parallel? This session introduces Squad: an open-source framework for multi-agent orchestration that lets you define teams of AI agents with specific roles, responsibilities, and expertise. We'll progress from Copilot basics to the Copilot CLI, explore how Agents add autonomy, and see how Instructions and Skills let you customize agent behavior. Then, the climax: a live demo where a Squad team of 3 agents (Lead, Developer, Tester) stands up and builds a working application in real-time, showcasing true multi-agent collaboration. Whether you're new to AI or exploring how to scale your use of Copilot, this session will show you what's possible when agents work as a team. **YouTube Link** TBD

AI is changing how art is made. But when does it stop being your work and start being the machine’s? This month we're going to be doing a panel with with digital image, music, and written word artists, talking about at what point, while using AI in the creation process, does the work become not the artist creation? We encourage audience participation during this event that will be moderated by Chris Slee. Whether you’re deep in the field or just getting curious, come connect with others building and exploring AI in Columbus. Sponsored by [Transform Labs](https://www.transformlabs.com/services)

Topic to be announced. **CALL FOR SPEAKERS** Learn more: https://www.awscolumbus.com/get-involved/ **THANK YOU** *VEEAM* for hosting our meetup! To learn more about *Veeam*, please visit their website: https://www.veeam.com/ **DIRECTIONS** 8800 Lyra Dr #450 · Columbus, OH go to 4th floor. **Want to sponsor the pizza and/or bar tab?** Please contact me if you would like to sponsor this meetup's pizza and/or bar tab: angelo@mandato.com

**Important time note:** Please plan on arriving between 5:30 and 6:00 as the elevators lock after 6 and you'll need to message us and we'll need to come get you. The building address is 4450 Bridge Park The entrance is 6620 Mooney St, Suite 400 You will need to scan your ID at the door to get a visitor badge. **Abstract** TBD **YouTube Link** TBD

Join us for an engaging panel discussion on **AI Agentic Coding** and how autonomous AI systems are transforming the way software is built. Experts in AI, software engineering, and developer tools will share insights on how agentic AI—systems that can plan, reason, and execute coding tasks—is reshaping modern development workflows. The discussion will cover topics such as AI-assisted development, productivity gains, challenges around reliability and governance, and what the future of software engineering may look like with AI agents as collaborators. Whether you’re a developer, tech leader, or AI enthusiast, this session is a great opportunity to learn, ask questions, and explore how agentic AI is redefining coding

NFT's are here to stay folks! This is a group for like minded people interested in understanding, leveraging, using, creating for, profiting from, trading too i suppose, NFT's.. everything around them, complexity, fear and exploits, best practices and more. **PLUS** This group will talk AI ART tools, techniques, artists, video, audio, prototypes and more in the AI assisted production space- ART specifically, but we can get into any aspect of some of the cooler things happening in AI in general.

Central Ohio Radio Enthusiasts—CORE—is an informal community for anyone enthusiastic or curious about radio—whether you're new to radio and want to learn or you've been tinkering for years and want to share. Ham radio operators, GMRS users, Meshtastic fans, software-defined radio nerds, makers, and technical and non-technical folks are all welcome. No experience required or expected. This month we have **WiFi HaLow: Introduction and Practical Use** with **Alex Barbur**. Details are are [core.radio](https://core.radio).