[Google Cloud Next '26 Recap #2] Three Unique Booths I Tried at the EXPO

This is the second post in my Google Cloud Next '26 (Las Vegas) recap series. You can find Part 1 here 👇 [[Google Cloud Next '26 Recap #1] Hands-On with the Agentic Hack Zone](https://dev.to/gde/google-cloud-next-26-recap-hands-on-with-the-agentic-hack-zone-12p9) Beyond the **Agentic Hack Zone** I covered last time, the EXPO floor was packed with engaging booths. In this post, I'd like to share my experience at **three booths** that especially stood out to me: - **GenLatte** - **CLI Mission Control** - **ADK and A2A In Action** --- ## 1. GenLatte (Order an AI-Personalized Latte Art) The first one is **GenLatte**. This was a demo where you could order a coffee personalized with Google AI — **Gemini (nano banana) generates a custom latte art design**, which is then served to you as a real, drinkable latte. A booth that was a treat for both your eyes and your taste buds. The order screen appeared to be built with a combination of **Gemini / Firebase / Flutter**. ### How the experience flowed 1. On the order screen, choose the type of latte you want (Latte, Non-Fat milk, Mocha, etc.) 2. Answer a few questions about the design you'd like 3. Pick your favorite from **4 generated design candidates** and hit Submit 4. Wait a little while, and your latte — complete with the chosen art — is served I went with a **snowy mountain** theme, and the result turned out really nicely.  The idea of "personalizing a latte" felt fresh, and the booth offered some great inspiration for designing AI-powered end-user experiences. --- ## 2. CLI Mission Control (Tackle Terminal Missions with Gemini CLI) The second one is **CLI Mission Control**. This was a game-style booth where you used **Gemini CLI** to complete three tasks in the terminal and compete for a high score. ### The tasks - Install an extension - Draw a **fuel can** and capture the image - Finally, launch the rocket 🚀 Apparently, faster input speed and higher-quality drawings translated into higher scores. For the "fuel can" prompt, I went with a straightforward **drum can** drawing… only to be hit with a "**too generic**" verdict from the judges, and my score didn't take off as I'd hoped.  A **leaderboard** was set up right next to the booth, displaying the names of participants who had nailed top scores. It was a fun take on bringing the CLI into a playful, gamified context — a booth with a nice sense of humor. --- ## 3. ADK and A2A In Action (Experience Multi-Agent Collaboration Firsthand) The third one is **ADK and A2A In Action**. This was a hands-on demo of multi-agent collaboration using **ADK (Agent Development Kit)** and the **A2A (Agent-to-Agent Protocol)**, where participants worked together to build **4 agents** that — through A2A — collaborated as a team to come up with a **new game concept**. ### How it worked There were 4 stations (tablets) set up, each responsible for an agent with a different role: - **Marketing** - **Game Design** - **Art and UX** - **Engineering and Production** I sat at the station building the **Marketing agent**. Once the agents at each station started collaborating as a "team" via A2A, a **new game concept report** was automatically produced within a few minutes.  ### The resulting game concept The report's title was… > **Alien World Survival** > *Survive and thrive in a hostile alien world.* Cover art was generated alongside it, and watching multiple agents divide up the work and collectively produce a single deliverable in real time was genuinely educational. The booth was clearly designed to let visitors intuitively enjoy the possibilities of multi-agent architectures, and it left a strong impression on me. --- ## Bonus: These Were All Part of the Skills Challenge By the way, all three booths I covered here were part of a program called **The Skills Challenge**. The Skills Challenge is a setup that lets you pick up new skills as you tour the venue during Next, and it added an extra layer of motivation to keep visiting more booths.  --- ## Wrap-Up Each of these three booths went well beyond a "look but don't touch" exhibit — they were all places where you could **actually move your hands and run agents or AI yourself**. The EXPO offers a different way to engage with technology compared to sessions, and once again I felt that it really expands the ways you can enjoy Next. If any of these booths show up, I'd absolutely love to swing by them again. To be continued in **#3**. [[Google Cloud Next '26 Recap #3] Anthropic's Vision for "After Software"](https://dev.to/gde/google-cloud-next-26-recap-3-anthropics-vision-for-after-software-2cj6)