DEV Community: koichim2

[Google Cloud Next '26 Recap #5] How I Prepared for the Trip — and How It Actually Played Out

koichim2 — Thu, 07 May 2026 15:40:31 +0000

This is the fifth and final post in my Google Cloud Next '26 (Las Vegas) recap series.

You can find the previous posts here 👇

So far, I've spent four posts walking through my Next '26 on-site experience. To wrap up the series, I'd like to look back on what I prepared before the trip — and how those preparations actually played out once I was on the ground.

Attending Next '26 in person turned out to be a 5-night international trip. I hope this post can serve as a useful reference for anyone planning to attend a tech conference in Las Vegas in the future.

Where I was coming from

This was my overseas tech conference since I attended Next in San Francisco three years ago, and my very first time in Las Vegas.

While I had attended Next once before, this was my first visit to Vegas itself, so I was very deliberate about gathering information during the prep phase.

Since Google Cloud Next was held at the same Las Vegas venue twice — in '24 and '25 — I was able to learn a lot from past attendees by watching their YouTube videos and blog posts, and attending lightning talks at pre-events organized by communities back home.

The resources I leaned on the most are below — many thanks to the authors 🙏

Jesse Nowlin: https://youtu.be/pqNG4FgLHYo
Kazumasa Iwao: https://zenn.dev/hogeticlab/articles/0e8aa36b179930
Jagu'e'r: https://jaguer.connpass.com/event/384137/

Things I felt I needed to prepare for

Once I started organizing all that information, I realized there were a surprising number of things to think about before leaving:

Dryness from Las Vegas's desert climate
Sunburn during the day
The convention center and airplane cabin being freezing cold
The convention center being huge — lots of walking
Next having so much content that I might run out of time
Possible crowds at badge pickup
SWAG filling up my luggage
Possible battery drain
Hydration (whether to bring a water bottle)
Bag size restrictions at the convention center
Clear bag requirements for stadium entry
General travel logistics: getting around the city, airport security, connecting flights, immigration

Topics like meals, casinos and other entertainment, hotel amenities, medications, travel insurance, and ESTA are out of scope for this post.

From here on, I'll share what I actually packed/prepared and how it went on the ground, based on my own personal experience.

Coping with Las Vegas dryness

What I brought:

Lip balm
Hand cream
Eye drops
Toner / lotion
Skincare cream
Throat lozenges

Result: Extremely useful. The dryness on the ground was more intense than I expected, and every single one of these earned its place. Skin, throat, and eye care turned out to matter way more than I'd anticipated — definitely glad I brought them all.

Sunburn protection during the day

What I brought:

Sunscreen
A cap
A thin, lightweight hooded jacket made for trail running

Result: Glad I brought all of these. The Vegas sun was stronger than I imagined — even a short walk outside left a clear "I'm getting cooked" feeling on my skin.

Cold convention centers and airplane cabins

This was solved with the same hooded jacket I mentioned above.

Since it doubled as both sun protection and warmth, it ended up being one of the most useful items of the entire trip. It handled the over-air-conditioned convention center and long-haul flights equally well.

Walking the huge venue, and my final outfit setup

Because the dryness, heat, and cold all turned out to be more intense than expected, I made prioritizing my health and stamina my top concern, and decided to go as light as possible.

In my case, I went all in on the choice to leave my laptop at the hotel. My final on-site setup looked like this:

The hooded jacket on top
Thick-soled sneakers
Stretchy pants
Badge hanging from my neck
Passport stayed in the hotel safe — not on me
In my pockets: phone, hotel key card, one credit card — that's it

In short, I walked in empty-handed. The downside was that my only computing device on me was my phone, but in exchange I could move around the venue extremely lightly — and for me, this style turned out to be the right call.

Too much content at Next

Next is the kind of event where, if you're not careful, you blink and suddenly there's no time left for the things you actually wanted to do.

To deal with this, I picked and reserved sessions early on. My booking rules were:

Only sessions I'd want to keep on my schedule even if I had to cut other plans (i.e., true must-sees)
A hard cap of 2–3 sessions per day

There were tons of sessions available, but by deliberately narrowing things down, I made sure I had plenty of buffer time for exploring the venue and trying out booths. This is advice many people give, and it's also a direct reflection on having packed my schedule too tightly the last time I went to Next.

Result: This worked out really well. I came away with both rich session content and plenty of booth experiences.

Failure story: I got locked out of a workshop

That said, I did mess one thing up.

I had reserved a 3-hour workshop right after the Opening Keynote, but I got hungry and decided to grab a snack at the partner lounge first — by the time I made it to the workshop room, it had already filled up to capacity, and I couldn't get in 😭

Apparently, after a session has been running for a while, they start letting standby attendees take vacant seats. Grabbing food to-go and eating it while attending the workshop would probably have been the right move.

After that, even for sessions I had already reserved, I started lining up early whenever I knew the session had reached its booking cap.

Crowds at badge pickup

I handled this by picking up my badge as soon as I landed at the airport, which made the whole process pretty smooth.

SWAG filling up your luggage

SWAG is one of those things where you keep wanting just one more thing, and your bag fills up fast on the way home.

This time I exercised some restraint and stuck mostly to pins, stickers, and other small, low-volume items.

Battery situation

I packed a portable battery just in case, but as mentioned above, all I was carrying was my phone, and I wasn't using it heavily for long stretches, so I was fine.

Things I brought that I never used

A few "just in case" items that ended up never coming out of my bag:

・Water bottle

I brought one from home for hydration — but water bottles were being given out for free at the venue. On top of that, there were plenty of spots to drink water from paper cups, so I ended up bringing the freebie bottle home, completely unused…

・A bag for the venue

I brought a separate bag sized to fit the official policy (roughly 12" × 18") in addition to my travel bag — but since I went empty-handed, it never got used.

・Clear bag for stadium entry

Policy stated that a clear bag is required for Next at Night, so I prepared one in advance — but again, I went in empty-handed, so this also went unused.

Getting around, the airport, connections, and immigration

Apps made this side of things significantly more comfortable:

Uber app: handled all my airport ↔ hotel rides
MPC app: gave me access to a dedicated lane at immigration during my connection — big time saver
MyTSA app: about a month before the trip, there was news about major airport security backlogs caused by TSA pay disruptions and staffing shortages tied to a federal funding lapse — I used this to check current wait times
Airline app: kept me on top of delays, schedule changes, and gate changes

A side note on CLEAR+

On the way home, I had to re-enter security at LAX during my connection, and a CLEAR+ Ambassador caught me near the security entrance and pitched the service. I went along with it and signed up on the spot.

It did genuinely shortcut my path through security, but I later discovered that after the 2-week trial period, it costs roughly $200/year as a subscription. Since I have no plans to be back in the US anytime soon, I cancelled before the charge hit. Lesson learned: be careful about signing up for things on impulse abroad.

Wrap-up: what I learned from this trip

The takeaways I'd hand my future self:

Dryness, sunburn, and cold protection are non-negotiables. A lightweight hooded jacket is a multi-purpose powerhouse.
Going empty-handed is more comfortable than expected. Committing to leaving the laptop behind paid off.
Cap your sessions. 2–3 a day, with the gaps reserved for venue exploration, ends up being more satisfying.
Line up early for popular sessions and workshops. "I have a reservation" doesn't always mean you'll get in.
Water bottles and secondary bags can easily go unused depending on your style.
Use apps to streamline immigration and connections.

And with that, this wraps up my series of posts on Next '26.

I wanted to share the most memorable lessons from everything I learned on this trip. I hope this proves to be useful to anyone reading.

Thank you so much for reading all the way to the end. See you somewhere next time!

See you in the Next. 👋

[Google Cloud Next '26 Recap #4] Live Report from the Two Keynotes

koichim2 — Tue, 05 May 2026 04:53:55 +0000

This is the fourth post in my Google Cloud Next '26 (Las Vegas) recap series.

You can find the previous posts here 👇

This time, I'd like to share a live report on the two keynotes from Next '26:

Opening Keynote
Developer Keynote

…with a focus on the atmosphere of the venue itself. When you attend a tech conference, the keynotes are the one thing you simply can't skip.

You may have already seen them, but the keynotes are also available on YouTube:

🎥 Opening Keynote: https://www.youtube.com/watch?v=11PBno-cJ1g
🎥 Developer Keynote: https://www.youtube.com/watch?v=A01DQ8_xy7Q

Where Keynotes sit in the program

According to Next's Session Types, the definition of Keynotes is as follows:

Join Google Cloud and industry leaders as they make big announcements, showcase the latest products and customer successes, and set the stage for everything else at the event.

In other words, Keynotes are the foundational sessions where major announcements, the latest products, and customer stories all land at once — setting the direction for the entire event.

The venue: Michelob ULTRA Arena

The keynote venue, as in past years, was the Michelob ULTRA Arena inside Mandalay Bay. This was my first time experiencing it in person, and with a capacity of 12,000 people, the sheer scale of the place hit me the moment I walked in.

Watching the seats gradually fill up before the show, with the lighting and sound design slowly building the atmosphere, gave me a kind of anticipation you simply can't get from a livestream.

Opening Keynote

The pre-show performance

Before the Opening Keynote kicked off, there was a music and visuals performance segment. The visuals appeared to be generated by AI, and an operator was switching between visual patterns by giving instructions through hand gestures in time with the music — a very unique production.

Even before the keynote actually started, the warm-up alone made it clear: "We're about to enter the era of agents."

The contents of the Opening Keynote have already been covered widely, so I'll just touch on the highlights here.

The overarching message

The industry is undergoing a major shift from generative AI to the "Agentic Era", where AI agents capable of autonomously reasoning, acting, and scaling are now being deployed across enterprises.

The strategic message

Google's strengths were framed as a fully owned full stack, end to end:

Custom silicon (Ironwood / 8th-gen TPU) → Frontier models (Gemini) → Cloud platform → Enterprise distribution channel (Workspace with 3 billion users)

The emphasis was on the fact that Google owns the entire stack from chip to app, in-house.

Major announcements

1. Gemini Enterprise Agent Platform (formerly Vertex AI)

Vertex AI has been rebranded to the Gemini Enterprise Agent Platform. The employee-facing AI assistant Agentspace is being folded in as well, consolidating everything into a single product called Gemini Enterprise — positioned as a platform that handles agent build, scale, governance, and optimization end-to-end.

2. The Gemini Enterprise app

A core business interface that lets even non-technical users build and use agents through natural language.

3. 8th-gen TPU (a 2-chip lineup)

TPU 8t (training): scales up to 9,600 TPUs in a single super-pod
TPU 8i (inference): 80% better cost-performance vs. the previous generation, with near-zero latency

4. Agentic Data Cloud

A complete redesign of the data foundation.

5. Agentic Defense

Integrating technology from the Wiz acquisition, autonomous Red / Blue / Green agents detect and remediate vulnerabilities at machine speed.

6. Workspace Intelligence

Agents are being embedded across Gmail / Docs / Sheets / Drive / Meet / Chat.

What stood out the most to me personally

The moment that stood out to me the most was the segment titled "State-of-the-art models in Gemini Enterprise Agent Platform", where various models were introduced.

Alongside Google's four models — Gemini 3.1 Pro / Gemini 3.1 Flash image / Lyria 3 Pro / Veo 3.1 Lite — Claude Opus 4.7 was featured as one of the Anthropic Models as well.

There may have been an element of wanting to avoid coming across as a closed ecosystem, but personally, I couldn't help but read it as a sign that Google is genuinely acknowledging the strength of Opus 4.7's model performance.

Developer Keynote

Another pre-show performance

Before the Developer Keynote, there was the same kind of music and visuals performance segment as the Opening Keynote. Same format, but it still had that "Oh, here we go again" feel of building anticipation.

The Developer Keynote has also been covered extensively on the official Google Cloud blog and elsewhere, so I'll just hit the highlights here.

The overall structure

The Developer Keynote was a developer-focused session centered around live demos and live coding.

The overarching theme was a multi-agent system that plans and simulates a fictional Las Vegas marathon, walking through the journey from the very first prototype all the way to production in a clear, story-driven progression.

For the record, the Las Vegas Marathon Simulator was made up of three agents:

Planner
Evaluator
Simulator

The 7 demos

The Developer Keynote presented the following 7 demos:

Build agents with Agent Platform
Creating multi-agent systems
Enhancing agents with memory
Debugging agents at scale
Intent to infrastructure with Gemini Cloud Assist
Build and share no-code agents
Securing agents

The flow — "build agents → make them collaborate → give them memory → debug them → handle infrastructure declaratively → distribute them no-code → secure them" — covered the entire agent development journey end-to-end. Even from a developer's perspective, it was packed with takeaways.

Source code and Codelabs fully published

What I really appreciated was that all the solutions were already published on GitHub, with the demos available as Codelabs. The QR codes shown on stage during the keynote pointed to:

Having a clean path of "watched the keynote → curious → let me try it myself right now" set up like this is genuinely one of the best things a developer-focused conference can do.

A side note: A couple of curious moments at the keynote venue

By the way, a couple of slightly odd things happened during the Developer Keynote.

The person sitting diagonally in front of me — apparently some kind of insider — started taking selfies with their phone before the keynote began. Their phone had a very bright dedicated phone light attached, which was honestly a bit dazzling from where I was sitting.

Then, near the end of the keynote during one of the demos, the person sitting directly in front of me turned around, stared right at me for a moment, and then silently walked away. I'm not sure what they wanted…?

Apparently this kind of thing is fairly common at tech conferences, so I'll just leave it be.

Wrap-Up

After attending both keynotes in person, here's what I came away with:

The scale of the venue and the live energy are things you can only experience by actually showing up
The "Agentic Era" message from the Opening Keynote runs as a clear thread through the rest of the sessions and the EXPO floor
The Developer Keynote, with its 7 demos centered on the marathon simulator, lets you experience the full stack of agent development as a single coherent story

"You can just watch the keynotes on YouTube" is technically true — but the value of being there in person is genuinely something else, and these sessions reminded me of that all over again.

To be continued in #5 (the final post).
[Google Cloud Next '26 Recap #5] How I Prepared for the Trip — and How It Actually Played Out

[Google Cloud Next '26 Recap #3] Anthropic's Vision for "After Software"

koichim2 — Mon, 04 May 2026 15:00:22 +0000

This is the third post in my Google Cloud Next '26 (Las Vegas) recap series.

You can find the previous posts here 👇

In Parts 1 and 2, I covered my experiences on the EXPO floor. This time, I'd like to switch gears and share one of the sessions I attended at Next '26 — specifically, an especially memorable session by Anthropic.

Session Overview

The session I attended was in the Spotlights category.

Title: After software: Anthropic's vision for the next era of enterprise AI
Speaker: Eric Burns (Anthropic)
Session ID: SPTL021

What is a "Spotlight" session?

According to Next's session type definitions, Spotlights are described as follows:

Take part in these dedicated keynote-style sessions featuring live demos, new tech, and customer success stories, delivered by Google leaders and partners.

In other words, Spotlights are positioned as special, keynote-style sessions packed with live demos, the latest technology, and customer stories.

The session video is available on the Google Cloud Next page.

The session's premise

Quoting from the YouTube video description, the session's premise was as follows:

Enterprise software will change more in the next two years than it has in the past twenty. The model is being inverted. Top-down planning, where organizations define and prioritize what to build, is shifting to bottom-up execution, where AI agents rapidly solve problems as teams discover them. Anthropic shares what's happening at the frontier. Teams are already deploying agents on Vertex AI that autonomously define, build, and iterate. We make this vision concrete, grounded in real examples and practical frameworks.

A pretty bold message, I'd say. From here on, I'll walk through the points that especially stood out to me during the session.

Highlights from the Session

Anthropic's presence in the coding market

The first thing that grabbed my attention was the figure that Anthropic holds 54% of the 2025 coding market share. The vague sense of "Anthropic is well-supported by developers" was reinforced by an actual number.

On top of that, the evolution of how AI is used at work was framed with these keywords:

2023: Chat
2025: Code
2026: Cowork

And the phrase that symbolizes where things are heading was "No terminal". Claude's benefits won't stay confined to engineers — they'll extend into non-engineering domains as well. That possibility came through clearly.

The evolution of Claude in a single video

For the evolution of Claude itself, the session played this YouTube video:

🎥 https://www.youtube.com/watch?v=PnX30ZXxKco

The video gives the same task — "clone claude.ai" — to each generation of Claude models and compares the results. The progress of Claude across generations was packed into a short clip, and you could clearly see the quality of the output rising with each version.

"The Intelligence Explosion" (AI's growth curve)

Next came the "The Intelligence Explosion" section.

Under the heading "The artificial intelligence exponential", the session walked through AI's growth using emblematic LLM products from various companies across each year.

When it comes to interpreting AI's growth curve, on one hand there's the view of:

The Pure Exponential

while on the other hand, there are skeptical views that frame it as:

The Sigmoid (an S-curve)
The Hard Ceiling

Which curve AI will actually trace from here is genuinely thought-provoking.

"The Dawn of Agents" (What is an Agent?)

The following "The Dawn of Agents" section finally dove into the discussion of Agents.

The definition of Agent introduced here was particularly memorable for me:

An Agent is a Large Language Model that uses tools in a loop to pursue a goal

Simple, but it captures the essence of an Agent neatly — a phrasing I find genuinely useful as a mental anchor.

"The Solutions Machine" (Agent-driven problem solving in practice)

The next section, "The Solutions Machine", presented concrete real-world examples of Agents in action.

Example 1: Building a C compiler with multiple Agents in parallel

A case study in which multiple Agents are run in parallel to build a C compiler. You can read the details here:

🔗 https://www.anthropic.com/engineering/building-c-compiler

Example 2: Phased development by 3 role-specialized AI Agents

A case where three role-specialized AI Agents collaborated to develop software in phases. The full write-up is here:

🔗 https://www.anthropic.com/engineering/harness-design-long-running-apps

The mental model behind the Solutions Machine

What I found especially compelling was the mental model used to describe the Solutions Machine:

Feed in Problems and Capital, then iterate Work and Test to produce a Self-improving solution

Just throw in problems and capital, and Agents will autonomously experiment and refine the solution — that future image came into much sharper focus.

"The Great Inversion" (the center of value flips)

Next is the "The Great Inversion" section.

In the traditional approach to problem-solving:

"Identify, define, and scope the problem; Decide to solve it" was relatively cheap, while
"Implement, validate, deploy, and maintain the solution" carried the heavy cost.

But in the new pyramid at 10x Scale, this cost structure is being inverted.

As someone who works at a company traditionally rooted in SI (Systems Integration), this was a slightly uncomfortable message to sit with. The weight of implementation, deployment, and operations is shrinking, while the importance of deciding "what to solve" is growing — and we, too, will need to evolve in response to this shift.

"The Three Doors" (Three compounding opportunities ahead)

In the latter half of the session, "The Three Doors" introduced "Three compounding opportunities" — three directions for putting AI to use going forward:

Empower every employee
Supercharge software development
Create revenue streams

What stood out was that the framing goes beyond engineering efficiency to include empowering every employee across the organization and creating new sources of business value. I'll definitely want to refer back to this framework when thinking about future AI strategy.

All in all, it was a dense, learning-packed session.

Bonus: "Introducing Cowork" at the Anthropic EXPO Booth

Now back to the EXPO for a moment.

Anthropic also had a booth at the EXPO, where a number of in-booth sessions were running throughout the event. I attended one of them, so let me briefly share that as well.

The session I joined was titled "Introducing Cowork". The content covered an explanation of how Claude Cowork works along with a live demo of producing Word, Excel, and PowerPoint deliverables with Cowork. Watching documents come together right in front of me was genuinely exciting — a demo that perfectly embodied the "2026 is the year of Cowork" message from earlier in the day.

The Anthropic booth ran several other sessions as well, with crowds large enough that people were standing in the back. The level of attention Anthropic was getting from attendees was tangible.

Wrap-Up

The Anthropic session I covered today was packed with content:

The dramatic changes coming in the next 2 years
The essence of Agents and the "Solutions Machine" concept
"The Great Inversion" of where value sits
Concrete opportunities through "The Three Doors"

It was a learning-packed session that nudged me to reconsider what "after software" might look like — and how my own work might need to adapt.

The session video is publicly available, so if any of this caught your interest, definitely give it a watch.

To be continued in #4.
[Google Cloud Next '26 Recap #4] Live Report from the Two Keynotes

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

koichim2 — Sun, 03 May 2026 11:11:51 +0000

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

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

On the order screen, choose the type of latte you want (Latte, Non-Fat milk, Mocha, etc.)
Answer a few questions about the design you'd like
Pick your favorite from 4 generated design candidates and hit Submit
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"

[Google Cloud Next '26 Recap #1] Hands-On with the Agentic Hack Zone

koichim2 — Sat, 02 May 2026 08:44:34 +0000

I recently attended Google Cloud Next '26 in Las Vegas. In this post, I'd like to share my experience at one of the most engaging spots on the EXPO floor: the Agentic Hack Zone.

Hands-On Booths at the EXPO

The Next EXPO floor isn't just about flashy demos to look at — it's packed with booths where you can actually open a terminal or console and try things out for yourself. That hands-on element is one of the things that makes the Next EXPO special.

Among all those booths, the one I dove into was the Agentic Hack Zone.

What is the Agentic Hack Zone?

A bold message was displayed at the Welcome desk.

"Build better agents to scale your impact and accelerate your work"

The zone featured 5 booths, each offering a different codelab focused on a specific aspect of agent development. The flow at each booth was simple:

Watch a ~5-minute live demo from an instructor
Run through the codelab yourself

And as a nice bonus — completing all five booths apparently earned you some swag (an Agent Platform T-shirt).

The 5 Booth Themes & Codelabs

Here are the five themes and their corresponding codelab URLs:

#	Theme	Codelab URL
1	Agent Development Kit (ADK)	https://codelabs.developers.google.com/next26/adk-a2ui
2	Agent-to-Agent Protocol (A2A)	https://codelabs.developers.google.com/next26/adk-agent2agent
3	Agent Tools / MCP	https://codelabs.developers.google.com/next26/adk-mcp-tools
4	Agent Governance & Security	https://codelabs.developers.google.com/next26/adk-agent-commerce
5	Agent Builder / Agent Engine	https://codelabs.developers.google.com/next26/adk-deploy-scale

Together, the labs cover the full agent development lifecycle — from the fundamentals of ADK, to inter-agent communication (A2A), tool integration (MCP), governance and security, and finally deployment and scaling.

Heads up

Each lab takes roughly 20–30 minutes to complete

Expect to spend a few dollars in cloud resources while running them

My Experience

At the venue, I was able to complete one of the booths. The booth provided a dedicated PC and a lab account, so there was no setup overhead on my side — I just sat down and got started. Within 20–30 minutes, I had a working agent up and running. The instructor's short demo beforehand was really helpful too: it gave me a clear mental model of where the lab was heading before I dove into the steps.

I'm planning to tackle the remaining four labs back home.

Want to Try It Yourself?

The good news. You don't have to be at Next to do these codelabs. They appear to be publicly available online, so anyone interested in modern agent development — ADK, A2A, MCP, and the rest — can give them a try using the URLs above. The labs are short, focused, and a great way to get a feel for the full agent stack.

Happy hacking!

To be continued in #2.
[Google Cloud Next '26 Recap #2] Three Unique Booths I Tried at the EXPO

Gemini 3.1 Pro: The Next Evolution of Multimodal AI

koichim2 — Sat, 21 Feb 2026 05:26:10 +0000

Gemini 3.1 Pro is officially here, bringing a massive upgrade to Gemini App. With state-of-the-art models for image (Nano Banana), video (Veo), and music (Lyria 3) generation—plus real-time conversational capabilities via Gemini Live—the multimodal toolkit is more powerful than ever.

Gemini 3.1 Pro: Announcing our latest Gemini AI model

3.1 Pro is designed for tasks where a simple answer isn’t enough.

blog.google

I immediately test-drove the new Lyria 3 music generation feature. It produced a stunningly high-fidelity, 30-second track (have a listen below 🎧).

Crucially, all tracks include a "SynthID" watermark for clear AI identification. When evaluating new technologies for actual projects and enterprise environments, this level of built-in governance and transparency is a massive advantage.

Which feature are you most excited to try first?