Google has made it possible for anyone to build an AI agent without writing a line of code. It is called Agent Designer, and it sits inside the new Gemini Enterprise app. The launch happened on the 22nd of April at Google Cloud Next in Las Vegas, in front of 32,000 attendees.
Let me set the scene. Google has retired Vertex AI, the developer platform most enterprises were using, and replaced it with something called Gemini Enterprise Agent Platform. If you heard the episode earlier this year on OpenAI Frontier, this is Google’s answer to that. The platform sits behind the scenes. The thing your team will actually see is the Gemini Enterprise app, and inside that app is Agent Designer.
Agent Designer is a no-code visual builder. You describe what you want the agent to do in plain English, or you drag and drop steps onto a canvas, and the agent gets built. No developer required. No prompt engineering certificate. Just a clear understanding of the workflow you want to automate.
What this looks like in practice
Imagine a comms team handling FOI requests. You build an agent that reads the incoming request, checks it against your previous responses, drafts a reply, flags anything sensitive for human review, and logs the case. Or a procurement team where the agent monitors supplier deadlines, chases missing documents, and updates the project file. Tasks that used to need a developer and three months. Agent Designer compresses that into an afternoon.
The technical capability
Now, the technical bit, because it matters. The platform underneath has been rebuilt for serious work. Cold starts are under one second, which means agents spin up almost instantly. Long-running agents can now run autonomously for days at a time, with Google’s release notes confirming support for operations of up to 7 days. There is something called Memory Bank that gives agents persistent memory, so they remember context across sessions. Your agent does not start from scratch every morning. It picks up where it left off.
And here is the multi-model part. The platform gives you access to Gemini 3.1 Pro, Google’s reasoning model, and also to Anthropic’s Claude Opus, Sonnet, and Haiku. More than 200 models in total. Google is no longer trying to lock you into one family. They are positioning themselves as the orchestration layer.
The access reality
Now, let me be honest about the access reality. This is not free, and it is not in your standard Microsoft 365 subscription. Gemini Enterprise app and Agent Platform are paid Google Cloud products. Your organisation needs a Google Workspace or Cloud agreement, and someone in IT needs to enable Gemini Enterprise. So if you are listening and thinking, “I’ll try this tomorrow morning,” the answer is probably no, unless you are already a Google shop.
Governance
A quick word on governance, because I cannot ignore it on a tool that lets a marketing manager spin up an agent with access to your CRM. Google has built in something called Agent Gateway, which is the security checkpoint between agents and the systems they touch. It uses a service called Model Armor to screen for prompt injection and sensitive data leakage. The guardrails exist. But guardrails only work if your IT team configures them, monitors them, and updates them. Agentic AI is more powerful than traditional automation, and that means it is also more dangerous when it goes wrong. Human oversight is not optional here.
If you want to build your AI literacy and skills, I can help
📚 Grab AI Playbook on Amazon, the perfect podcast companion.
📰 Subscribe to Human in the Loop, my LinkedIn Newsletter
🎓 Take the CPD Accredited AI Playbook Diploma
📞 Book a call at digitaltraining.ie
Sources
- Introducing Gemini Enterprise Agent Platform — Google Cloud Blog (announcement): cloud.google.com/blog/products/ai-machine-learning/introducing-gemini-enterprise-agent-platform
- Gemini Enterprise Agent Platform overview — blog.google: blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/gemini-enterprise-agent-platform
- Google Cloud Next 2026 wrap-up (260 announcements, 32,000 attendees): cloud.google.com/blog/topics/google-cloud-next/google-cloud-next-2026-wrap-up
- Agent Platform release notes (sub-second cold starts, up to 7-day operations): docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes
- The new Gemini Enterprise — one platform for agent development (Agent Designer detail): cloud.google.com/blog/products/ai-machine-learning/the-new-gemini-enterprise-one-platform-for-agent-development
- Agent Gateway and Model Armor — Google Cloud documentation: docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/agent-gateway-overview
- Next ’26 — security with Google Cloud and Wiz (Model Armor scope): cloud.google.com/blog/products/identity-security/next26-redefining-security-for-the-ai-era-with-google-cloud-and-wiz
- Google Announces New Gemini Enterprise Agent Platform — THE Journal (independent coverage): thejournal.com/articles/2026/05/04/google-announces-new-gemini-enterprise-agent-platform.aspx
Key Statistics
- Announced at Google Cloud Next ’26 in Las Vegas, the opening keynote on 22 April 2026
- 32,000+ attendees; 260 announcements across the week
- Sub-second cold starts on the rebuilt Agent Runtime
- Long-running agents now supported for operations up to 7 days
- More than 200 models available through Model Garden, including Gemini 3.1 Pro, Gemma 4, and Anthropic’s Claude Opus, Sonnet, and Haiku
- $750 million Google Cloud innovation fund for partners building AI agents
- Agent Designer (no-code, knowledge worker) and Agent Studio (low-code, developer) are the two builder tools, both governed through Agent Platform
- Vertex AI is being retired — all roadmap evolutions move to Gemini Enterprise Agent Platform
About the Podcast Host
AI and Communications Specialist | Author | Podcaster | International Speaker
Joanne Sweeney is a recognised leader in digital marketing and digital transformation, specialising in the practical application of AI to enhance communication strategies. The founder of Digital Training Institute, Joanne, empowers leaders and communications professionals to leverage AI responsibly and effectively, ensuring transparency, trust, and tangible results.
She completed the Harvard Kennedy School Executive Programme in AI and Public Policy this summer before launching her fourth book AI Playbook, in September. Joanne has also published two editions of Public Sector Marketing Pro, which were preceded by her first title, Social Media Under Investigation Law Enforcement and the Social Web.
Her books have become go-to resources for governments, public sector and policing agencies, as well as marketing and communications professionals, all navigating the challenges of the changing Internet.
Joanne is the host of the AI SIX Podcast, a daily six-minute podcast that provides actionable insights, expert interviews, and practical advice to help professionals navigate the new world of work.
