Announcing the next generation of Make AI Agents

Back in October 2025, we announced our vision for the next generation of Make AI Agents. We invited Make users to sign up for the waitlist - and realised very quickly that demand was extremely high. Our promise was that Make AI Agents would be as visual and intuitive as every other part of Make. This promise was based on the foundation of trust our customers have come to expect in the transparency and clarity of Make. 

We’re delighted to be able to deliver on that promise and to give our users new, improved next-generation AI agents developed according to the core principles on which Make itself was built.

With today’s announcement, we’re inviting Make users to build AI agents you can share across teams and workflows, orchestrating processes across 3000+ apps, combining adaptive AI decision-making with transparent, reliable automation in one visual platform. This means you can scale efficiently, handle more work, and stay in control as AI moves from experiments to real business value.

The new generation agents will help businesses automate complex work while keeping full visibility into how decisions are made, how systems connect, and how costs scale. This means you get the speed of AI, the reliability of automation, and the clarity needed to operate at scale for results you can trust. 

What’s new?

Agents that live inside the scenario builder

We listened to your feedback to deliver what we believe is a major step change - agents that are built, run, and debugged inside the same canvas as your scenarios. This means that you can create agents that interpret input, choose the right tools, and adapt within your workflows. 

Radical transparency, built into the canvas

Because the agents exist within the automation canvas, every decision is visible, reviewable, and controllable in the exact place you build and run your workflows. Nothing runs behind the scenes. This next generation of Make AI Agents doubles down on the unique visual approach that Make is known best for. The new Reasoning Panel gives you a clear real-time view into how your agent thinks, which tools it calls, and why it takes each path so you can build with confidence, debug faster, and prove what happened. Your agent can be equipped with tools in seconds by selecting any Make app and module and still have full control over which inputs are determined by AI and which are set by you. It’s AI you can see, understand, and trust, that is designed for real workflows not black boxes.  

In-canvas chat for faster refinement

You can now chat directly with your AI agent inside the Make canvas to test, refine, and improve its behaviour in real time. This makes iteration faster and more intuitive; ask questions, probe decisions, and adjust instructions without leaving your workflow. By keeping conversation and execution in one place, the in-canvas chat helps you move from first build to reliable results with far less friction, while maintaining full visibility into how your agent responds and why. 

Multi-modal support for real workflows

Make AI Agents now go beyond text. With built-in multi-modal support, you can provide files directly to your agent and have it generate files as part of your workflow. Agents can now accept, analyse, and produce f PDFs, images, CSVs, and more, directly as inputs and outputs on the canvas. This overcomes limitations such as text-only formats, having to rely on complex external OCR tools, or manually parsing files. Now, you can turn unstructured data into actionable workflow assets automatically.

A focus on shareability

Our new approach has also allowed us to incorporate one of the most important pieces of feedback - we can now share pre-built AI agents and allow users to share their valuable use cases with each other for inspiration. For teams looking to orchestrate or scale their outputs, instead of having to duplicate solitary Agents, full scenario solutions that combine the best of deterministic automation with Agents can now be shared. That means the full flexibility to adapt Agents as frequently as use cases crop up, but with more ease. To help with this, we’re also introducing a new Library of Agents that gives you ready-made AI Agent examples built for real workflows, not demos. 

A Library of Agents built for real business workflows

The new Library of Agents gives you a practical starting point for building with confidence. Instead of beginning from a blank canvas, you can explore ready-made AI Agent examples designed for real-world scenarios, like inventory management, research, triage, reporting, and more.

Each template shows how deterministic automation and agentic reasoning work together, so you can understand the structure, adapt it to your needs, and deploy faster. The Library of Agents provides a shortcut to production-ready agents with full visibility, control, and scalability built in from the start.

What’s next?

Get started straight away with the next generation Make AI Agents. Learn more about the key features of the new Make AI Agents and the benefits you can enjoy in this deep dive article.

Learn more about when to use Make AI Agents - and how to maximise their potential.