Join Maestro Studio AI Private Preview




Enter your name, email address and a brief message describing your use case below to join the Maestro Studio AI private preview program.

If you would like to experience Maestro Studio AI before you get access to the program, use our Request a Demo form to book a demo with our team.

If you run into issues with this form, use our Support form or email us: support@stratuson.com


Start Using Conversational AI


Maestro Studio AI is a SaaS solution that generates Azure artifacts (ARM Templates, UI Definition and View Definition files) from the natural language description of the desired solution in Azure.

Maestro Studio AI
Watch Demo  

Frequently Asked Questions

Click on any question below to expand it and see the related answer.

HCL is excellent and very popular, and Terraform Infrastructure-as-Code (IaC) is a great choice for defining and managing the building blocks of your cloud infrastructure—arguably the gold standard when it comes to cross-platform IaC. And Bicep is great too, and it is in many ways inspired by HCL.

For Azure, our preference is native IaC, i.e. ARM templates. One reason is that even Bicep files are converted to ARM templates before being deployed, so why not save an extra step and go straight to ARM templates? But the key reason for choosing ARM over the other IaC variants is that ARM templates are idempotent, so they enable deployments to produce repeatable results. This is a major differentiator from general, cross-platform IaC like HCL.

One key friction point impacting the adoption of ARM templates has been the JSON-based syntax that many consider archaic (even though it is similar to AWS CloudFormation's syntax), especially when compared to HCL. Bicep solved some of those problems by providing a cleaner, more intuitive syntax.

Rather than re-invent another wheel, we decided to address the root cause of the problem. At StratusOn, we started using generative AI internally to generate our own ARM templates. We used conversational AI and natural language to build the Quickstart Templates we offer in our Maestro Studio ENSEMBLE product. Our conversational AI journey has not been easy, but now that we've gotten the technology to a mature state—increasing the quality of its results and eliminating hallucination-type results—we are ready to share our work publicly. We are confident it will be as useful to others as it has been to us, and perhaps even more useful to many who are new to Azure and to ARM templates.

The following Azure documentation page provides a good ARM template primer (great for those new to Azure), and it lists ample reasons highlighting why ARM templates are still superior and deserve to be supported: Why choose ARM templates?

One of the main reasons we have waited so long before introducing Maestro Studio AI was to get it to a mature state by building the guardrails and validations that help us introduce it today while being confident that it will only provide valid, working ARM templates that are ready to deploy.

We are the first to admit that no product is perfect, and we continue to work hard to fine-tune and improve the workflow for generating ARM templates from natural language queries. We take feedback very seriously and have been using feedback from private preview participants to improve the quality and accuracy of the results.

We make it easy to provide us with quick feedback about problems encountered or suggestions you think can help improve the product.

The private preview is currently limited to only a subset of Azure resources, specifically resources that are required and supported for publishing Azure Applications to the Azure Marketplace.

Participants who need to have access to the expanded set of Azure resources during the private preview can use the feedback feature (accessible on the private preview website) to let us know. In most cases, we should be able to assign your account to a compute stamp with expanded resource support.

We are limiting the ARM templates generated to a maximum size of 100 KiB for the JSON. We also limit the generated templates to no more than 20 resources (including resources in nested ARM templates) during the private preview.

The feedback feature on the private preview website can be used to request a quota increase for both the JSON payload size and the number of resources.

The private preview is limited to a maximum of 10 natural language questions per day. This helps us balance the utilization of the compute stamps among private preview participants.

Use the feedback feature on the private preview website to request a quota increase of the number of questions per day, and we will move the corresponding account to a compute stamp that allows a higher number of questions (the upper ceiling is 100 during the private preview).

We are tentatively planning to move Maestro Studio AI to general availability (GA) by the end of January 2025.

All participants in the private preview will be moved to the free tier at that time.

Private preview participants have the ability to cancel their participation in the program at any point in time.

We are currently allocating a limited compute capacity to the private preview to make it easier for us to troubleshoot problems encountered by early participants before we open the floodgates.

We are assigning private preview participants into batches with each batch allocated resources on a separate compute stamp (essentially a cluster of compute resources and dependencies). When the stamps are all full, we place new subscribers on a waitlist until we have allocated new stamps.

Ultimately, we want everyone to be able to join the private preview. If you receive a confirmation message stating that you've been placed on a waitlist, please rest assured that we'll get you into the program as soon as we have resources provisioned. We appreciate your patience, but if you don't hear back from us after two weeks, then this is very likely due to a glitch on our side: please contact StratusOn Support and make sure to mention the email address you have signed up with.

We certainly don't think so, which is why we've waited so long before making this product publicly available, albeit in a private preview program for the short term.

We built this initially as something we needed to build our own ARM templates. Just like any other AI product (or even non-AI software product), it continues to be tuned and improved—and it continues to get better, faster and more accurate. Over time, our internal project transformed into something beyond what we had originally envisioned, and we are very excited to share it publicly so that others can enjoy the same benefits.

But don't take our word for it—try it out for free and see for yourself.