en
Automating tasks in IT environments has always been a complex process: it required time, technical knowledge, and multiple iterations. With Create with AI, Flexxible’s microservice designer with AI, we have transformed this reality: you can now turn a need into a functional microservice simply by describing what you want to create in natural language.
However, as with any tool, the quality of the results depends directly on how we frame the request. Unlike general language models, Create with AI is specifically trained to develop microservices in digital workspace management environments: it knows the context, best practices, and common patterns in end-user management. Your job is simply to communicate clearly what problem you want to solve.
Let's think about two real scenarios:
Unclear request:
"Can you make a backup copy of the desktop and documents?"
Effective request:
"Make a backup copy of the desktop and the Documents folder. Copy these files to a ZIP file in \nas\backups-<username>. I want to keep only the most recent copy. Delete the rest of the files at the moment the copy has been completed successfully."
The difference is clear.
The first leaves too many questions unanswered: where is the copy saved?, in what format?, what happens with old copies?
The second eliminates all ambiguity and provides a microservice ready for production.
Brevity doesn't mean omitting information; it means communicating directly. Avoid detours, unnecessary polite phrases, or explanations that don't add technical value.
Instead of: "I would like, if possible, for you to help me create something that mightperhaps be useful for..."
Write: "Create a microservice that..."
Specificity is your best ally. Include all relevant technical details: file paths, output formats, execution conditions, restrictions, and any other element that defines the expected behavior.
Think about these aspects:
Context allows the AI to understand not only what it should do, but also why and underwhat circumstances. Indicate the purpose of the microservice, the environment where it will be applied, and any relevant considerations about the fleet of devices or users.
For example: "Create a scheduled task in Windows 11 for remote work environments. The task should log out the current user when 30 minutes of inactivity are detected, to improve security on shared devices."
Communicate actions directly. Instead of asking or suggesting, clearly indicate what the microservice should do.
Effective verbs: create, generate, detect, notify, copy, delete, verify, compare,execute, schedule, monitor.
Eliminate ambiguity. Every request should have only one possible interpretation. If when reading it you can imagine two different ways to implement it, add more details.
Iterate when necessary. One of the advantages of Create with AI is that you can refine the result using natural language. If the first attempt isn't exactly what you were looking for, simply adjust the instruction:
Include reference examples. When possible, show what the result should look like. This guides the AI on the output format, data structure, or expected behavior.
Define constraints and rules. Specify clear limits
Establish success criteria. Explain what should happen to consider that the microservice works correctly. This allows generating code with appropriate validations and error handling.
❌ Not effective: "Notify users when they need to restart."
✅ Effective: "Detect if the device hasn't been restarted for more than 30 days and notify the user to schedule a restart. The notification should appear once a day and offer options to restart now, schedule for tonight, or postpone 24 hours."
❌ Not effective: "Delete old files."
✅ Effective: "Delete files from theC:\Windows\Temp folder older than 7 days. Exclude files currently in use. Generate a log with the number of files deleted and space freed inC:\Logs\TempCleanup.txt."
❌ Not effective: "Check disk space."
✅ Effective: "Verify available space on all local drives. If any drive has less than 10% free space, send a notification to the user and log the event in the Flexxible log with warning level."
Unlike general AI assistants, Create with AI deeply understands the digital workspace management ecosystem: it knows Windows APIs, scripting best practices for corporate environments, common automation patterns, and the specific challenges of technical support.
This means you don't need to explain basic concepts or provide context about how workplace management works. You can focus on the specific problem you want to solve, trusting that the AI will apply industry best practices.
Traditionally, creating a solution for a recurring problem required a cascading process: analysis, design, development, testing, validation, and deployment. This cycle could take days or weeks, especially if intervention from multiple teams was needed.
With Create with AI, that cycle is reduced to minutes.
The IT team can review the generated code, adjust it if necessary through iterations in natural language, and put it into production immediately.
This not only accelerates solution delivery for an improved digital employee experience, but also frees technical teams to focus on strategic initiatives instead of spending time on repetitive tasks.
Effective automation starts with clarity. When writing your requests in Create with AI, remember: be concise, specific, provide context, and use direct verbs. Eliminate ambiguities, iterate when necessary, and clearly define what the microservice should do and under what conditions.
With these principles, you'll transform your organization's needs into functional solutions with a speed that previously seemed impossible.
The technology is ready. Now is the time to precisely describe what problem you want to solve.
Want to see it in action? Watch the live launch recording now.
Want to try it yourself? Schedule a demo with our team and write "Create with AI" in the comments.
* Gartner®, Magic Quadrant™ for Digital Employee Experience Management Tools, Dan Wilson, Stuart Downes, Lina Al Dana, 26 May 2025.
**Gartner®, Magic Quadrant™ for Desktop as a Service, Stuart Downes, Eri Hariu, Mark Margevicius, Craig Fisler, Sunil Kumar, 16 September 2024
GARTNER® is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally, and MAGIC QUADRANT™ is a registered trademark of Gartner, Inc. and/or its affiliates and are used herein with permission. All rights reserved. Gartner® does not endorse any vendor, product or service depicted in its research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner® research publications consist of the opinions of Gartner's research organization and should not be construed as statements of fact. Gartner® disclaims all warranties, expressed or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.
Carrer de Vallhonrat, 45, 08221
Terrassa, Barcelona, Spain
6750 N. Andrews Avenue, #200, Office 2013, Ft. Lauderdale, FL 33309, USA
+1 919-806-45806th Floor, 2 Kingdom Street, London, W2 6BD, UK
+44 (0) 203 4688752Av. Engenheiro Luís Carlos Berrini, 550 – 41 – Brooklin Paulista, São Paulo 04571-000, Brazil
