Using the AI Agent
Learn how to effectively use the AI agent to generate infrastructure with blueprints
How to use the AI agent
The AI agent uses blueprints to generate infrastructure through a three-step workflow:
- Describing your infrastructure needs clearly
- Collaborating with the agent to refine the blueprint plan
- Guiding the agent through blueprint execution
The agent leverages expert-crafted blueprints to ensure each step produces production-ready, enterprise-grade infrastructure code.
Communicate your needs clearly
Begin by describing your infrastructure needs in detail. You can optionally upload your source code and attach pdfs/images to give the agent more context about your application. The agent will select appropriate blueprints and attempt to clarify any ambiguous requests, but the quality of the output depends significantly on how well you describe what you need.
Good requirements:
"I need to set up a highly available web application on AWS using ECS Fargate. The app needs an RDS Postgres database, Redis for caching, and should be deployed across multiple availability zones with enterprise-grade security."
Vague requirements:
"Deploy my app to the cloud."
Collaborate on the blueprint plan
The agent will analyze your requirements and either execute immediately or generate a blueprint with step-by-step instructions. We recommend asking the agent to create a plan for most use cases and spending time collaborating to refine the blueprint steps before execution. This planning stage is crucial for ensuring high-quality results.
Guide the agent through execution
The agent will follow the blueprint and pause after each step, giving you a chance to review changes and address any issues detected by validation checks. The agent uses battle-tested infrastructure patterns with built-in security and compliance, but your guidance ensures the results match your specific needs.
Once you're happy with the infrastructure changes, you can export the code as a zip file for local deployment or sync directly to GitHub or GitLab for CI/CD. The generated code is yours to own and customize - no vendor lock-in.
Working effectively with the agent
- For best results, keep your conversations focused on a single infrastructure task or application. Start fresh conversations for unrelated infrastructure needs to ensure optimal agent context.
- If the agent makes unexpected changes, it's often better to provide more specific requirements and let it regenerate rather than trying to patch the output. The agent works best with clear, detailed specifications.
- Trust the agent's blueprint selections - they include enterprise-grade security and compliance patterns that represent best practices and save significant development time.
- Use the agent's built-in tools like cost analysis, documentation reference, and module registry connections to enhance your infrastructure development workflow.
Using the AI Agent
Learn how to effectively use the AI agent to generate infrastructure with blueprints
How to use the AI agent
The AI agent uses blueprints to generate infrastructure through a three-step workflow:
- Describing your infrastructure needs clearly
- Collaborating with the agent to refine the blueprint plan
- Guiding the agent through blueprint execution
The agent leverages expert-crafted blueprints to ensure each step produces production-ready, enterprise-grade infrastructure code.
Communicate your needs clearly
Begin by describing your infrastructure needs in detail. You can optionally upload your source code and attach pdfs/images to give the agent more context about your application. The agent will select appropriate blueprints and attempt to clarify any ambiguous requests, but the quality of the output depends significantly on how well you describe what you need.
Good requirements:
"I need to set up a highly available web application on AWS using ECS Fargate. The app needs an RDS Postgres database, Redis for caching, and should be deployed across multiple availability zones with enterprise-grade security."
Vague requirements:
"Deploy my app to the cloud."
Collaborate on the blueprint plan
The agent will analyze your requirements and either execute immediately or generate a blueprint with step-by-step instructions. We recommend asking the agent to create a plan for most use cases and spending time collaborating to refine the blueprint steps before execution. This planning stage is crucial for ensuring high-quality results.
Guide the agent through execution
The agent will follow the blueprint and pause after each step, giving you a chance to review changes and address any issues detected by validation checks. The agent uses battle-tested infrastructure patterns with built-in security and compliance, but your guidance ensures the results match your specific needs.
Once you're happy with the infrastructure changes, you can export the code as a zip file for local deployment or sync directly to GitHub or GitLab for CI/CD. The generated code is yours to own and customize - no vendor lock-in.
Working effectively with the agent
- For best results, keep your conversations focused on a single infrastructure task or application. Start fresh conversations for unrelated infrastructure needs to ensure optimal agent context.
- If the agent makes unexpected changes, it's often better to provide more specific requirements and let it regenerate rather than trying to patch the output. The agent works best with clear, detailed specifications.
- Trust the agent's blueprint selections - they include enterprise-grade security and compliance patterns that represent best practices and save significant development time.
- Use the agent's built-in tools like cost analysis, documentation reference, and module registry connections to enhance your infrastructure development workflow.