​

FAQ

​

What Is Maestro?

​

What exactly is Maestro?

​

How is Maestro different from GitHub Copilot or Cursor?

​

Is Maestro a chatbot that writes code?

• Multiple LLMs, each optimized for specific tasks (research, coding, verification, optimization)
• Secure sandboxes for testing and validation
• Rich toolbox for file management, web research, visualization
• Quality oversight and validation layers

​

Can non-developers use Maestro?

• Software requirements and architecture
• Testing and validation concepts
• Code quality and performance

• Understand what good code looks like
• Recognize test failures
• Evaluate performance metrics
• Make technical trade-off decisions

​

How Maestro Works

​

How does Maestro actually work?

1. Research models: Gather information, analyze approaches
2. Planning models: Design systems, create specifications
3. Implementation models: Write code, refactor, optimize
4. Validation models: Review code, flag issues, ensure quality

• Isolated Ubuntu Linux sandboxes
• Real code execution and testing
• Performance benchmarking
• Validation of claims

• File management and analysis
• Terminal access and execution
• Web research and browsing
• Visualization and diagramming
• External service integration

​

Do I need to write any code?

• Defining goals and constraints
• Making architectural decisions
• Reviewing and validating implementations
• Ensuring quality standards
• Providing domain expertise

• Review Maestro’s implementations
• Spot logical errors
• Validate test coverage
• Make informed technical decisions

​

Does Maestro make mistakes?

• Can misunderstand requirements
• May choose suboptimal approaches
• Sometimes needs multiple attempts
• Occasionally makes logical errors

• Systematic testing
• Multi-model validation
• Quality oversight
• Your review

​

Can Maestro learn from my feedback?

• Maestro incorporates feedback immediately
• Adjusts approach based on corrections
• Learns your preferences and patterns
• Improves throughout the session

• General knowledge doesn’t transfer between sessions
• Each session starts fresh
• But you can provide context via custom instructions

​

Use Cases and Capabilities

​

What kinds of projects can Maestro complete?

• REST APIs and web services
• Full-stack applications
• Database schemas and migrations
• Authentication and authorization systems
• Caching layers and performance optimization
• Integration with third-party APIs

• ETL pipelines
• Data transformation logic
• Quality validation systems
• Data analysis workflows

• Model training pipelines
• Feature engineering
• Inference services
• ML model optimization

• CI/CD pipeline configuration
• Deployment automation
• Infrastructure as Code
• Monitoring and alerting

• Competitive technical analysis
• Performance benchmarking
• Root cause investigation
• Technology evaluation

​

Can I use Maestro with my existing codebase?

• GitHub integration: Clone any repository (public or private)
• Direct upload: Zip or tar your codebase, Maestro extracts it
• Gradual integration: Start with analysis, then implement changes

• Well-tested codebases (Maestro preserves test behavior)
• Clear documentation (helps Maestro understand)
• Consistent patterns (easier to follow and extend)

• Poorly documented legacy code
• No tests (hard to validate changes)
• Highly coupled architecture
• Unusual or proprietary frameworks

​

What if my codebase is too large for Maestro?

• Clone subsets: Work on specific modules/services
• Parallel sessions: Different parts in different sessions
• Strategic cloning: Clone only what’s needed for current work

​

Can Maestro work with multiple repositories?

Clone all relevant service repositories
Implement changes across services
Create coordinated PRs
Link PRs for review coordination

Clone monorepo once
Work on different subsystems
File management keeps work organized

Clone both repositories
Coordinate API changes
Implement frontend consuming new API
Create PRs for both with cross-references

​

Integration and Tooling

​

What tools and integrations are supported?

• GitHub (native integration)
• GitLab (API access)
• Bitbucket (git operations)

• AWS (S3, EC2, Lambda, etc.)
• Azure (Blob Storage, VMs, etc.)
• GCP (Cloud Storage, Compute Engine, etc.)

• PostgreSQL, MySQL, SQLite
• MongoDB, Redis, Memcached
• Any database accessible via connection string

• OpenAI, Anthropic (AI APIs)
• Stripe (payments)
• SendGrid, Mailgun (email)
• Custom REST/GraphQL APIs

• Package managers (pip, npm, cargo, go get)
• Test frameworks (pytest, jest, go test, etc.)
• Build tools (webpack, vite, cargo, maven)
• CI/CD (GitHub Actions compatible)

• Automated browser control
• Screenshot capture
• Web scraping
• Public URL access

​

Can I integrate Maestro with Slack/Discord/Teams?

​

Can Maestro access private resources?

• Private GitHub repos: OAuth authentication
• Private APIs: API keys via credential manager
• Internal databases: Connection strings (ensure network access)
• VPNs: SSH sandboxes can connect through jump hosts

​

Security and Privacy

​

Is Maestro secure?

• Dedicated sandbox per session
• Process isolation between users
• Credential isolation per session

• Encrypted at rest
• User-controlled activation
• Never logged or shared
• Automatic cleanup

• Sandboxed Firecracker microVMs
• No access to host system
• Limited resource quotas
• Network isolation options

• Your code never used for training
• Sessions completely isolated
• Optional data persistence (you control)

​

Does Maestro learn from my code?

• Your session state (if you choose to save it)
• Files you create (in your session only)
• Clone records (for your sessions only)

• Code patterns you use
• Architectural choices
• Domain knowledge
• Anything from your work

​

Can other users see my code?

• Sessions are private to your account
• Other users cannot access your sessions
• Other users cannot see your files
• Other users cannot view your history

​

What happens to my data if I cancel my subscription?

• Checkpointed sessions: Preserved per retention policy (typically 30-90 days)
• Deleted sessions: Immediate removal on request
• Exported files: You keep what you downloaded

​

Billing and Plans

​

How much does Maestro cost?

• Basic: $X/month + Y credits
• Pro: $X/month + Y credits
• Ultimate: $X/month + Y credits

• Model API calls (passed through at cost, no markup)
• Sandbox compute time
• Storage (files and checkpoints)

​

How do credits work?

• Different models cost different amounts
• Longer responses cost more (more tokens)
• Sandbox execution time counted
• Storage and bandwidth included up to limits

• Track balance in UI
• Low balance warnings
• /topup command for quick refill
• Optional auto-reload (configure in settings)

• Real-time credit usage shown
• Warnings before large operations
• Control credit consumption via session management

​

Do I need my own OpenAI/Anthropic accounts?

• We manage API accounts
• We orchestrate model calls
• We pass through costs to your credits
• No markup: You pay model cost + platform fee

​

Can I control costs?

• Shorter sessions cost less
• /compact and /forget reduce ongoing costs
• /refresh reduces token usage per turn

• Disable expensive tools if not needed
• Use faster tools when appropriate (Google vs Perplexity)
• Limit sandbox usage for non-execution tasks

• Use cheaper models for simple tasks
• Use premium models for complex reasoning

• Set maximum auto-reload amount
• Prevent runaway costs
• Manual approval for large expenses

​

Session and State

​

How long can sessions run?

• Sessions checkpoint automatically
• Resumable across long periods
• Context preserved

• Complex projects: Multiple focused sessions better than one massive session
• Capacity management: Easier with bounded sessions
• Checkpointing: Natural session boundaries

​

Can I have multiple sessions?

• Different features in parallel
• Separate concerns (frontend vs backend)
• Experimental vs production work
• Personal vs work projects

​

What happens if my browser crashes?

• Automatic checkpointing saves state
• Refresh browser to reload session
• Complete history restored
• Work continues from where you left off

• Running processes continue
• Files preserved
• Terminal state maintained

​

Can I access my session from different devices?

• Same session on desktop, laptop, tablet, phone
• Synchronized state across all devices
• Answer asks from any device
• Real-time updates

​

Performance and Scale

​

How fast is Maestro?

• Simple code generation: Seconds
• Complex feature implementation: Minutes to hours
• Research and analysis: Seconds to minutes
• Test execution: Depends on your tests

• Model latency (inherent to LLMs)
• Sandbox execution time (real code takes real time)
• Validation thoroughness (quality over speed)

​

Can Maestro handle large codebases?

• Repositories up to ~10GB
• Thousands of files
• Complex architectures

• View files selectively
• Use file search and analysis
• Pattern-based operations

• Well-structured codebases
• Clear module boundaries
• Good documentation

​

What are Maestro’s limits?

• Repository size: ~10GB
• Session capacity: Token-based (manage via commands)
• Sandbox resources: 2 vCPU, 7 GB RAM default
• Public ports: Port 8080 only
• GPU: Not yet available

• Works best on validatable projects
• Requires testable implementations
• Benefits from clear requirements
• Best with existing test infrastructure

• Number of sessions
• Session duration
• Complexity of problems
• Number of tools used

​

Working with Maestro

​

When should I use Maestro vs writing code myself?

• Implementing complete features (not tiny changes)
• Need systematic validation (comprehensive testing)
• Working across many files
• Tackling unfamiliar domains
• Want evidence-driven development
• Speed matters (weeks → days compression)

• Trivial changes (button color, typo fix)
• You already know exact implementation
• Rapid experimentation (trying something quickly)
• Preference for hands-on coding

​

How much should I guide vs let Maestro decide?

• Your experience with Maestro
• Complexity of problem
• Familiarity with domain
• Risk tolerance

• Set goals clearly (what success looks like)
• Define constraints (what must/must not happen)
• Let Maestro propose approaches (leverage its knowledge)
• Validate thoroughly (evidence required)

​

What if Maestro goes off track?

"Stop. This is going in the wrong direction. [Explain correct path]. Reset and start from [point]."

• Acknowledge the correction
• Adjust approach
• Continue with new understanding

• Correct misunderstandings early
• Provide clear constraints upfront
• Validate at milestones, not just end

​

Can Maestro work without internet?

• Model API calls (core functionality)
• Sandbox connectivity
• Web research tools
• External service integration

​

Data and Privacy

​

Where is my code stored?

• In your session state (cloud-hosted)
• In sandbox (temporary, isolated)
• Checkpoints (if persistence enabled)

• Checkpoints preserved per retention policy
• Or immediately deleted (your choice)
• Downloaded files on your machine

• Encrypted in transit and at rest
• Access controlled
• Isolated per user

​

Can I delete my data?

• Delete individual sessions
• Clear all session data
• Remove checkpoints
• Request complete account data deletion

​

Is my session visible to iGent AI staff?

• Automated systems only
• No human access to session content

• If you request support
• With explicit consent
• Limited to debugging specific issue

​

Billing and Costs

​

How are credits charged?

• Model API calls (varies by model)
• Sandbox compute time
• Storage and bandwidth

• Session length (more turns = more cost)
• Model choice (some models more expensive)
• Sandbox usage (execution time)
• File storage size

• Manage capacity to reduce token usage
• Use appropriate models for tasks
• Minimize unnecessary sandbox operations

​

What if I run out of credits mid-session?

1. /topup command for quick credit purchase
2. Auto-reload (if configured) purchases credits automatically
3. Pause session until credits added

​

Can I get refunds for unused credits?

• Subscription fees: Subject to cancellation policy
• Unused credits: May or may not roll over (plan-dependent)
• Refunds: Per terms of service

​

Technical Questions

​

What programming languages does Maestro support?

• Python
• JavaScript/TypeScript
• Go
• Rust
• Java/Kotlin
• C/C++
• Ruby
• PHP
• Shell scripting

• Virtually any text-based language
• Configuration formats (YAML, JSON, TOML, XML)
• Markdown, HTML, CSS
• SQL, query languages

​

Does Maestro support frameworks like React, Django, FastAPI?

• Frontend: React, Vue, Angular, Next.js, Svelte
• Backend: Django, FastAPI, Express, Gin, Actix
• Full-stack: Next.js, Nuxt, SvelteKit
• Mobile: React Native, Flutter (code generation)
• Data: Pandas, NumPy, PyTorch, TensorFlow

• Idioms and best practices
• Common patterns
• Testing approaches
• Performance optimization
• Security considerations

​

Can Maestro help with mobile development?

• React Native (JavaScript/TypeScript)
• Flutter (Dart)
• SwiftUI/UIKit (Swift)
• Jetpack Compose (Kotlin)

• No mobile device emulator in sandbox
• Cannot test iOS apps (requires macOS)
• Android testing possible but limited

• Business logic implementation
• API client code
• State management
• Unit tests

​

Does Maestro work with databases?

• Schema design
• Migration scripts
• Query optimization
• ORM integration (SQLAlchemy, Prisma, etc.)

• Local PostgreSQL/MySQL in sandbox
• SQLite for testing
• Can connect to external databases with credentials

"Design database schema for multi-tenant SaaS.

Requirements:
- PostgreSQL with row-level security
- Tenant isolation
- Migration scripts with Alembic
- Comprehensive tests

Validate by running migrations on test database in sandbox."

​

Comparison to Other Tools

​

Maestro vs Cursor

• IDE extension
• Real-time autocomplete
• Fast inline suggestions
• Works with your editor

• Complete implementation partner
• Autonomous execution and validation
• Handles entire features
• Includes testing and benchmarking

​

Maestro vs ChatGPT/Claude

• General-purpose chatbots
• Code generation via conversation
• No execution environment
• No validation
• You copy/paste code

• Specialized engineering system
• Orchestrates multiple models
• Executes and tests code
• Validates all claims
• Delivers tested, working code

​

Maestro vs Replit/Glitch

• Browser-based IDEs
• Good for prototyping
• You write the code
• Instant deployment

• AI writes the code
• Comprehensive testing
• Production-ready output
• Validation-first approach

​

Getting Help

​

I’m stuck. What should I do?

1. Ask Maestro: “I’m stuck with [X]. How should I proceed?”
2. Check documentation: Search for relevant topic
3. Try different approach: “Let’s try a different way”
4. Use commands: /reset-sandbox, /forget, /refresh
5. Start fresh: New session with lesson learned
6. Contact support: support@igent.ai

​

Something isn’t working as documented

• What documentation says
• What actually happened
• Steps to reproduce
• Session ID if relevant

​

I have a feature request

• Email: support@igent.ai
• Include use case and benefit
• Explain why current features don’t solve it

• User demand
• Strategic value
• Technical feasibility
• Resource availability

​

Is there a community?

• Community forums
• Discord server
• Office hours
• User groups

• Share workflows and patterns
• Provide feedback
• Request features
• Help other users

​

Next Steps

• Best Practices: Production-ready patterns
• Billing Guide: Detailed billing information
• Models: How Maestro’s AI models work