Tinyml Microcontroller Ai

Skill Profile

(Select at least one profile to enable specific modules)

[ ] DevOps
[x] Backend
[ ] Frontend
[ ] AI-RAG
[ ] Security Critical

Overview

TinyML Microcontroller AI enables deployment of machine learning models on resource-constrained microcontrollers (MCUs) with limited memory, compute, and power. This capability is essential for edge AI applications requiring offline operation, low latency, and energy efficiency in industrial IoT, smart devices, and embedded systems.

Why This Matters

Offline Intelligence: Enables AI capabilities without cloud connectivity, critical for remote or offline applications
Low Latency: Sub-millisecond inference for real-time applications where every millisecond counts
Energy Efficiency: Battery-powered devices with months/years of operation through power optimization
Cost Reduction: Eliminates cloud infrastructure and data transfer costs by processing on-device
Privacy: Data processing on-device without leaving the edge, ensuring data privacy and compliance

Core Concepts & Rules

1. Core Principles

Follow established patterns and conventions
Maintain consistency across codebase
Document decisions and trade-offs

2. Implementation Guidelines

Start with the simplest viable solution
Iterate based on feedback and requirements
Test thoroughly before deployment

Inputs / Outputs / Contracts

Inputs:
- Trained TensorFlow/Keras model
- Representative dataset for quantization
- Target hardware specifications (RAM, Flash, compute)
- Performance requirements (latency, power)
Entry Conditions:
- TensorFlow/Keras model trained and validated
- Target microcontroller selected and available
- Development environment set up (PlatformIO, STM32CubeIDE, etc.)
- Hardware constraints understood and documented
Outputs:
- Quantized TFLite model file (.tflite)
- C header file with model data
- Inference implementation code
- Performance metrics (latency, memory, power)
Artifacts Required (Deliverables):
- TFLite model file
- C header file (model_data.cc/h)
- Inference class implementation
- Main application code
- Performance benchmark results
Acceptance Evidence:
- Inference latency measurement (< 100ms)
- Memory usage report (RAM/Flash)
- Power consumption measurement (< 10mW)
- Accuracy comparison with original model (> 95%)
Success Criteria:
- Model size fits in flash memory
- Tensor arena fits in RAM
- Inference latency meets requirements (< 100ms)
- Power consumption within budget (< 10mW)
- Accuracy within acceptable range (> 95% of cloud model)

Skill Composition

Depends on: edge-model-compression (Model optimization techniques)
Compatible with: hybrid-inference-architecture, on-device-model-training
Conflicts with: None
Related Skills: edge-ai-development-workflow, model-optimization-quantization

Quick Start / Implementation Example

Review requirements and constraints
Set up development environment
Implement core functionality following patterns
Write tests for critical paths
Run tests and fix issues
Document any deviations or decisions

# Example implementation following best practices
def example_function():
    # Your implementation here
    pass

Assumptions / Constraints / Non-goals

Assumptions:
- Development environment is properly configured
- Required dependencies are available
- Team has basic understanding of domain
Constraints:
- Must follow existing codebase conventions
- Time and resource limitations
- Compatibility requirements
Non-goals:
- This skill does not cover edge cases outside scope
- Not a replacement for formal training

Compatibility & Prerequisites

Supported Versions:
- Python 3.8+
- Node.js 16+
- Modern browsers (Chrome, Firefox, Safari, Edge)
Required AI Tools:
- Code editor (VS Code recommended)
- Testing framework appropriate for language
- Version control (Git)
Dependencies:
- Language-specific package manager
- Build tools
- Testing libraries
Environment Setup:
- .env.example keys: API_KEY, DATABASE_URL (no values)

Test Scenario Matrix (QA Strategy)

Technical Guardrails & Security Threat Model

1. Security & Privacy (Threat Model)

Top Threats: Injection attacks, authentication bypass, data exposure

[ ] Data Handling: Sanitize all user inputs to prevent Injection attacks. Never log raw PII
[ ] Secrets Management: No hardcoded API keys. Use Env Vars/Secrets Manager
[ ] Authorization: Validate user permissions before state changes

2. Performance & Resources

[ ] Execution Efficiency: Consider time complexity for algorithms
[ ] Memory Management: Use streams/pagination for large data
[ ] Resource Cleanup: Close DB connections/file handlers in finally blocks

3. Architecture & Scalability

[ ] Design Pattern: Follow SOLID principles, use Dependency Injection
[ ] Modularity: Decouple logic from UI/Frameworks

4. Observability & Reliability

[ ] Logging Standards: Structured JSON, include trace IDs request_id
[ ] Metrics: Track error_rate, latency, queue_depth
[ ] Error Handling: Standardized error codes, no bare except
[ ] Observability Artifacts:
- Log Fields: timestamp, level, message, request_id
- Metrics: request_count, error_count, response_time
- Dashboards/Alerts: High Error Rate > 5%

Agent Directives & Error Recovery

(ข้อกำหนดสำหรับ AI Agent ในการคิดและแก้ปัญหาเมื่อเกิดข้อผิดพลาด)

Thinking Process: Analyze root cause before fixing. Do not brute-force.
Fallback Strategy: Stop after 3 failed test attempts. Output root cause and ask for human intervention/clarification.
Self-Review: Check against Guardrails & Anti-patterns before finalizing.
Output Constraints: Output ONLY the modified code block. Do not explain unless asked.

Definition of Done (DoD) Checklist

[ ] Tests passed + coverage met
[ ] Lint/Typecheck passed
[ ] Logging/Metrics/Trace implemented
[ ] Security checks passed
[ ] Documentation/Changelog updated
[ ] Accessibility/Performance requirements met (if frontend)

Anti-patterns / Pitfalls

⛔ Don't: Log PII, catch-all exception, N+1 queries
⚠️ Watch out for: Common symptoms and quick fixes
💡 Instead: Use proper error handling, pagination, and logging

Reference Links & Examples

Internal documentation and examples
Official documentation and best practices
Community resources and discussions

Versioning & Changelog

Version: 1.0.0
Changelog:
- 2026-02-22: Initial version with complete template structure