androidengineers.Book a session

LEARN WITH A CLEAR DIRECTION

Gemini Nano + ML Kit GenAI

Build on-device text and image features with Gemini Nano, ML Kit capability checks and explicit download and fallback states.

Intermediate to AdvancedSelf-paced7 modules13 available lessons

Your path, one skill at a time.

Build on-device text and image features with Gemini Nano, ML Kit capability checks and explicit download and fallback states. Follow six teaching modules, each with a practical assignment, then combine the skills in the final project. Start with the introduction even if the tools are familiar: it defines the scope and boundaries of the path.

Self-paced. Complete each exercise and use its checkpoint before moving to the next module. Revisit any prerequisite you cannot yet demonstrate.

What you’ll learn

  • Show unavailable, downloading, ready and failed states
  • Demonstrate that private text is not uploaded on fallback
  • Compare summary fidelity and rewrite meaning on a fixed evaluation set

THE CURRICULUM

Build your knowledge, step by step.

13 lessons across 7 modules. Open a module to explore its lessons and practical work.

01MODULE 01What Gemini Nano and ML Kit do2 lessons · Self-paced
  • Model and runtime
  • Task-specific GenAI
  • Local processing boundary

Distinguish the model, the system runtime and task-specific APIs.

  1. 01What Gemini Nano and ML Kit doLesson · Self-paced
  2. 02Practice: What Gemini Nano and ML Kit doLab · Self-paced

Ready to move on when: You can explain the relationship between Nano, AICore and ML Kit without treating them as interchangeable names.

02MODULE 02Compatibility and model readiness2 lessons · Self-paced
  • Capability checks
  • Download states
  • Resource ownership

Design for devices where the feature cannot run.

  1. 01Compatibility and model readinessLesson · Self-paced
  2. 02Practice: Compatibility and model readinessLab · Self-paced

Ready to move on when: Unsupported hardware and temporarily unavailable model data produce different user guidance.

03MODULE 03Summarization with factual fidelity2 lessons · Self-paced
  • Input boundaries
  • Output evaluation
  • User controls

Preserve the source meaning while shortening text.

  1. 01Summarization with factual fidelityLesson · Self-paced
  2. 02Practice: Summarization with factual fidelityLab · Self-paced

Ready to move on when: Your quality check catches meaning changes, not only awkward wording.

04MODULE 04Rewriting, proofreading and image description2 lessons · Self-paced
  • Rewriting versus correction
  • Image descriptions
  • Accessibility behavior

Choose the task API and evaluate its specific failure mode.

  1. 01Rewriting, proofreading and image descriptionLesson · Self-paced
  2. 02Practice: Rewriting, proofreading and image descriptionLab · Self-paced

Ready to move on when: You select an API based on the required transformation rather than treating every task as generic prompting.

05MODULE 05Prompt API and bounded local generation2 lessons · Self-paced
  • Prompt capability
  • Context budgets
  • Result handling

Use flexible generation without assuming cloud-level capabilities.

  1. 01Prompt API and bounded local generationLesson · Self-paced
  2. 02Practice: Prompt API and bounded local generationLab · Self-paced

Ready to move on when: Flexible prompting remains bounded by input, output and capability checks.

06MODULE 06Performance and local-only delivery2 lessons · Self-paced
  • Cold and warm runs
  • Memory and thermal behavior
  • Fallback contract

Measure resource use and preserve user expectations under load.

  1. 01Performance and local-only deliveryLesson · Self-paced
  2. 02Practice: Performance and local-only deliveryLab · Self-paced

Ready to move on when: Your performance report states the tested hardware and the limits of its conclusions.

07MODULE 07Capstone and portfolio review1 lessons · Self-paced
  • Show unavailable, downloading, ready and failed states
  • Demonstrate that private text is not uploaded on fallback
  • Compare summary fidelity and rewrite meaning on a fixed evaluation set

Build a private writing assistant that summarizes and rewrites locally, with a clear unsupported-device experience.

  1. 01Capstone: Gemini Nano + ML Kit GenAIProject · Self-paced

Ready to move on when: Demonstrate every acceptance criterion and explain the tradeoffs without relying on the lesson text.

PROVE YOUR SKILLS

A portfolio you can build, explain, and defend.

  • Show unavailable, downloading, ready and failed states
  • Demonstrate that private text is not uploaded on fallback
  • Compare summary fidelity and rewrite meaning on a fixed evaluation set

Use the final review rubric to identify gaps. Lesson completion tracks study progress; readiness comes from independently demonstrating the work.

Open the portfolio review rubric →