Skip to content

vidyabhandary/Kaggle5DayAICourse

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Kaggle5DayAICourse

Repo for Kaggle 5 Day AI Course

https://www.kaggle.com/learn-guide/5-day-agents

🤖 5-Day AI Agents Intensive with Google (Kaggle x Gemini)

Repository documenting the 5-Day AI Agents Intensive Course by Google & Kaggle.


📆 Course Structure

Day Topic Key Focus
Day 1 Introduction to Agents Taxonomy, reliability, interoperability, and identity policies
Day 2 Agent Reasoning & Tools How agents use tools and reason through complex tasks
Day 3 Multi-Agent Systems Architectures, communication, and coordination
Day 4 AgentOps & Governance Reliability, monitoring, and secure agent deployment
Day 5 Capstone Project Designing and implementing a real-world AI agent system

🧠 Key Learnings

  • Understood what AI Agents really are — systems that reason, act, observe, and iterate instead of just generating text.
  • Learned the Agent Architecture:
    • Model (Brain) for reasoning
    • Tools (Hands) for taking real-world actions
    • Orchestration Layer (Nervous System) for planning, memory, and control
  • Built my first agent using Gemini 2.5 Flash + ADK, including planning, tool-calling, and multi-step reasoning loops.
  • Created a multi-agent system and understood coordination patterns like:
    • Shared vs. individual session histories
    • Delegation between agents
    • A2A communication
  • Learned the foundations of Context Engineering:
    • Sessions vs. Memory
    • How to build dynamic context windows
    • How agents maintain state, recall past interactions, and optimize long conversations
  • Studied Agent Quality:
    • Observability (logs, traces, metrics)
    • LLM-as-a-Judge & evaluation datasets
    • Safety, robustness, and guardrails
  • Understood productionizing agents:
    • CI/CD pipelines for agents
    • Safe rollout strategies
    • Monitoring cost, latency, and drift
    • Security hardening, identity, and constrained policies
  • Explored interoperability through MCP and A2A, enabling tools, remote agents, and enterprise integration
  • Gained hands-on experience using Google Search grounding, built-in tools, and NotebookLM for research and refinement

🧩 Tools & Tech Used

  • Gemini API via Google AI Studio
  • Agent Development Kit (ADK)
  • Kaggle Notebooks for all codelabs
  • NotebookLM for interactive research
  • Discord Community for Q&A and networking

🧩 Official Resources

About

Repo for Kaggle 5 Day AI Course

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published