arrow_back अभ्यास
Phase 9 • Week 43

Tool-Calling & MCP in Spring AI, Design a Rate Limiter

verified_user

Weekly Production Deliverable

Target Output
Deliverable: Capstone can now call tools and reason over real data. A minimal working MCP server — cutting-edge for a 2027 interview. Second fresh system-design problem (Rate Limiter) practiced.
Weeks: W41 W42 W43 Active W44 W45

Monday

0 / 2 done
DSA Weekly contest
1.5h
AI/ML Tool Calling Design Principles
How LLMs decide when to call tools; writing clean tool names, descriptions, and JSON schemas; designing tools for read vs write operations
2.5h

Tuesday

0 / 2 done
DSA Redo 2 hard problems, weakest topic
1.5h
CORE Fresh HLD Practice: Distributed Rate Limiter & Netflix Video Pipeline
Distributed Rate Limiter (Token Bucket, Lua scripts, Redis) + System Design of Netflix Video Onboarding Pipeline (Transcoding, chunking, manifest generation, multi-CDN caching)
2.5h

Wednesday

0 / 2 done
DSA Redo 2 hard problems, second weak topic
1.5h
AI/ML Model Context Protocol (MCP) Foundations
Read modelcontextprotocol.io: What problem MCP solves, MCP Clients vs Servers, standardizing context and tool access across enterprise agents
2.5h

Thursday

0 / 2 done
DSA Light mixed practice
1.5h
CORE Distributed Rate Limiter Architecture
Distributed counter storage (Redis), race conditions with Redis Lua scripts, fail-open vs fail-closed strategies, integration with API Gateways
2.5h

Friday

0 / 2 done
DSA Second weekly contest
1.5h
AI/ML Design Tools for Capstone
Define 2 tools for the capstone: (1) Live Database Query Tool (e.g. searching study notes metadata), (2) External API Search Tool; write clean schemas
2.5h
⚡ Weekend High-Load Execution • 8.0h Daily Deep Focus Lab

Saturday

0 / 3 done
DSA Review contest mistakes
1.5h
AI/ML Spring AI Function Calling & Tool Execution (4.0h)
Register Java @Bean functions for tool-calling (database queries, weather, calculator); observe LLM tool orchestration.
4.0h
JAVA Spring AI Tool Calling Implementation
Expose Java @Bean methods as tools via Spring AI @Description; wire tools into ChatClient; test automatic tool invocation and output synthesis
2.5h

Sunday

0 / 3 done
DSA Full mixed revision
1.5h
AI/ML Model Context Protocol (MCP) Server Architecture (4.0h)
Implement an MCP server in Java providing structured enterprise tools and resources to LLM agents.
4.0h
JAVA Spring AI MCP Server
Build a standalone MCP server using Spring AI's native MCP support; expose tools via MCP protocol; test with an MCP client; push to GitHub
2.5h
edit_note

Week 43 Technical Notes & Journal

#LeetCode #Java #DSA #Week43