Codersarts Blog.

Introduction Most AI assistants are good at answering questions but poor at remembering what you asked them to do yesterday. They have no persistent state across conversations — every session starts fresh. The Model Context Protocol (MCP) solves this by letting you build external tools that Claude (or any MCP-compatible host) can call during a conversation, with results persisted wherever you choose. In this tutorial, we build an MCP To-Do List Manager — a local server that g

Semantic chunking is a chunking strategy that groups text based on meaning rather than fixed size. Instead of splitting text after a certain number of tokens, semantic chunking tries to identify: topic boundaries, semantic transitions, and coherent conceptual units. The goal is simple: Keep semantically related information together.

Sliding window chunking has become one of the most widely used retrieval strategies because it helps preserve continuity between chunks without requiring complex semantic analysis.

Introduction Most AI email tools work as a single prompt: paste your draft, get a rewrite. The problem is that rewriting well requires two very different cognitive tasks — understanding what is wrong with the email, and then knowing how to fix it. Combining both into one prompt produces mediocre results for the same reason that asking a single person to be both a critic and a writer at the same time produces weak output. In this tutorial, we build an A2A Multi-Agent Email Dra

Chunking is the process of splitting documents into smaller retrievable units before embedding and indexing them. In a RAG pipeline: Documents are split into chunks. Each chunk is converted into embeddings. The embeddings are stored in a vector database. User queries retrieve the most relevant chunks. The retrieved chunks are passed to the LLM as context. This means retrieval quality depends heavily on chunk quality.

Introduction Not every piece of text needs the most powerful language model to check it. A short sentence with a grammar error can be caught by a fast, cheap model in under a second. Only long, complex writing with structural and coherence problems genuinely benefits from the most capable model available. Tiered model routing applies this logic systematically. Short to medium text (up to 100 words) goes to GPT-4o-mini for grammar and clarity. If it detects structural or coher

Introduction Finding the next great book is harder than it sounds. Generic bestseller lists ignore your taste, and search engines return the same ten titles for every query. What most readers need is a recommendation that actually understands them — their preferred themes, emotional tone, narrative pace, and the books they already love. In this tutorial, we build an AI-powered Book Recommender using Kimi K2, Moonshot AI’s flagship agentic model. The user describes their readi

Introduction Job interviews are stressful, not because candidates lack skills, but because they lack structured preparation. Most people either over-prepare generic answers or walk in completely unprepared for role-specific questions. In this tutorial, we build an AI-powered Interview Prep Agent using Qwen 3.7 Max, Alibaba’s flagship reasoning model. The agent takes a single job title as input and returns a full preparation package: categorized question types, 8 tailored prac

A production-ready full-stack inventory management system that eliminates spreadsheet chaos, provides real-time stock visibility, and automatically alerts you when inventory falls below reorder thresholds.

Assignment Overview Scenario: You are a research engineer at an academic institution building tools to help researchers manage and analyze scientific literature. Your task is to create an advanced MCP server that not only provides access to research papers but also uses AI sampling (server-initiated LLM calls) to generate intelligent summaries, extract key findings, and compare papers. This assignment builds on Assignment 1 by adding Module 4 concepts: sampling, production pa

Assignment Overview Scenario: You are a software engineer at a productivity software company. Your team is developing an AI-powered personal assistant that helps users manage their daily tasks, projects, and goals. Your task is to build an MCP server that provides intelligent task management capabilities to Claude Desktop, allowing users to interact with their task lists using natural language. Learning Objectives: Implement MCP tools for CRUD operations on task data Design a

Purpose In Assignment 1, you built the core protocol and task-handling pieces. In this assignment, you will extend that foundation into a more realistic system that supports streaming responses, multi-turn conversation continuity, framework integration, observability, and production-minded orchestration. This assignment draws heavily on Chapters 6–7 and asks you to show how FastA2A behaves when it is used as the coordination layer for real application workflows. Connection to

Introduction During a disaster, incident commanders must process conflicting data from dozens of sources, coordinate resources across multiple agencies, and make life-safety decisions under extreme time pressure. Traditional tools and static decision trees cannot keep pace with rapidly evolving, multi-agency incidents. AI-Powered Emergency Response Agents built on Retrieval-Augmented Generation (RAG) address this by continuously retrieving real-time situational data, historic

Purpose This assignment requires you to build a working multi-agent service using the FastA2A design principles covered in Chapters 1–5. You will implement agent identity, capability metadata, structured messages, tasks, context handling, routing, and a basic request/response workflow that mirrors the FastA2A protocol model. Your solution should demonstrate how a real agent system moves from discovery to execution and then back to the client with a stable, inspectable task li

Introduction Programming industrial robots requires mastery of multiple proprietary controller languages, motion planning algorithms, safety standards, and constantly evolving vendor documentation. This knowledge burden slows deployments, escalates costs, and creates dangerous skill gaps across automation teams. Robot Programming Assistance Systems powered by Retrieval-Augmented Generation (RAG) address this by dynamically retrieving relevant vendor documentation, safety stan

Duration: 10–14 days following Assignment 1 Type: Individual Assignment Difficulty Level: Advanced Marks: 100 This assignment requires you to create an original, domain-specific cost optimization strategy for a real-world LLM application that you research or design. Unlike Assignment 1 (general framework), Assignment 2 demands independent research, creative problem-solving, and domain expertise. Learning Objectives Research real LLM cost challenges in a specific industry. Des

Course: LLM Cost Engineering — From Token Economics to Production Monitoring Student Level: Undergraduate Year 3 / Postgraduate Submission Platform: Moodle (Learning Management System) Individual / Group: Individual Assignments Purpose This assignment requires you to design and implement a comprehensive cost optimization framework for a real or hypothetical LLM-powered application. You will leverage every core concept introduced across Chapters 1–9: understand token economics

ASSIGNMENT REQUIREMENT DOCUMENT Course: Agent-to-Agent (A2A) — Multi-Agent Systems in Python Student Level: Undergraduate Year 3 / Postgraduate Submission Platform: Moodle (Learning Management System) Individual / Group: Individual Assignments Total Assignments: 2 This document contains the full specifications for Assignment 1 . Read every section carefully before you begin. You will be assessed on the quality of your implementation, the depth of your analysis, and the c

Purpose In this assignment, you move beyond isolated chunking techniques to design a complete, adaptive chunking system that intelligently detects document types and selects or combines chunking strategies accordingly. This simulates how chunking is actually deployed in production RAG systems — not as a fixed function, but as a design decision that adapts to input characteristics. Connection to Course Learning Outcomes (CLOs) CLO Description Relevance CLO 1 Identify structu

Course: Metadata Filtering Level: Medium → Advanced Type: Individual Assignment Duration: 5–7 days Objective The objective of this assignment is to help you: Understand why metadata filtering is essential for production RAG systems Design a metadata schema for a real-world knowledge base Implement metadata-preserving chunking so that chunk-level metadata is never lost Build and apply pre-filters using ChromaDB's filter syntax Compare pre-filtering vs post-filtering a