Sandeep Bazar 365 Days of AI
Labs

Courses › Course07

Course07 · AI Engineering: Agents and Applications

Agents, MCP, AI coding tools, evaluation, and full-stack AI applications — engineering AI systems that hold up in production.

42 days 0 written 0 complete

Days 288-294 · AI Agents 0/7 complete
  1. Day 288 What an AI Agent Is planned
  2. Day 289 The Agent Loop: Reason, Act, Observe planned
  3. Day 290 Designing Tools for Agents planned
  4. Day 291 An Agent from Scratch planned
  5. Day 292 Agent Frameworks and When to Use Them planned
  6. Day 293 Multi-Agent Systems planned
  7. Day 294 Building a Research Agent planned

Project: Research Agent — Build an agent that researches a question with search and note-taking tools and produces a cited brief.

Days 295-301 · The Model Context Protocol 0/7 complete
  1. Day 295 What MCP Is and Why It Exists planned
  2. Day 296 Using MCP Servers planned
  3. Day 297 Building an MCP Server planned
  4. Day 298 MCP Resources and Prompts planned
  5. Day 299 Building an MCP Client planned
  6. Day 300 MCP Security planned
  7. Day 301 Your Personal MCP Server planned

Project: Personal MCP Server — Build and test an MCP server exposing your own data or tools, and use it from a real client.

Days 302-308 · AI Coding Agents 0/7 complete
  1. Day 302 The AI Coding Landscape planned
  2. Day 303 Working with a Coding Agent planned
  3. Day 304 Effective Agentic Coding Workflows planned
  4. Day 305 Configuring Agents: Memory, Skills, and Rules planned
  5. Day 306 Reviewing and Trusting AI-Written Code planned
  6. Day 307 Coding Agents in CI and Automation planned
  7. Day 308 Shipping a Feature with an Agent planned

Project: Agent-Built Feature — Ship a reviewed, tested feature to one of your own projects using an AI coding agent, documenting the workflow.

Days 309-315 · Evaluation and Reliability 0/7 complete
  1. Day 309 Why Evals Are the Real Moat planned
  2. Day 310 Building Evaluation Datasets planned
  3. Day 311 LLM-as-Judge planned
  4. Day 312 Regression Testing for Prompts and Models planned
  5. Day 313 Guardrails and Content Moderation planned
  6. Day 314 Observability and Tracing for AI planned
  7. Day 315 An Evaluation Harness planned

Project: Evaluation Harness — Build an eval harness with a labeled dataset, an LLM judge, and regression gates for one of your AI features.

Days 316-322 · Full-Stack AI Applications 0/7 complete
  1. Day 316 Architecture of an AI Product planned
  2. Day 317 Backend Patterns for LLM Apps planned
  3. Day 318 Chat UX and Streaming Frontends planned
  4. Day 319 Auth, Quotas, and Billing planned
  5. Day 320 Latency and Caching planned
  6. Day 321 Vendor Abstraction and Fallbacks planned
  7. Day 322 A Full-Stack AI Application planned

Project: Full-Stack AI App — Build a deployed chat application with streaming, auth, usage quotas, and a vendor-abstraction layer.

Days 323-329 · Production Retrieval and Pipelines 0/7 complete
  1. Day 323 Data Ingestion Pipelines planned
  2. Day 324 Document Processing at Scale planned
  3. Day 325 Keeping Indexes Fresh planned
  4. Day 326 Scaling Retrieval planned
  5. Day 327 Cost Engineering for AI Systems planned
  6. Day 328 Privacy in AI Systems planned
  7. Day 329 Section Project: A Production Assistant planned

Project: Section Project: Production Assistant — Assemble a production-grade assistant: ingestion pipeline, fresh index, evals, cost budget, and privacy review.