AI Journal
10 Days of AI
Documenting the journey through AI and machine learning concepts — one day, one build, one set of notes at a time.
Progress
7/10
Day 1: AI is literally a baby
Introduction to AI and Large Language Models — how models learn, and how the input/output relationship grew from text-only chatbots into multimodal systems.
Day 2: Whisper, Prompt Templates and Chains
OpenAI's Whisper API, plus LangChain's TypeScript module — prompt templates and sequential LLM chains.
Day 3: Retrieval-Augmented Generation
RAG — grounding an LLM against a knowledge base, and building a PDF question-answering system with LangChain.
Day 4: Model Context Protocol (MCP)
MCP as an open standard for connecting AI applications to external systems, networks and databases.
Day 5: The first major roadblock
Building an MCP server for Claude Desktop — the script ran, the client never picked it up. A debugging post-mortem.
Day 6: Text to Speech using generated voices
Building a voice-over generator on ElevenLabs — an artificially generated voice model driven by whatever text the user types.
Day 7: Coming Soon
Add your content summary for day 7 here.
Day 8: Coming Soon
Add your content summary for day 8 here.
Day 9: Coming Soon
Add your content summary for day 9 here.
Day 10: Finale — Agents and the state of AI
Wrapping the challenge: interoperability between providers, what agents actually are, and everything explored across the ten days.