Part of the “Understanding LLM from Scratch” collection — standalone posts unpacking how LLMs actually work, written as I learn. Multilingual embeddings are the mechanism that lets a language model read “5 …
Byte Pair Encoding — How LLMs Tokenize Text
Byte Pair Encoding (BPE) is the algorithm that turns raw text into tokens — the units every LLM reads, reasons in, and is billed by. This post traces how it …
AI Agent Portal: Try Before You Integrate
Part 11 of “My Journey in Building Agents from Scratch” — building a React portal where teams can discover agents, try them against real use cases, and see what’s happening …
AI Agent Vector Search
Part 9 of “My Journey in Building Agents from Scratch” — AI agent vector search with a YAML-driven ingestion pipeline At the end of Part 8, I left a failure unresolved. …
AI Agent Planning Module: Step Tracking & YAML Workflows
Part 7 of “My Journey in Building Agents from Scratch” — building an AI agent planning module AI agent planning module: two-phase plan-then-execute flow showing step list with status The …
AI Agent Reasoning Layer: ReAct Pattern in Python
Part 6 of “My Journey in Building Agents from Scratch” Building a capable AI agent is straightforward — until it has to make more than one decision to answer a …
AI Agent Session Management: Streaming & State
Part 5 of “My Journey in Building Agents from Scratch” The Black Box Problem in AI Agent Session Management In my last post, Automating Agent Creation with Templates, I had …
Shared Python Tools for AI Agents Using MCP
Part 3 of “My Journey in Building AI Agents from Scratch” Introduction In Part 2, I built my first agent from scratch — LLM + tool calling + context management. …
Building AI Agents: My First Agent with LLM and Tool Calling
Part 2 of “My Journey in Building AI Agents from Scratch” Introduction In Part 1, I shared why I started with Autogen and hit its limits. This post is about …