ENGINEERING MISSIONS
Projects
Missions, not courses. Each ends in a running system, scored by the same evaluation suite.
PROJECT 01 · OPENFREE
AI Chat ApplicationBeginner–Intermediate8–12hAny language · an LLM API
A streaming, multi-turn chat application with a designed persona, robust error handling, context management, and a per-conversation cost budget.7 stages · 3 failuresPROJECT 02PRO
RAG Knowledge AssistantIntermediate15–20hPython · pgvector
A full RAG system: document chunking, semantic search, reranked retrieval, cited answers, and hallucination guardrails — with an eval set proving it works.6 stages · 4 failuresPROJECT 03PRO
Customer Support AgentIntermediate–Advanced15–20hTypeScript · MCP
A tool-using agent with structured outputs and guardrails that handles tool failure and escalates with justified reasoning.6 stages · 3 failuresPROJECT 04PRO
Research AgentAdvanced18–25hAny language · an LLM API · a web-search API — the loop is hand-written; frameworks come later, if ever
A full agentic loop written by hand: planning, search & read tools, a complete ReAct trace, iteration/budget bounds with a give-up exit, and a synthesized brief with verified citations — with reliability and cost engineering.6 stages · 3 failures