Series
Phase 4 gave the study system memory of individual problems — when each one is due for review based on SM-2. Phase 5 asks a different question: zoomed out across all topics, what should I actually be
The first three phases of my study system handled the session loop: generate a problem, grade the solution, log the result. Useful, but with a fundamental gap — there was no memory of what I struggled
Prompt engineering only becomes interesting when you're prompting for structured, specific output that has to be reliable enough to feed downstream systems. A chatbot that gives a slightly different a
Automated evaluation using an LLM sounds like an elegant solution until you understand its failure modes. The model playing the role of a teacher grading work has four well-documented ways to get it w
Most LLM project ideas start from the technology. "What can I build with agents?" or "Let me try a RAG pipeline." That approach produces demos that are interesting for a day and abandoned by the weeke
