01
What Llms Actually Do
14 min read
drafted
02
Prompt Anatomy: System, Developer, User, and Tool Turns
13 min read
junior
drafted
03
Core Prompting Techniques: Few-Shot, Role, and Output Formatting
13 min read
mid
drafted
04
Chain-of-Thought and Reasoning Effort: What Actually Helps and What's Theater
15 min read
mid
drafted
05
Structured Output: Constrained Decoding and Why It Beats Free-Form Parsing
13 min read
mid
drafted
06
The Limits of Prompting: Why Some Failures Aren't Prompt Problems
12 min read
senior
drafted
07
Context Engineering as a Discipline: The Context Window as a Budget
14 min read
senior
drafted
08
Context Failure Modes: Poisoning, Distraction, and Confusion
14 min read
senior
drafted
09
Retrieval: RAG vs. Long Context, and When Each Wins
9 min read
senior
drafted
10
Context Compaction and Sub-Agent Handoff for Long-Horizon Tasks
17 min read
staff
drafted
11
Memory Architecture: Types, Persistence, and Staleness
22 min read
staff
drafted