tech-radarlisted

# Tech Radar Goal: answer **"what should I learn next?"** for a principal software + AI engineer — a Thoughtworks-style radar, not a trends listicle. Every candidate lands on one of four **rings** in its quadrant, and the **Learn ring is the answer**. Every placement must survive: *"why this, why now, and why for someone at this level?"* This skill finds topics; sibling **learn** (`~/.cursor/skills/learn/`) briefs them. Shared library: briefs are this skill's memory; this skill's Learn ring is that skill's input queue. ## The role lens Apply ruthlessly. Principal software + AI engineer needs: - **Decision leverage** — architecture choices, build-vs-buy, platform bets, how you review others' designs. Not "another framework that renders lists". - **AI engineering depth** — agents, serving/inference economics, evals, retrieval, routing, AI-adjacent infra. Signal over demos. One strand of the lens, **not** the scan's default topic. - **Durability** — still matters in 2 years. Hot repo, no production adoption → Watch, not Learn. - **Force-multiplier** — upgrades how the team works, not personal trivia. - **101-feasibility** — correct 101 in roughly a day via the learn loop. Semester-scale → recommend the entry slice. Out of scope: junior fundamentals, certification chasing, single-vendor launch fluff, marketing-only evidence. A scan whose pool is nearly all AI with no AI focus filter is a **skew bug**. Classify every candidate into a Thoughtworks quadrant: - **Techniques**