watts.it.com // daily AI micro-learning

// the library · browse by pillar

The curriculum

10 modules · view as constellation →

01 Prompting & context Directing the model; what you feed it

2026·06·08 Brief the AI like a brilliant new hire: writing clear, direct instructions 3 min 2026·06·08 Context engineering: curate the few high-signal tokens, don't dump everything in 4 min 2026·06·08 Beyond the prompt recipe: iterative collaboration, not a better template 4 min

02 Memory & recall What persists across turns and sessions; retrieval

2026·06·08 Your context window is working memory, not a hard drive 4 min 2026·06·08 RAG without the jargon: how AI can answer from your documents instead of guessing 4 min

03 Tools & connectors Extending the model: integrations, connectors, setup

2026·06·08 Connectors vs. file upload: when to plug into your live data and when to just drag a file in 4 min

04 Workflows & iteration Multi-step work, orchestration, refining to a result

2026·06·08 The generate-critique-refine loop: stop accepting first drafts 4 min 2026·06·08 Plan first, execute second: the 80/20 rule for letting AI tackle big tasks 4 min

05 Judgment & limits Knowing when not to; failure modes, over-reliance

2026·06·08 Why it makes things up: hallucination is a feature of the scoring, not a glitch you can prompt away 4 min

06 The landscape Reading model developments; signal from hype

2026·06·08 The jagged frontier: why AI aces one task and bombs the next one that looks identical 4 min

visitor@watts:~$

WATTS(1)                 User Commands                 WATTS(1)

NAME
    watts — daily AI micro-learning, human-reviewed

KEYS
    j / k      next / previous module
    ~          drop into the shell
    ?          this manual
    q, Esc     close

SHELL BUILTINS
    help, ls, ls <pillar>, open <module>, latest,
    whoami, crt, play, sudo publish, clear, exit

COLOPHON
    drafted by AI · reviewed and signed off by a human editor