Watts on today? · human-reviewed
The reflexive question: Can AI do this?
A daily micro-lesson on using AI for real work.
// latest module
Brief the AI like a brilliant new hire: writing clear, direct instructions
This is the one prompting habit worth fixing before any other: saying exactly what you mean, in plain words, with no room for a second reading. Why now — Anthropic's living prompting guide, current through Claude Fable…
// the curriculum · six pillars
browse the library → 01
Prompting & context
Directing the model; what you feed it
02
Memory & recall
What persists across turns and sessions; retrieval
03
Tools & connectors
Extending the model: integrations, connectors, setup
04
Workflows & iteration
Multi-step work, orchestration, refining to a result
05
Judgment & limits
Knowing when not to; failure modes, over-reliance
06
The landscape
Reading model developments; signal from hype
// the trail · published & reviewed
2026·06·08 Brief the AI like a brilliant new hire: writing clear, direct instructions latest Prompting & context
2026·06·08 Connectors vs. file upload: when to plug into your live data and when to just drag a file in Tools & connectors
2026·06·08 Context engineering: curate the few high-signal tokens, don't dump everything in Prompting & context
2026·06·08 Beyond the prompt recipe: iterative collaboration, not a better template Prompting & context
↓ 10 modules in the archive · browse by pillar or by date