Observatory open
free guides
Stars · · Links ·
Vol. I · MMXXVI
Open to all
↓ scroll
How AI models actually work: what they can do, where they fail, and how to tell the difference.
Getting the right material in front of the model: instructions, examples, and retrieved context, arranged so what matters stands out.
Models that act on their own: tools, MCP, and multi-step workflows that hold up without you watching.
Shipping AI features other people can rely on: APIs, retrieval, and evals that prove it works.
The daily habits: verification, taste, and knowing when not to use the model.
Claude Design asks the questions a designer would, keeps your colors and fonts in a design system your whole team reuses, and fixes whatever a teammate circles in a comment. When it beats a plain chat, and the path from brand system to finished asset.
7 min Nº 049 · August MMXXVIA language model reaches for the most familiar answer, and the better it sounds the less you check. Four staged prompts force the opposite: break the problem into parts, sort facts from assumptions, recombine the checked parts, and design cheap tests. You keep the judgment.
6 min Nº 048 · August MMXXVITheo let Claude Code save memories on its own, then audited them: 45 files, written three times more often than read, most never opened again. How to run the same audit on your machine, the three ways saved memories rot, the ladder that finds a better home for each lesson, and what a harness built to pass the audit looks like.
8 min Nº 047 · August MMXXVI| Layer | Constellation | Guides | Topics |
|---|---|---|---|
| Foundations | THE LENS | 3 | model behaviormodel choicewriting prompts |
| Prompting & Context | THE LOOM | 8 | writing promptsplanningagent safety |
| Agents & Automation | THE COURIER | 22 | automationdelegationClaude Code |
| Building with AI | THE FORGE | 4 | teamsdesignknowledge bases |
| Practice | THE METRONOME | 5 | careercost controlClaude Code |
| Browse the whole catalogue 42 guides · 18 topics → | |||
“If it can, one day it will.”
Assume your agent uses every tool it has
“The familiar answer wins by default.”
Take a problem apart before AI solves it
“A memory earns its keep when it gets read.”
Audit what your agent saved to memory
CoreWise Academy is a free library of original guides on working with AI. Each guide distills real sources (lectures, official docs, field notes) into a short read with objectives, an exercise, and a self-check. There are 42 published guides, about 284 minutes of reading in total.
Nothing: $0, no account, no signup, no newsletter gate. Admission is 100% free and every guide is open to read in full.
Start with the Foundations layer if you are new to working with AI, or jump straight to the layer that matches your problem: Prompting & Context, Agents & Automation, Building with AI, or Practice. Levels run Broad, then Practitioner, then Deep, and prerequisites are marked on every guide.
Free · no signup
No accounts, no fees, no forms. Pick a layer and start reading.