Make skills improve after each run
Use failed runs to repair skill descriptions, scripts, and checks. Test each change before keeping it, with Harness Firmware as a working example.
5 min Nº 054 · September MMXXVIObservatory open
free guides
Stars · · Links ·
Vol. I · MMXXVI
Open to all
↓ scroll
5 Layers
Curriculum chart · Broad → Practitioner → DeepFoundations
Constellation · THE LENSHow AI models actually work: what they can do, where they fail, and how to tell the difference.
BROAD ★★ 2 guides PRACTITIONER ★ 1 guide DEEP none yet
II Prompting & Context
Constellation · THE LOOMGetting the right material in front of the model: instructions, examples, and retrieved context, arranged so what matters stands out.
BROAD ★ 1 guide PRACTITIONER ★★★★★ 6 guides DEEP ★ 1 guide
III Agents & Automation
Constellation · THE COURIERModels that act on their own: tools, MCP, and multi-step workflows that hold up without you watching.
BROAD ★★★★★ 12 guides PRACTITIONER ★★★★★ 13 guides DEEP ★ 1 guide
IV Building with AI
Constellation · THE FORGEShipping AI features other people can rely on: APIs, retrieval, and evals that prove it works.
BROAD ★★ 2 guides PRACTITIONER ★★ 2 guides DEEP none yet
V Practice
Constellation · THE METRONOMEThe daily habits: verification, taste, and knowing when not to use the model.
BROAD ★★★★ 4 guides PRACTITIONER ★★ 2 guides DEEP none yet
Latest guides
Newest firstCompare AI agents on your own work
Compare agents on one repeatable task, check the tools each can use, and keep your skills usable when you switch.
5 min Nº 053 · September MMXXVILearn a work skill with AI
Choose a task you need to do, learn from checked sources, then test your understanding by doing the work and explaining your decisions.
5 min Nº 052 · September MMXXVIThe catalogue at a glance
Working with AI · five layers · three depths| Layer | Constellation | Guides | Topics |
|---|---|---|---|
| Foundations | THE LENS | 3 | model behaviormodel choicewriting prompts |
| Prompting & Context | THE LOOM | 8 | writing promptsplanningagent safety |
| Agents & Automation | THE COURIER | 26 | automationdelegationskills |
| Building with AI | THE FORGE | 4 | teamsdesignknowledge bases |
| Practice | THE METRONOME | 6 | careercost controlverification |
| Browse the whole catalogue 47 guides · 18 topics → | |||
Quotes from the guides
“The rules were written for a weaker model.”
Trim the instructions your model outgrew
“Value is what they get divided by what it costs them.”
What still pays when AI does the work
“Slop is what a page looks like when nothing decided it.”
The design concept does the work
FAQ · working with the Academy
What is CoreWise Academy?
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 47 published guides, about 311 minutes of reading in total.
How much does it cost?
Nothing: $0, no account, no signup, no newsletter gate. Admission is 100% free and every guide is open to read in full.
Where should I start?
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
Start anywhere, anytime
No accounts, no fees, no forms. Pick a layer and start reading.