# CoreWise Academy

> CoreWise Academy is a free library of original guides on working with AI, organized into five layers (Foundations, Prompting & Context, Agents & Automation, Building with AI, Practice) at three depths (Broad, Practitioner, Deep). Edited by Ryan D. Allen.

- [About the editor](https://corewise.academy/about/)
- [How guides get made](https://corewise.academy/how-its-built/)

Every guide is also published as a plain-markdown skill file for agents: swap the guide URL's trailing slash for ".md" (for example https://corewise.academy/guides/brief-the-model.md).

## Foundations

- [Layer page](https://corewise.academy/tracks/foundations/): How AI models actually work: what they can do, where they fail, and how to tell the difference.
- [The new Claude lineup and what it breaks](https://corewise.academy/guides/new-claude-lineup/): Claude's July 2026 lineup is four models: Fable 5, Glasswing-gated Mythos 5, Sonnet 5 at intro pricing, and Opus 4.8, plus the three migration changes that bite.
- [Claude and OpenAI, one prompting playbook](https://corewise.academy/guides/one-prompting-playbook/): OpenAI and Anthropic prompting guides are one playbook when read side by side: lean out the prompt. Where they converge, where they diverge, which habits to drop.
- [Judge whether AI has original ideas](https://corewise.academy/guides/judge-whether-ai-has-original-ideas/): Whether AI can have original ideas is a debate that keeps moving the goalposts. A way to judge it honestly: read the trend line, and see why learning to predict text can build real understanding.

## Prompting & Context

- [Layer page](https://corewise.academy/tracks/prompting/): Getting the right material in front of the model: instructions, examples, and retrieved context, arranged so what matters stands out.
- [Thinking on a budget](https://corewise.academy/guides/thinking-on-a-budget/): Reasoning tokens are billed at the output rate and re-read every turn after. How to compress what a model says without compressing what it knows.
- [Brief the model like a brilliant new hire](https://corewise.academy/guides/brief-the-model/): Claude is a brilliant new hire with no context on your job. Brief it like one: explicit instructions with motivation, examples, XML tags, roles, and context ordering.
- [Stop shouting at the model](https://corewise.academy/guides/stop-shouting-at-the-model/): The newest Claude models are highly responsive to system prompts, so shouting backfires: soften trigger language, migrate deprecated levers, keep the model in bounds.
- [Guardrails for hours-long agent runs](https://corewise.academy/guides/guardrails-for-long-runs/): Guardrails are the support structure that keeps an hours-long agent run honest: an audit instruction, a memory that survives resets, and fresh-eyed verifiers.
- [Sharpen the prompt or brainstorm first](https://corewise.academy/guides/sharpen-the-prompt-or-brainstorm-first/): Two ways to start an AI task: deepen a rough prompt when you know the goal, or brainstorm first when the goal or the tradeoffs are still open. A quick test for which one you are in.
- [Power start sessions with /enhance-prompt](https://corewise.academy/guides/power-start-sessions-with-enhance-prompt/): An enhance-prompt skill turns a rough request into the full prompt the model will actually run, and shows it to you first. Reading that rewrite catches misunderstandings before any work starts.
- [Trim the instructions your model outgrew](https://corewise.academy/guides/trim-the-instructions-your-model-outgrew/): Anthropic removed over 80 percent of Claude Code's system prompt for the Claude 5 models and measured no loss on its coding evaluations. How to give your own instruction files the same trim: goals instead of rule lists, context loaded on demand, and a /doctor audit.

## Agents & Automation

- [Layer page](https://corewise.academy/tracks/agents/): Models that act on their own: tools, MCP, and multi-step workflows that hold up without you watching.
- [Automate the step that slows you down](https://corewise.academy/guides/automate-the-bottleneck/): Automating the bottleneck means finding the constraint that sets your pace and pointing Claude at it: four working rules distilled from Anthropic's own engineers.
- [Capture the model's discipline](https://corewise.academy/guides/rent-the-model-own-the-method/): Models get repriced, capped, and retired; their way of working can be kept. Extract the top model's discipline into skill files, routing tables, and planner-and-worker setups any model can run.
- [Expertise you can install](https://corewise.academy/guides/expertise-you-can-install/): A skill file is career-long judgment packaged as instructions your agent can run. How to adopt someone's method, and why you scan it like untrusted input first.
- [Every new repo starts with your lessons](https://corewise.academy/guides/firmware-not-folklore/): AI Firmware is a boot layer of kernel rules, installable skills, and committed memory that makes every new agent repo start senior instead of relearning old lessons.
- [Give your agent a memory](https://corewise.academy/guides/give-your-agent-a-memory/): A memory store is a workspace-scoped directory your agent reads and writes with normal file tools, carrying preferences and prior mistakes across sessions.
- [Automate a workflow as a Claude routine](https://corewise.academy/guides/automate-a-workflow-as-a-claude-routine/): A routine is a saved instruction Claude runs on its own, on a schedule or an incoming signal. What it replaces, and why an unattended run has to be written tighter than one you watch.
- [Turn repeated fixes into rules](https://corewise.academy/guides/turn-repeated-fixes-into-rules/): When an agent hits the same problem twice, encode the fix as a lint rule, CI check, or steering-file instruction that every future session inherits.
- [Keep a growing knowledge base accurate](https://corewise.academy/guides/keep-a-growing-knowledge-base-accurate/): Wrong agent answers usually trace to the files the agent reads. The four ways a growing knowledge base drifts from reality, and the habits (a router file, read-only audits, scheduled pulls, backtracking) that catch the drift.
- [Loop the agent until the work passes](https://corewise.academy/guides/loop-the-agent-until-the-work-passes/): A rerun loop makes the agent redo its own work until a check passes. Script the repetitive half of a skill, end it with a pass or fail verdict, wrap both in a loop, and keep a human at the checkpoints where errors are expensive.
- [Defend your agent from prompt injection](https://corewise.academy/guides/defend-your-agent-from-prompt-injection/): Anything your agent reads (a web page, a resume, a calendar invite) can carry hidden instructions it will follow. Why the attack has no clean fix, and the five defense layers that shrink what a successful one can do.
- [Split big AI tasks into steps and checks](https://corewise.academy/guides/split-big-ai-tasks-into-steps-and-checks/): One big question in one chat makes the model decide, research, write, and grade itself in a single pass. Map the work instead: parallel research jobs, a checker that did not write the answer, a merge, and your approval before anything expensive.
- [Assume your agent uses every tool it has](https://corewise.academy/guides/assume-your-agent-uses-every-tool-it-has/): An agent sent a discount code to 150,000 people because a to-do item looked like an instruction. A rule in the prompt is a suggestion; a rule built into the tools is a restriction. Scope every key to the least the task needs.
- [Buzz puts AI agents in your team chat](https://corewise.academy/guides/buzz-puts-ai-agents-in-your-team-chat/): Buzz is an open-source team chat from Jack Dorsey's Block where AI agents are members of the channel. What that buys you (swap the model, keep the context), what it can already do, and whether your team should try it yet.
- [Delegate to your agent in stages](https://corewise.academy/guides/delegate-to-your-agent-in-stages/): A new agent should not run your inbox on day one. Give it one job with read-and-draft access only, check its work until your corrections stop, then add the next tool, and let it run unattended only after it has earned that.
- [One chat can run all your other chats](https://corewise.academy/guides/one-chat-can-run-all-your-other-chats/): In ChatGPT, any chat can search every other chat, send work into them, and collect the results. How to find a lost conversation by asking, delegate work between chats, publish a result to a shareable page, and reach it all from your phone.
- [Build an agent that finds your customers](https://corewise.academy/guides/build-an-agent-that-finds-your-customers/): Cody Schneider builds agents that find leads and post content while nobody watches. The method: turn the human process into scripts on a schedule, and call the model only where a judgment is needed. Both of his builds, tool by tool.

## Building with AI

- [Layer page](https://corewise.academy/tracks/building/): Shipping AI features other people can rely on: APIs, retrieval, and evals that prove it works.
- [The design concept does the work](https://corewise.academy/guides/the-design-concept-does-the-work/): The prompt and the reusable skill file behind the about page on this site, with the reason each part earns its place.
- [Build a knowledge base your team can ask](https://corewise.academy/guides/build-a-knowledge-base-your-team-can-ask/): Retrieval augmented generation in plain terms: put the relevant facts in front of the question. How to feed the chat, docs, and code your team already uses into a knowledge base anyone can ask, and why weighting beats volume.
- [Score your agent on known good answers](https://corewise.academy/guides/score-your-agent-on-known-good-answers/): One successful run proves an agent worked once. Collect real examples with answers a person already judged good, grade each run with a script or a judging model, and rerun the set after every change so you know whether it helped.

## Practice

- [Layer page](https://corewise.academy/tracks/practice/): The daily habits: verification, taste, and knowing when not to use the model.
- [Stop hitting your token limit](https://corewise.academy/guides/stop-hitting-your-token-limit/): Your limit is a compute budget: tokens consumed times the model that reads them. Audit where a session spends, trim the context every chat preloads, and send grunt work to cheaper models so the budget lasts the day.
- [Recheck your model choices each release](https://corewise.academy/guides/recheck-your-model-choices-each-release/): When a new model family ships, treat your routing as expired. Re-measure which size and effort give the most score per dollar, spot the size you can skip, and drop the speed modes that do not pay.
- [Why AI makes slop and how to catch it](https://corewise.academy/guides/why-ai-makes-slop-and-how-to-catch-it/): Models got good where the work grades itself, and they aim at the most likely answer, which in design and writing is the average one. The fix: break your quality standard into checkable rules and keep human judgment for taste.
- [What still pays when AI does the work](https://corewise.academy/guides/what-still-pays-when-ai-does-the-work/): When a model can finish the task in minutes, what people will pay you for changes: choosing the task well, doing things others do not know AI can do, feeding your results back into your tools, and proving you can deliver.
- [Rehearse the interview with an AI coach](https://corewise.academy/guides/rehearse-the-interview-with-an-ai-coach/): Nearly everyone gets anxious before a job interview, and practicing out loud is what lowers it. Give an agent the real documents, a skeptical interviewer to play, and your voice, then have it break character and coach you.