“Unusual was obliged to invent many of the magic he did, working from basic rules and half-remembered tales from outdated books.”
— Susanna Clarke, Jonathan Unusual & Mr Norrell
Fairy tales, myths, and fantasy fiction are filled with magic spells. You say “abracadabra” and one thing profound occurs.1 Say “open sesame” and the door swings open.
It seems that that is additionally a helpful metaphor for what occurs with massive language fashions.
I first acquired this concept from David Griffiths’s O’Reilly course on utilizing AI to spice up your productiveness. He gave a easy instance. You possibly can inform ChatGPT “Set up my activity checklist utilizing the Eisenhower four-sided field.” And it simply is aware of what to do, even should you your self know nothing about Normal Dwight D. Eisenhower’s method to resolution making. David then suggests his college students as an alternative strive “Set up my activity checklist utilizing Getting Issues Completed,” or simply “Use GTD.” Every of these phrases is shorthand for techniques of thought, practices, and conventions that the mannequin has discovered from human tradition.
These are magic phrases. They’re magic not as a result of they do one thing unworldly and sudden however as a result of they’ve the ability to summon patterns which were encoded within the mannequin. The phrases act as keys, unlocking context and even complete workflows.
All of us use magic phrases in our prompts. We are saying one thing like “Replace my resume” or “Draft a Substack submit” with out pondering how a lot detailed prompting we’d should do to create that output if the LLM didn’t already know the magic phrase.
Each discipline has a specialised language whose phrases are identified solely to its initiates. We will be fanciful and faux they’re magic spells, however the actuality is that every of them is known as a form of fuzzy perform name to an LLM, bringing in a physique of context and unlocking a set of behaviors and capabilities. Once we ask an LLM to put in writing a program in Javascript slightly than Python, we’re utilizing one among these fuzzy perform calls. Once we ask for output as an .md file, we’re doing the identical. Not like a perform name in a conventional programming language, it doesn’t at all times return the identical end result, which is why builders have a possibility to boost the magic.
From Prompts to Functions
The subsequent gentle bulb went off for me in a dialog with Claire Vo, the creator of an AI software referred to as ChatPRD. Claire spent years as a product supervisor, and as quickly as ChatGPT grew to become accessible, started utilizing it to assist her write product requirement paperwork or PRDs. Each product supervisor is aware of what a PRD is. When Claire prompted ChatGPT to “write a PRD,” it didn’t want an extended preamble. That one acronym carried many years {of professional} follow. However Claire went additional. She refined her prompts, improved them, and taught ChatGPT the way to suppose like her. Over time, she had skilled a system, not on the mannequin stage, however on the stage of context and workflow.
Subsequent, Claire turned her workflow right into a product. That product is a software program interface that wraps up quite a lot of associated magic phrases right into a helpful bundle. It controls entry to her custom-made magic spell, so to talk. Claire added detailed prompts, integrations with different instruments, entry management, and an entire lot of conventional programming in a next-generation software that makes use of a mixture of conventional software program code and “magical” fuzzy perform calls to an LLM. ChatPRD even interviews customers to be taught extra about their objectives, customizing the applying for every group and use case.
Claire’s quickstart information to ChatPRD is a superb instance of what a magic-word (fuzzy perform name) software appears like.
You too can see how magic phrases are crafted into magic spells and the way these spells are even a part of the structure of functions like Claude Code by means of the explorations of builders like Jesse Vincent and Simon Willison.
In “How I’m Utilizing Coding Brokers in September, 2025,” Jesse first describes how his claude.md file gives a base immediate that “encodes a bunch of course of documentation and guidelines that do a fairly good job conserving Claude on observe.” After which his workflow calls on a bunch of specialised prompts he has created (i.e., “spells” that give clearer and extra customized which means to particular magic phrases) like “brainstorm,” “plan,” “architect,” “implement,” “debug,” and so forth. Observe how inside these prompts, he might use extra magic phrases like DRY, YAGNI, and TDD, which confer with particular programming methodologies. For instance, right here’s his planning immediate (boldface mine):
Nice. I would like your assist to put in writing out a complete implementation plan.
Assume that the engineer has zero context for our codebase and questionablestyle. doc every part they should know. which recordsdata to the touch for everyactivity, code, testing, docs they may must verify. the way to check it.givethem the entire plan as bite-sized duties. DRY. YAGNI. TDD. frequent commits.
Assume they're a talented developer, however know virtually nothing about ourtoolset or downside area. assume they do not know good check designverynicely.
please write out this plan, in full element, into docs/plans/
However Jesse didn’t cease there. He constructed a mission referred to as Superpowers, which makes use of Claude’s just lately introduced plug-in structure to “give Claude Code superpowers with a complete expertise library of confirmed strategies, patterns, and instruments.” Asserting the mission, he wrote:
Abilities are what give your brokers Superpowers. The primary time they actually popped up on my radar was a couple of weeks in the past when Anthropic rolled out improved Workplace doc creation. When the characteristic rolled out, I went poking round a bit – I requested Claude to inform me all about its new expertise. And it was solely too pleased to dish…. [Be sure to follow this link! – TOR]
One of many first expertise I taught Superpowers was How you can create expertise. That has meant that after I needed to do one thing like add git worktree workflows to Superpowers, it was a matter of describing how I needed the workflows to go…after which Claude put the items collectively and added a pair notes to the prevailing expertise that wanted to clue future-Claude into utilizing worktrees.
After studying Jesse’s submit, Simon Willison did a bit extra digging into the unique doc dealing with expertise that Claude had introduced and that had sparked Jesse’s brainstorm. He famous:
Abilities are extra than simply prompts although: the repository additionally contains dozens of pre-written Python scripts for performing widespread operations.
pdf/scripts/fill_fillable_fields.py for instance is a customized CLI software that makes use of pypdf to search out after which fill in a bunch of PDF type fields, specified as JSON, then render out the ensuing mixed PDF.
This can be a actually subtle set of instruments for doc manipulation, and I really like that Anthropic have made these seen—presumably intentionally—to customers of Claude who know the way to ask for them.
You possibly can see what’s taking place right here. Magic phrases are being enhanced and given a extra rigorous definition, and new ones are being added to what, in fantasy tales, they name a “grimoire,” or guide of spells. Microsoft calls such spells “metacognitive recipes,” an exquisite time period that ought to get broadly adopted, although on this article I’m going to stay with my fanciful analogy to magic.
At O’Reilly, we’re working with a really completely different set of magic phrases. For instance, we’re constructing a system for exactly focused competency-based studying, by means of which our clients can skip what they already know, grasp what they want, and show what they’ve discovered. It additionally offers company studying system managers the flexibility to assign studying objectives and to measure the ROI on their funding.
It seems that there are dozens of studying frameworks (and that’s itself a magic phrase). Within the design of our personal specialised studying framework, we’re invoking Bloom’s taxonomy, SFIA, and the Dreyfus Mannequin of Talent Acquisition. However when a buyer says, “We love your method, however we use LTEM,” we are able to invoke that framework as an alternative. Each company buyer additionally has its personal specialised tech stack. So we’re exploring the way to use magic phrases to let no matter we construct adapt dynamically not solely to our finish customers’ studying wants however to the tech stack and to the training framework that already exists at every firm.
That will be a nightmare if we needed to help dozens of various studying frameworks utilizing conventional processes. However the issue appears way more tractable if we’re in a position to invoke the suitable magic phrases. That’s what I imply after I say that magic phrases are an important constructing block within the subsequent technology of software programming.
The Structure of Magic
Right here’s the essential factor: Magic isn’t arbitrary. In each mythic custom, it has construction, self-discipline, and value. The magician’s energy is dependent upon figuring out the suitable phrases, pronounced in the suitable manner, with the suitable intent.
The identical is true for AI techniques. The effectiveness of our magic phrases is dependent upon context, grounding, and suggestions loops that give the mannequin dependable details about the world.
That’s why I discover the rising ecosystem of AI functions so fascinating. It’s about offering the suitable context to the mannequin. It’s about defining vocabularies, workflows, and roles that expose and make sense of the mannequin’s talents. It’s about turning implicit cultural information into specific techniques of interplay.
We’re solely initially. However simply as early programmers discovered to construct structured software program with out spelling out actual machine directions, in the present day’s AI practitioners are studying to construct structured reasoning techniques out of fuzzy language patterns.
Magic phrases aren’t only a poetic picture. They’re the syntax of a brand new form of computing. As individuals turn out to be extra comfy with LLMs, they are going to move across the magic phrases they’ve discovered as energy consumer tips. In the meantime, builders will wrap extra superior capabilities round current magic phrases and even perhaps train the fashions new ones that haven’t but had the time to accrete adequate which means by means of large utilization within the coaching set. Every software can be constructed round a shared vocabulary that encodes its area information. Again in 2022, Mike Loukides referred to as these techniques “formal casual languages.” That’s, they’re spoken in human language, however do higher if you apply a little bit of rigor.
And at the very least for the foreseeable future, builders will write “shims” between the magic phrases that management the LLMs and the extra conventional programming instruments and strategies that interface with current techniques, a lot as Claire did with ChatPRD. However finally we’ll see true AI to AI communication.
Magic phrases and the spells constructed round them are solely the start. As soon as individuals begin utilizing them in widespread, they turn out to be protocols. They outline how people and AI techniques cooperate, and the way AI techniques cooperate with one another.
We will already see this taking place. Frameworks like LangChain or the Mannequin Context Protocol (MCP) formalize how context and instruments are shared. Groups construct agentic workflows that depend upon a standard vocabulary of intent. What’s an MCP server, in any case, however a mapping of a fuzzy perform name right into a set of predictable instruments and providers accessible at a given endpoint?
In different phrases, what was as soon as a set of magic spells is changing into infrastructure. When sufficient individuals use the identical magic phrases, they cease being magic and begin being requirements—the constructing blocks for the subsequent technology of software program.
We will already see this development with MCP. There are three distinct sorts of MCP servers. Some, like Playwright MCP, are designed to make it simpler for AIs to interface with functions initially designed for interactive human use. Others, just like the GitHub MCP Server, are designed to make it simpler for AIs to interface with current APIs, that’s, with interfaces initially designed to be referred to as by conventional applications. However some are designed as a frontend for a real AI-to-AI dialog. Different protocols, like A2A, are already optimized for this third use case.
However in every case, an MCP server is known as a dictionary (or in magic phrases, a spellbook) that explains the magic phrases that it understands and the way to invoke them. As Jesse Vincent put it to me after studying a draft of this piece:
The half that feels essentially the most like magic spells is the half that almost all MCP authors do extremely poorly. Every software has a “description” discipline that tells the LLM how you employ the software. That description discipline is learn and internalized by the LLM and adjustments the way it behaves. Anthropic are significantly good at software descriptions and most all people else, in my expertise, is…much less good.
In some ways, publishing the prompts, software descriptions, context, and expertise that add performance to LLMs could also be a extra essential frontier of open supply AI than open weights. It’s essential that we deal with our enhancements to magic phrases not as proprietary secrets and techniques however as shared cultural artifacts. The extra open and participatory our vocabularies are, the extra inclusive and artistic the ensuing ecosystem can be.
Footnotes
- Whereas usually related in the present day with stage magic and cartoons, this magic phrase was apparently used from Roman instances as a therapeutic spell. One proposed etymology means that it comes from the Aramaic for “I create as I converse.”