Highlight
Saved.
My Notes
0 highlights on this page
No highlights yet. Select any text and choose a color to begin building your notes.
Mindvalley AI Mastery  ·  Lesson 6  ·  Lesson Notes

Onboard Your First AI Team Member

GPTs and Projects  ·  Noelle Russell
01   Start Here

Last lesson you wrote the instructions. This one you hand them to someone.

Noelle Russell returns to pick up the other side of context engineering. Last session was about getting clear: the role, the task, the examples, the constraints. Useful, and also a little abstract, because the words sat in a document and nothing happened to them. This session is where those words go to work.

She frames her own instinct honestly. Her temperament is go, ship it, build it, get it out the door. What her career taught her is that design comes first and building comes second, and that the journey is shorter that way, though it is still a journey. So the order here is deliberate. You are not learning a platform today. You are learning what to do with clarity once you have it.

Two demonstrations carry the lesson. First a pre-built system where six agents already exist and your only job is to give them context, which is the fastest way to feel what a working AI team is actually like. Then Claude, where nothing is pre-built and you construct the thing yourself. She calls them a walking tool and a running tool, and the order matters as much as the tools do.

Audio Summary: Onboard Your First AI Team Member

Listen to an audio summary of this session here.

0:00 0:00
What you will walk away with

A felt sense of what six context engineered agents can do for you in an afternoon, and then the more durable skill underneath it: writing a full persona document, understanding that guardrails arrive in layers you did not all choose, and knowing where the real leverage sits once the big platforms catch up.

Where lesson 5 left you
Crawling

Writing your role, task, examples, and constraints by hand, into a document, one careful prompt at a time.

Where this lesson takes you
Walking, then running

Those same words dropped into a harness that holds them, and then into a system where you build the harness too.

02   Design First, Build Second

The model is the processor. The context is the working memory.

Noelle reaches for hardware to explain what a context window actually is. A computer has a central processing unit, the part that does the thinking, and it has random access memory, the working space the processor uses while it does that thinking. Neither is useful without the other.

In this analogy the language model is the processor. It can reason, but on its own it knows nothing about your situation. The context window is the working memory: the space where you tell that processor what it has access to, who it is being right now, and what finished work looks like in your world.

This reframes a complaint you have probably had. When a model gives you something flat, the processor did not fail. The working memory was empty. You handed a capable thinker an empty desk and asked for a finished report.

The three things you owe a model, every time

Who it is being. The role it plays in this particular conversation.

What the work is, and who it serves. The task, and the person on the other end of it.

What good looks like. Examples. And a useful permission from Noelle here: the examples do not have to be real. You are allowed to write the example you wish existed. The model needs a target, not a history.

A million tokens of space, and most of us leave it blank.

The rest of this lesson is about what happens when you stop leaving it blank, and where you put all that context once you have written it down.

03   What You Pay With

Before you add another system, look at the ones you already have.

Noelle asks the room a question before she demonstrates anything. If you are using an AI system and you are not paying for it, what are you paying with? Someone says time. Her answer is blunter. You pay with the inner workings of your mind. When you talk to a model you do not pay for, there is no barrier and no agreed boundary that says this material is yours and no one else may use it.

Her conclusion is not that free tools are wrong. It is that the work you are moving into deserves a real relationship with the vendor. A paid, transactional relationship is one you can hold someone to. That framing sits underneath everything else in this session, because you are about to connect a system to your email and your calendar.

Then comes the discipline she says matters more than any single tool. Keep an inventory of every AI system you buy. Not a list of names and links, which decays into wallpaper. An inventory with a little metadata attached: who you were when you bought it, what problem you were solving, and whether it is still solving that problem. She keeps hers as a small app rather than a spreadsheet. She has somewhere between fifty and seventy of these subscriptions, and says the discipline is the biggest gift she can offer you, because the alternative is death by a thousand small charges. Large organizations lose track the same way, at a scale where nobody can name what is running.

Type straight into the table. Nothing is saved or sent, it is here to think in.

The system
The problem I bought it to solve
Still solving it? 1 to 10

Three rows is enough to feel it. The one you had forgotten about is usually the one that teaches you something.

04   Six Teammates

A harness that already exists, waiting for your words.

The first demonstration uses Marblism, a platform that provisions six agents for you in a single setup pass. Noelle is careful about why she is showing it, and it is worth repeating, because it is the actual lesson. The harness is built. The context engineering is not. That is still yours to do, and it is the only part that makes any of them useful.

The onboarding asks for your role and your website, then reads the site and infers your company, what you do, and who you do it for. Noelle points out the uncomfortable implication immediately. If your website is vague, everything downstream inherits that vagueness. The system is only reflecting the clarity you already published.

Tap any teammate to open what it needs from you and the boundary it cannot cross.

The point is not the six agents. It is that a stranger's words are running your inbox until you replace them with your own.

Noelle's own framing of the real prize: once the commoditized work is handled, what would you build? Do not spend your time building a custom agent that reads your inbox. That problem is solved. Spend it on the thing only you can see.

05   Guardrails Come in Layers

Some of the rules are yours. Some were decided before you arrived.

This is the quiet, important correction in the session. When you write a persona document you are setting constraints, and it is easy to assume those are the only constraints in play. They are not. The platform has its own, written by people you will never meet, and they are not up for negotiation. Eva archiving but never deleting is the clean example. Noelle did not choose that. She discovered it, and knowing it is part of the job.

The lane an agent may act within Two bands form a channel. The upper gold band is the guardrails you write. The lower plum band is the constraints the platform imposes. Between them runs the space where the agent may actually operate. THE GUARDRAILS YOU WRITE role, task, examples, constraints, tone, what it must never do THE GUARDRAILS THE PLATFORM SET decided before you signed up, and not yours to move WHERE THE AGENT MAY ACTUALLY ACT Eva drafts. Eva archives. Eva cannot delete, and cannot send as you.
Your rules narrow the lane from above. The platform's rules narrow it from below. What is left in between is the only room your agent has, and you should be able to describe it out loud.
Read the connection screen

Every time you connect a system to your email, your calendar, or your social accounts, a permission screen describes exactly what access you are granting. Noelle's name for what most of us do with it is YOLO mode: click, click, click, in. Her ask is modest. Read it once. Or paste it into NotebookLM and have it read to you. Then decide.

The real superpower is between them

Plenty of tools take meeting notes. What changes here is that the note taker can reach the social media agent, the legal agent, and the sales agent. Ask Eva to tell Sunny to build a campaign from what was just decided in that meeting, and it happens. The value is in the connections, not in any one agent.

06   The Persona Document

RTEC was the sketch. This is the finished thing.

Last lesson gave you RTEC: role, task, examples, constraints. Noelle is direct about what that was. A mini version. A place to start. What it grows into is a full document, one per agent, and she calls it a persona document or a guardrails guide.

She shares three of her own, for her executive assistant, her blogger, and her social media associate, and then says the thing that keeps this honest: do not use mine. These are my words and my rules. Build your own. Hand mine to Claude as a shape to follow if that helps, and then write yours.

Our job is not to write code. Our job is to write words that tell a machine how to operate.

Her framing for what the document actually is: it should look a great deal like a job description. That is the whole trick. You already know how to describe a role to a person you are hiring, including the parts about judgment and boundaries that never make it into a task list. You are writing that, for a machine.

A persona document, section by section
ROLE DEFINITION Who this agent is. Not a job title alone, the specialty. Example: not "a writer" but "a writer of warm, benefit led wellness copy." RESPONSIBILITIES The work it owns, listed plainly. What lands on its desk. WHAT IT OPTIMIZES FOR The thing to maximize when two good options compete. Speed or accuracy. Reach or precision. Warmth or brevity. Choose. WHAT IT MUST NOT DO The explicit no list. Be concrete. This is where most documents are too polite. OPERATING PRINCIPLES How it makes decisions when your instructions run out. This is the section that separates a persona document from a prompt. AUTHORITY What it may decide alone, what it drafts for your review, and what it must never touch without you. RESPONSIBLE AI FRAMING Your security and accuracy policy for this agent. What sources it may use. What it does when it is not sure. What it must disclose about how it reached an answer. PRACTICAL USE CASES The real situations you expect it to handle, in your own words. WRITING STYLE GUARDRAILS Voice, length, formatting, words to use, words to avoid, and one example of good and one example of bad.
Copied

Noelle's caution is worth carrying with you. Not every conversation needs this level of control, and you should not overthink it or feel behind for not having one yet. The point of AI Mastery is that you are leaving vending machine behavior behind. You are training a model to give you results worth having, and this is how that is done.

07   From Harness to Your Own Build

The walking tool showed you what is possible. Now you build it.

The second half moves to Claude, and Noelle's framing of the relationship between the two is the clearest line in the session. Claude is the engine. The pre-built platform is one of the cars. Seeing the car first tells you what engines can do. Then you go and build your own.

Here the vocabulary shifts, and it is worth getting straight, because these three words get used loosely everywhere else.

The thing you want done
Task

A job to be performed, once or on a schedule. Noelle runs a daily brief that reads her calendar and inbox, gathers stories she can use on stage, and cites every source so she can follow the trail.

How you teach it
Skill

The instructions that let the model perform that task properly. Skills are the mechanism by which you train the model. There is a skill creator built in, which interviews you and writes the skill from your answers.

Several skills, one button
Plugin

A collection of skills bundled together, so one action triggers six. Noelle runs an internal communications plugin covering status reports and newsletters.

How it reaches the world
Connector

Access to the systems where your work actually lives. Hers reach her project tracker, her design tools, her code, her mail, and her domain registrar, so a skill can go and check whether a domain is free and then register it.

It is not having the most powerful tool. It is having the most connected one.

She is unusually honest about where people actually get stuck, and it is not the part the marketing shows you. Ask Claude to rebuild one of those six agents and it will tell you plainly what you would need: a telephony service, a voice provider, a lead database. Connectivity is the glue, and most people never get to that part. It is the hard bit, and pretending otherwise does you no favours.

A standard operating procedure that actually operates

Noelle's rule in her own company: the second time you do something, it becomes a standard operating procedure. What is different now is that the procedure no longer waits for a person to notice the trigger and act. Written as a skill, it says when this condition exists, do this thing, and then it does it. The document became the doing.

08   Change How You Work

The system worked. She was the one who had not changed.

This is the most useful story in the lesson, and it is a story about failure that turned out not to be one.

Noelle asked Claude to organize her downloads folder every morning. It did. She opened it, found something that looked like a five year old's bedroom, nothing alphabetical, nothing sorted by size, and concluded the thing was broken.

Then she remembered Amazon. When their fulfillment centers went fully robotic, the robots reorganized the shelves by how often items were retrieved rather than by any human category. Toothpaste beside batteries beside bananas. To a person walking in, chaos. To the system, a thirty eight percent efficiency gain. The shelves were not disordered. They were ordered for a different reader.

Her downloads folder was the same. The organization was real, it just was not built for scrolling. And she had kept scrolling, because that is what she had always done. The old habit arrived before the new capability could be used.

It did work. I just had not changed the way I work to match it.

Now she does not scroll. She asks. That presentation from last week, the one about such and such, where is it. And it comes back instantly. The model became her index rather than her filing clerk. Watch for this in yourself over the next few weeks. When a system feels like it made things harder, ask whether the tool failed or whether an old routine is still running underneath it.

09   Where Your Brain Lives

Point at where the knowledge already is. Do not drag it into one room.

A question came up that this program has been circling for weeks: where exactly do I build my brain? Noelle's answer has two halves, and both are true at once, which is why it is worth sitting with.

Tap either heading to switch between the two ways of holding your knowledge.

Knowledge copied into a single store Six sources around the edge, each with an arrow pointing inward to one central box labeled one place. ONE PLACE everything, copied in Google Drive SharePoint Your websites Podcasts Image library Documents
Everything moves inward. Simple to picture, and it is never finished, because the sources keep producing while you copy.

Start here when you are new. One contained set of material, a single place, so you can build an end to end system without drowning. Noelle calls this a data set: one piece of the very large puzzle that is you.

A model pointed at knowledge where it already lives A central node labeled your model, with arrows reaching outward to six sources that stay where they are. YOUR MODEL knows where Google Drive SharePoint Your websites Podcasts Image library Documents
Nothing moves. The material stays where it was made, and the model holds the map. Add a source and the brain grows without a migration.

This is where it goes. Noelle's own knowledge is spread across drives, sites, and podcasts she does not even own, and she treats it as a mesh rather than a location. Large organizations learned the same lesson the expensive way, which is why the industry now builds data fabrics instead of central copies. She has worked with a client running two thousand sources. Nobody was going to move those.

The resolution between the two is sequencing, not contradiction. Begin contained so you can finish something. Grow toward the mesh as your material outgrows any single room. What matters either way is that you can name the scope of your brain and say where each piece of it lives. She keeps an actual map of hers.

NotebookLM as the mapping tool

Her practical route: load your sources into NotebookLM, which will ingest drives, sites, documents, images, and audio, and then generate a mind map of what you have. It will also produce a podcast, a slide deck, a video overview, flashcards, quizzes, and reports from the same material.

The move worth stealing is how she divides it. One notebook per campaign, per project, per class. The mind map then shows one line of thinking clearly instead of showing everything at once and teaching you nothing.

10   Document It

Nothing you build should be a black box, least of all to you.

Noelle learned this one by living it. After roughly five years and seventeen hundred days of prompting inside one platform, she moved most of her work to another. Everything she had taught the first system was gone. What saved the migration was documentation she had written along the way, not memory.

Her hack is small enough to adopt today. When you finish building something, ask the model to document it for you, so that you could rebuild it from the description alone. It costs one sentence.

Ask for the rebuild document
We just built this together. Please document it so that I could rebuild it from scratch if I lost access to everything tomorrow. Include: - what this system does, in plain language - every source, account, and connection it depends on - the instructions and guardrails currently governing it - the order I would need to rebuild the pieces in - an audit trail of how you reached the results in this session, including which sources you actually used and why Flag anything you relied on that I should look at more closely.
Copied

You get two things from that, and the second is the one people miss. The obvious return is disaster recovery: a rebuild path when an account is lost or a platform changes. The less obvious return is the audit trail. Read how the system actually reached its answer and you may find sourcing that does not sit right with you. Noelle's example is direct. It may be able to get past a paywall. That does not mean you want it to.

This is also, she notes, how you keep systems safe as they get faster. The temptation as speed increases is to stop checking and assume it is fine. Making a system explain its own reasoning is the discipline that holds against that drift.

And one more thing about that document

She points out that this documentation is your intellectual property. The words that make your agents behave like yours are an asset. Store them accordingly.

11   Building in the AI Gap

Everything you build will be commoditized. Build it anyway.

Someone asks the question everyone building on top of a platform eventually asks. The pre-built system is adding the feature I was going to sell. What happens to me? Noelle's answer reframes the whole enterprise, and it is the most strategically useful minute of the session.

There is always a distance between what a large platform has shipped and what a particular customer actually needs. She calls that distance the AI gap. Big companies move in quarters and years. You move in days. The gap is not a risk to your business. It is your business.

The AI gap over time A rising smooth line shows what customers need. A lower stepped line shows what large platforms ship. The shaded area between them is the gap where independent builders work. A point where you ship something is later reached by a platform step, and the gap reopens above it. YOU BUILD IT NOW A FEATURE THE GAP where you work WHAT YOUR CUSTOMERS NEED WHAT THE BIG PLATFORMS SHIP time
The platform reaches, eventually, exactly where you were standing. By then the line above has moved again, and the gap has reopened somewhere new. That is the pattern, not the problem.
Microsoft might deliver this next quarter, or next year. I can deliver it for you right now.

Noelle is unsentimental about her own work because of this. She builds, it serves for a while, a large platform absorbs it, and she asks what the next thing is. She credits the habit to something she learned at Amazon: you innovate on behalf of your customers, continuously. And she adds the part that makes it sustainable rather than exhausting. Solve one problem for someone and new problems appear, problems they could not have had until the first one was gone.

The same logic if you are not building a business

She keeps checking this in the room, because roughly half the people there are growing a career rather than a company. The gap works identically. Before she owned a business her question was how do I solve my customer's problem, where the customer happened to be her employer. Employee or founder, you are looking at the distance between what exists and what is needed, and closing it faster than a large organization can.

How she learns from a product she did not build

Her advice for a first win is to stop trying to invent something nobody has built. Find people doing it well, become a customer, and study the craft. She was not a customer of that six agent platform at first. She was looking for something she could hand to other people, and then noticed the intentionality behind it and stayed.

Then the part most people would never think to do: interrogate the agents. Ask where these leads came from. Ask what you are not allowed to do. Ask how you were trained, and why that rule exists. She says she has collected more understanding of ethics, policy, and governance by asking models those questions than by almost anything else. A production system in the wild is a playground for anyone willing to ask.

12   Check Yourself

Nine cards. Answer before you turn them over.

The quick reference below is there to be read. These are here to be retrieved, which is the part that makes a thing stay. Say your answer out loud first, then turn the card.

Tap a card to turn it over.

13   Tools and Resources

What was actually on screen.

The running tool

Where you build skills, plugins, and connectors of your own. The engine underneath the demonstration, and where Noelle now does the large majority of her work.

The walking tool

Six pre-built agents with the harness already assembled, so the only work left is context. Shown as a worked example of a well built agentic system, not as a requirement.

Mapping your brain

Ingests your sources and generates a mind map, plus podcasts, slide decks, video overviews, flashcards, and quizzes from the same material. One notebook per project keeps the map readable.

Reading the fine print
Your permission screens

Not a product. The screen that appears when you connect an AI system to your mail, calendar, or social accounts. Noelle's suggestion if the language is dense: paste it into NotebookLM and have it explained to you.

A note on cost, since the session is candid about it. Noelle spends thousands each month across her systems, against a business that supports it, and she is explicit that this is not the expectation for anyone here. The tools shown run in the range of thirteen to thirty dollars a month. Her actual instruction is the inventory: know what you pay for, and know whether it still earns its place.

14   Quick Reference

The words from this session.

Persona document
The full guardrails guide for one agent. Role, responsibilities, what it optimizes for, what it must never do, operating principles, authority, responsible AI framing, use cases, and style. The grown up version of RTEC, and it should read like a job description.
Harness
The structure that holds an agent's context and connections so it can act. A pre-built platform gives you the harness and leaves the context to you.
Skill
The instruction set that teaches a model to perform a task properly. The unit you build in Claude.
Plugin
Several skills bundled so one action runs all of them.
Connector
Authorised access to a system where your work lives. The glue, and the part most people never finish.
The AI gap
The distance between what large platforms have shipped and what a specific customer needs now. Where an independent builder creates value, knowing it will eventually close.
Brain as a mesh
Treating your knowledge as a mapped network of sources that stay where they are, rather than one store everything is copied into.
Algorithmic heartbeat
Steady, consistent content that keeps you visible, as distinct from your major pieces. The job of a social agent.
AI engine optimisation
Writing so that AI systems name you when someone asks them for an expert in your field.
Actionable SOP
A standard operating procedure written as a skill, so it runs when its trigger occurs instead of waiting for a person to notice.
The shift this lesson asks for

Our job is not to write code. Our job is to write words that tell a machine how to operate.

Noelle Russell
15   Key Takeaways

What to carry out of this one.

01Design first, build second. The clarity you wrote last week is the input to everything here, and skipping it does not save time, it moves the cost later.
02The model is the processor and the context window is the working memory. Flat output usually means an empty desk, not a weak thinker.
03Keep an inventory of every AI system you pay for, with the problem you bought it to solve and whether it still solves it.
04Guardrails come in layers. You write some. The platform wrote others before you arrived. Know both, and be able to say what your agent may actually do.
05Write a persona document per agent. It should read like a job description, because that is exactly what it is.
06Do not build what is already commoditized. Your inbox is solved. Spend your effort on what only you can see.
07It is not the most powerful tool, it is the most connected one. Connectivity is where the real work is, and where most people stop.
08When a system feels worse, check whether an old habit is still running. Ask instead of scrolling.
09Point your model at where your knowledge already lives. Start contained, grow toward a mesh, and always know the scope of it.
10Ask for the rebuild document. You get disaster recovery and an audit trail, and the audit trail is the one that protects you.
11Build in the gap. It will close, and another will open above it. That is the pattern of the work, not a flaw in your plan.
12Interrogate the systems you use. Ask what they are not allowed to do and why. It is the cheapest education available.
What is next
Lesson 7
Implementation Lab: Building Your First AI Assistant
Noelle showed you a workforce someone else assembled and then pointed at the engine underneath it. Next session you sit down and build one yourself, with Vykintas Glodenis, using Claude Projects. The persona document you write from this lesson is the raw material you will bring.
You already know how to describe a role to someone you are about to hire. That is the whole skill. The only new part is who is reading it.
Lesson 6  ·  Onboard Your First AI Team Member  ·  Noelle Russell