🤫husshhussh
  • Wiki
Reserve
🤫husshhusshOneOne Puppy
🤫 Academy · learning, training & development

Become genuinely great. Go deep.

The era belongs to the curious and the confident - to deeply passionate researchers who can create, build, scale, and serve AI that keeps the human in control. The 🤫 Academy is our open curriculum of 27 skills that make you stand out and stand for something. Free, in the open, for every American and everyone who wants to grow.

Enroll in the semesterBuild with AI - field guide
We start with you

Working backwards from the student.

The Academy does not start with a syllabus. It starts with you, where you are in your journey, what you actually need, and who you are trying to help. Then we work backwards: the skills you learn and the agent you build are the ones that solve a real need in your life and your market.

Every agent you ship joins 🤫 Agent One's Trusted Circle of Agents: a growing set of trusted worker agents that let Agent One get more done for more people without going back to the human. The point is simple, that 🤫 Agent One meets people exactly where they are and becomes genuinely useful to them, their families, and the ones they love.

Start from a real need

Name a job that matters to you or your community. That becomes what you build, so the work is useful from day one, not a toy.

Build a trusted worker agent

Ship an agent good enough to join Agent One's Trusted Circle of Agents, one it can hand real tasks to and trust to finish them.

Meet people where they are

The measure is whether it helps a real person, a family, a loved one, on their terms, with the human always in control.

What you build, and why

Give the mundane work to the machine. Keep the inspiring work for yourself.

Here is the whole idea in one line. You build the daily agents that take on the work humans are not good at and do not enjoy, the mundane, deterministic, consistent, mindless work that is not inspiring or productive or fun for a person to do. Inbox triage. Rescheduling. Bills and reconciliations. Forms and follow-ups. Renewals and filing. Status chasing. The paperwork that grinds people down.

A machine does that work better than we ever will, because it is deterministic, consistent, and tireless. It applies the same rule to the first item and the ten-thousandth, at 2am, without a slow week or a bad mood. So we hand it that work on purpose, and we get the human back for the inspiring, creative, relational work only a person can do. The agents you build here are not toys. They are the boring, load-bearing things people quietly need done every single day.

What you actually build

A catalog of genuinely useful daily agents.

Over the semester you build a set of real, buildable agents, each one taking on a specific mundane task a person dislikes. For each: why it drains a human, what the agent does end to end, why a machine does it better, and the consent boundary that keeps the person in control. Pick the one that solves a real need in your life or your market, and go deep.

Inbox triage

🤫 Inbox Triage

The human pain
A few hundred messages a day, most of them noise, a few that truly matter. Sorting them by hand burns your freshest hours and still lets the important one slip.
What it does
Reads every incoming message, sorts by what actually needs you, drafts replies to the routine ones, and surfaces the short list that is genuinely yours to decide.
Why a machine does it better
It never gets tired at message two hundred, never skims, and applies the same rules to the first and the last. Consistency is the whole point.
The consent boundary
It only reads the accounts you connect and only sends what you approve. Every draft, label, and archive is a receipt you can undo.
Scheduling and rescheduling

🤫 Scheduling

The human pain
The endless back and forth to find a time, then the reshuffle when one thing moves and breaks five others. Nobody grew up dreaming of this.
What it does
Finds times that work across calendars, sends the invite, and when something moves it reschedules the knock-on meetings and tells everyone, cleanly.
Why a machine does it better
It holds every constraint in its head at once and never double-books. A human juggling ten calendars will eventually drop one.
The consent boundary
It sees only the calendars you share and books only inside the rules you set. Each hold and change is logged for you to reverse.
Bills and invoicing

🤫 Invoicing

The human pain
Cutting invoices, chasing the ones unpaid, matching payments as they trickle in. It is repetitive, it is late-at-night work, and one typo costs you real money.
What it does
Raises invoices from your agreed terms, sends them on schedule, watches for payment, and sends the polite reminder on the day it is due.
Why a machine does it better
It runs the same billing rules every cycle without forgetting, without a slow week, without letting a late invoice sit for a month.
The consent boundary
It bills only the clients and terms you authorize and sends only the reminders you approve. Every invoice and nudge is on the record.
Expense reports

🤫 Expense Reports

The human pain
The shoebox of receipts, the category dropdowns, the report due at month end that everyone puts off. Pure friction, zero joy.
What it does
Captures receipts as they happen, categorizes each one, matches it to the card charge, and assembles the finished report ready for you to submit.
Why a machine does it better
It categorizes the thousandth receipt exactly like the first, and never loses one to a washing machine or a coat pocket.
The consent boundary
It reads only the receipts and card feeds you connect and submits nothing without your sign-off. The full trail is yours to check.
Reconciliations

🤫 Reconciliation

The human pain
Line by line, statement against ledger, hunting the one number that does not tie out. Hours of squinting for a difference of a few cents.
What it does
Matches every transaction across your accounts and ledger, flags only the true mismatches, and shows the likely cause for each one.
Why a machine does it better
It compares thousands of rows without a lapse in attention and finds the break a tired human eye slides right past.
The consent boundary
It reads only the accounts you link, changes nothing on its own, and hands you the flagged items to resolve with a clear reason each.
Form-filling and paperwork

🤫 Paperwork

The human pain
The same details typed into the same fields, again, across forms that never quite agree. Mind-numbing, and one wrong box means starting over.
What it does
Fills recurring forms and applications from your consented details, checks them for the common mistakes, and stages them for your review.
Why a machine does it better
It transcribes the same field the same way every time and never fat-fingers a date on the two hundredth form.
The consent boundary
It uses only the information you authorize for the specific form and submits nothing until you say so. Every filled field is traceable.
Follow-ups and reminders

🤫 Follow-ups

The human pain
The promise you made to circle back, buried under the next thing. Dropped follow-ups quietly cost relationships and deals.
What it does
Tracks every open loop you create, remembers who owes what by when, and sends the right nudge at the right time in your voice.
Why a machine does it better
It forgets nothing and lets nothing age out. A human remembers the loud ones and loses the quiet, important ones.
The consent boundary
It follows up only on the threads you mark and sends only messages you approve. Every reminder it fires is logged for you.
Renewals

🤫 Renewals

The human pain
Subscriptions and policies that auto-renew before you look, or lapse right when you need them. Either way you lose, and you never see it coming.
What it does
Watches every renewal date, surfaces the choice ahead of time with what changed, and renews, cancels, or renegotiates on your instruction.
Why a machine does it better
It watches every date at once, all year, and never misses the window the way a human buried in the day always eventually does.
The consent boundary
It tracks only what you add and acts only on your decision. Nothing renews or cancels without your word and a receipt.
Data entry and filing

🤫 Filing

The human pain
Retyping the same numbers into the same systems, sorting documents into the right folders. Deadening, error-prone, and endless.
What it does
Reads incoming documents, extracts the fields that matter, files each in the right place, and enters the data into your systems cleanly.
Why a machine does it better
It types the same value the same way a thousand times and files by the same rule every time. Humans transpose digits when they are bored.
The consent boundary
It reads only the documents and systems you connect and writes only where you allow. Every entry and move leaves a receipt.
Status chasing

🤫 Status Chaser

The human pain
The daily rounds to ask where things stand, then stitching the answers into one picture. Interruptive for everyone and stale by lunch.
What it does
Pulls status from the tools and people involved, assembles one honest current picture, and flags only what is actually stuck.
Why a machine does it better
It checks every source on the same cadence without nagging fatigue, and gives you the same complete picture every morning.
The consent boundary
It reads only the sources you connect and asks only the people you approve. What it gathers and shares is on the record.
Prior-authorization workflows

🤫 Prior Authorization

The human pain
Gathering the same documents, filling the same request, calling to check on it, resubmitting when a box was wrong. A person in need waits while a human wrestles paperwork.
What it does
Assembles the required documents, submits the request the way the process demands, tracks its status, and handles the routine back and forth.
Why a machine does it better
It follows a long, exacting, rule-bound process the same way every time and never tires of the paperwork that grinds humans down.
The consent boundary
It acts only within the case and permissions you authorize, and a human always makes the decisions that matter, with a full receipt.
How to use this

Pick one. Go three levels deeper than anyone expects.

Go deep, not wide

Pick a topic and become the person others come to. Depth is what differentiates; breadth is what follows.

Curiosity → confidence

Real confidence comes from knowing, deeply. The more you genuinely understand, the calmer and bolder you become.

The human is always in control

We build toward a world where machines keep learning and helping, and humans always decide. Co-exist, co-operate, co-evolve.

Knowledge as a utility

Intelligence and supercomputing should be as available as electricity, clean water, and good food - to every American, whenever they need it.

Track I · understand the machine

Foundations of agentic AI

Topic 01

How LLMs actually work

Tokens, embeddings, attention, context windows - the real mechanics, so nothing is magic and everything is debuggable.

Topic 02

Prompting & context engineering

Designing the inputs, memory, and retrieval that make a model reliable - the highest-leverage skill in the field.

Topic 03

Building agents

Tools, planning loops, memory, and guardrails - turning a model into something that gets real work done, safely.

Topic 04

Evals & taste

Measuring quality you can't eyeball. Building evals, and developing the taste to know what 'good' even is.

Topic 05

Retrieval & knowledge systems (RAG)

Grounding agents in real, current, owned knowledge - and knowing when retrieval helps and when it hurts.

Topic 06

Multi-agent systems & orchestration

Agents that coordinate - fan-out, verify, synthesize - without turning into chaos. Deterministic where it matters.

Track II · build it well

Engineering craft

Topic 07

Vibe coding & Software 2.0

Building with AI as your pair - fast, fluent, and still rigorous. The new default way to make software.

Topic 08

Code like bacteria

Small, modular, self-contained code anyone can yoink. Maximize bacterial DNA; build a backbone only where complexity demands.

Topic 09

Protocols & interoperability

MCP, A2A, AP2, UCP - and PCHP for consent. How systems and agents speak to each other so everything composes.

Topic 10

Security, privacy & consent-first design

Build so the person owns their data by construction - scoped access, receipts, least privilege, revocability.

Topic 11

Systems design & scaling

From one user to millions - latency, cost, failure modes, and the distributed edge. Design for the real world.

Topic 12

Observability & reliability

If you can't see it, you can't run it. Logs, metrics, traces, and the discipline of operating what you ship.

Track III · serve the person

Human & customer centricity

Topic 13

Work backwards from the customer

Start with what the person is trying to accomplish, then build toward it. The discipline behind every great product.

Topic 14

Human-centered design & taste

Fewer, better surfaces that make the right action obvious. Simplicity is the hardest, highest craft.

Topic 15

Storytelling - clarity, class & candor

Say the true thing, simply and beautifully. The skill that turns good work into work that moves people.

Topic 16

Keep the human in control

Designing AI that amplifies human agency - machines that learn and help, humans who always decide.

Topic 17

Accessibility & inclusion

Build for everyone, including grandma and the person on the worst connection. Excellence leaves no one out.

Track IV · think deeply

The researcher's mind

Topic 18

Become a deep researcher

Go three levels deeper than anyone expects. Curiosity compounded into genuine, hard-won expertise.

Topic 19

First-principles thinking

Reason from what's actually true, not from what's merely assumed. The root of every real breakthrough.

Topic 20

Read & synthesize primary sources

Go to the paper, the law, the code. Build the muscle of separating signal from secondhand noise.

Topic 21

Write to think, in the open

Writing is thinking made checkable. Publish your reasoning; let the world strengthen it.

Topic 22

Learn how to learn

Deliberate practice, spaced repetition, feedback loops - the meta-skill that makes every other skill faster.

Track V · make it matter

Business, value & distribution

Topic 23

How businesses really win

Free cash flow, durable advantage, and compounding - own the things that grow value over decades, not quarters.

Topic 24

Go-to-market, sales & hustle

Aligning with the people you serve and getting real value into their hands. Selling the right thing, the right way.

Topic 25

Community building & open source

Grow a movement by being generous and legible. The strongest distribution there is.

Topic 26

Personal & business supercomputing

Own your compute. Think like a garage owner - a distributed edge grid that serves people at the lowest cost per watt.

Topic 27

Data ownership, rights & the sovereign agent

The right to own your information and the agent that acts on it - the foundation everything else stands on.

Why we do this

Superpowers, generally available.

We believe knowledge and intelligence - and personal and business supercomputing - should be as available as electricity, clean water, great food, and a safe home: there whenever you need it, for every American citizen first, and for everyone who wants to learn. Machines that keep learning and helping; humans always in control, achieving their true potential, whatever that may be. That's the world the 🤫 Academy is here to help build.

Enroll

A semester you build through, day by day.

The Academy is not a video you half-watch. It is a 16-week semester you enroll in and build through, 8 to 10 hours a day, hands on the keyboard, shipping something real every single day on 🤫 Agent One end to end. You learn by doing, get your hands dirty daily, and come out able to build a genuinely useful working agent, with a certification to prove it.

Length
16 weeks
Each day
8 to 10 hours, hands on
Cadence
Learn, build, ship, every day
You finish with
A shipped agent and a cert
A day at the Academy

Same rhythm every day, so the habit does the work.

0:00 - 1:30

Learn the concept

Start with the day's idea from the field guide and the track, three levels deeper than a tutorial. Read the code like bacteria: small, modular, yoink-able.

1:30 - 2:00

See it done

Watch a train-the-trainer build the thing live, then read the working example end to end so you know exactly what good looks like.

2:00 - 6:30

Build it yourself

Hands on the keyboard. Build today's piece of your own agent on 🤫 Agent One, with Siri AI on-device and GCP Private Cloud Compute. Stuck is part of the plan; your pod and your trainer are right there.

6:30 - 7:30

Ship and demo

Deploy what you built today and demo it to your pod. If it does not run for a real person, it does not count. Ship daily.

7:30 - 8:00

Reflect and log

Write down what you learned and what broke. Post your build to the leaderboard. Tomorrow you go again, a little better.

How you get into flow

Eight to ten hours a day, and the day disappears.

Flow is not an accident here. It is engineered. You show up, you build, and the hours vanish because everything that usually pulls you out of the work has been designed away. This is what a day actually feels like.

One clear thing to build, today

You never open the laptop wondering what to do. Each day has one concrete artifact to ship. A clear, hard, reachable goal is the fastest on-ramp to flow there is.

A pod beside you

You build in a small pod of people at your level. You demo to them, you unblock each other, you carry each other on the hard days. Nobody builds alone.

A trainer within arm's reach

A train-the-trainer is right there, not a ticket queue. When you are stuck, help is minutes away, so you stay in the work instead of drowning in it.

Stuck is the plan

Being stuck is not failure, it is the curriculum. The struggle right before the breakthrough is where the learning lives. We expect it, and we build straight through it.

Ship daily, feel it move

Every day ends with something that runs for a real person. That daily win, visible and real, is the loop that keeps you coming back sharper tomorrow.

The leaderboard and the demo

You post your build, you see the cohort's, you demo yours out loud. Friendly pressure and a real audience turn a long day into a game you want to win.

Put it together and the day gets its own momentum. Learn, build, get stuck, break through, ship, demo, log it, sleep, go again. By week three you are not studying agentic AI. You are living inside it, and it is the best part of your day.

The semester, week by week

Sixteen weeks. Five tracks. One shipped agent.

Every week has an outcome and a thing you ship. You move from understanding the machine, to building it well, to serving the human, to thinking deeply, to making it matter, and finally to a three-week capstone where you build and ship one genuinely useful agent into 🤫 Agent One's Trusted Circle of Agents.

Week 1
Track I - Foundations

Orientation and your first agent

Set up your 🤫 Agent One, your tools, and your build environment. Understand what an agent actually is by making one do a job you dislike.

You build: A hello-world agent that does one real, boring task for you end to end.

  • Day 1: pick one mundane task from your own week that you hate doing. That is your north star for the whole semester.
  • Wire the agent to one tool and one trigger. No planning loop yet, just an honest input to output.
  • Read a working example line by line before you write your own. Yoink shamelessly, then make it yours.

What good looks like: A non-technical friend watches it run once and immediately says I want that.

You ship: A working hello-world agent that does one real task for you by end of day one.

Week 2
Track I - Foundations

How agents think

Planning, tools, memory, and the loop. Learn the machine well enough to debug it when it goes sideways.

You build: An agent that plans a multi-step task and picks the right tool at each step.

  • Trace one request end to end: what the model saw, what it decided, which tool it called, what came back.
  • Break your agent on purpose, then read the trace to find where the plan went wrong.
  • Write the tool descriptions the way you would brief a new hire: precise, unambiguous, testable.

What good looks like: You can point at any step in a run and explain in plain English why the agent did that.

You ship: An agent that plans a multi-step task and uses two tools to finish it.

Week 3
Track I - Foundations

Memory and context

Personal memory, retrieval, and context windows. Give your agent something to remember so it stops asking the same question twice.

You build: An agent that remembers your preferences and context across sessions.

  • Store the three facts your task needs most, and prove they survive a restart.
  • Retrieve only what the current step needs. A full memory dump is a bug, not a feature.
  • Show the receipt: the agent can tell the person what it remembered and why.

What good looks like: Run it Monday, run it Friday, and it already knows you. No re-briefing.

You ship: An agent with durable memory that recalls your preferences across sessions.

Week 4
Track II - Engineering craft

Patterns that hold up

The design patterns of resilient agents: guardrails, retries, timeouts, and clean failure recovery.

You build: An agent that fails gracefully, retries, and hands control back to the human when it should.

  • List every way today's task can fail, then handle the top three deliberately.
  • Add a stop line: the exact condition where the agent must pause and ask a human.
  • Keep the code bacterial. Small functions a stranger could lift into their own project.

What good looks like: You unplug the network mid-run and the agent degrades calmly instead of lying.

You ship: An agent that fails gracefully and recovers, with the human able to step in.

Week 5
Track II - Engineering craft

Evals and trust

How you know it works: evals, tests, and measuring real behavior instead of vibes.

You build: An eval suite and a small dashboard that proves your agent got better, not just different.

  • Write ten real cases from your own task, including the two that always break.
  • Score a run today, change one thing, score again. Watch the number move.
  • Catch a silent regression before your pod does. That is the whole job.

What good looks like: You can defend the sentence it is better now with a number and a test, not a feeling.

You ship: An eval suite for your agent and a dashboard that proves it improved.

Week 6
Track II - Engineering craft

On-device and at the edge

Run on Siri AI on-device and GCP Private Cloud Compute. Tokens per watt, in practice, the way we actually ship.

You build: Your agent running privately on Siri AI on-device with a measured cost per task.

  • Move the sensitive step on-device so the person's data never leaves their hands.
  • Measure cost and latency per task, then cut one of them in half.
  • Decide out loud what runs on-device and what runs in Private Cloud Compute, and why.

What good looks like: It runs with the network off for the private step, and you know its cost per run to the cent.

You ship: Your agent running privately on-device, with a clear cost per task.

Week 7
Track III - Human centricity

An experience a grandmother loves

UX for agents: make the right action obvious, the tone calm and kind, the human always in control.

You build: A redesign of your agent that a non-technical person finishes alone, calmly.

  • Cut every screen and word that is not doing real work. Fewer, better surfaces.
  • Watch a real non-technical person use it without your help. Say nothing. Take notes.
  • Make the undo and the stop button impossible to miss.

What good looks like: Someone who has never seen it finishes the task on the first try without asking you a thing.

You ship: A redesign of your agent that a non-technical person finishes without help.

Week 8
Track III - Human centricity

Consent, by construction

The 🤫 consent layer and the Hushh Protocol: sharing with a receipt, the Circle of Trust, privacy you can feel.

You build: Consent and a receipt wired into every action your agent takes.

  • The agent acts only on what the person authorized, scoped and revocable, least privilege by default.
  • Every action leaves a plain-English receipt the person can read and undo.
  • Design the moment of asking so consent feels like control, not a dialog box in the way.

What good looks like: A stranger can see exactly what the agent did on their behalf, and revoke it in one tap.

You ship: Your agent shares only by consent, with a receipt for every action.

Week 9
Track IV - The researcher's mind

Go deep on one thing

Pick a hard problem inside your task and out-study everyone. Read the primary sources, run the experiments.

You build: A written deep dive plus a working experiment that teaches the cohort something new.

  • Go to the paper, the law, or the code itself, not the summary of the summary.
  • Form a claim, then design the smallest experiment that could prove you wrong.
  • Write it in the open so the cohort can check your reasoning and make it stronger.

What good looks like: The room learns something they did not know this morning, and can reproduce it.

You ship: A written deep dive and a working experiment that teaches the cohort something new.

Week 10
Track IV - The researcher's mind

Build a personal world model

Turn a person's real data, by consent, into an agent that knows their world well enough to act without re-asking.

You build: An agent grounded in a real, consented personal world model that genuinely knows one person's context.

  • Ground the agent in one real person's consented data, with a receipt for every source.
  • Prove the model helps: a task that was slow yesterday is one step today.
  • Keep it owned by the person. They can see it, correct it, and take it with them.

What good looks like: The agent makes a call that is right precisely because it knows this person, and shows why.

You ship: An agent grounded in a real (consented) personal world model.

Week 11
Track V - Value and distribution

Make it matter

Package the agent as something a real person or business would pay for and keep using.

You build: A one-page offer: what the agent does, who it is for, and what it is honestly worth.

  • Name the mundane job it removes and the hours it gives back, in the person's own words.
  • Price it honestly against the pain it removes, not against what you wish it were worth.
  • Write the promise you can actually keep, and nothing you cannot.

What good looks like: A stranger reads the one-pager and says how do I get it, with no pitch from you.

You ship: A clear offer: what it does, who it helps, and what it is worth.

Week 12
Track V - Value and distribution

Get your first ten users

Grass-roots distribution: install 🤫 Agent One for real households and shops, then listen harder than you talk.

You build: Ten real people or shops outside the cohort using your agent, and a feedback loop that catches every complaint.

  • Install it for ten real users by hand. Watch each one; the install is the interview.
  • Open one channel where users can reach you, and answer every message fast.
  • Turn the top complaint into tomorrow's build. Close the loop out loud.

What good looks like: At least a few users come back unprompted and tell a friend. That is the seed of a community.

You ship: Ten real installs outside the cohort, with feedback flowing back into the build.

Week 13
Capstone

Capstone, week one: scope

Start from a real need and design one genuinely useful agent for 🤫 Agent One's Trusted Circle of Agents, built to finish the job without going back to the human.

You build: A scoped capstone spec rooted in a real person's need, plus a working skeleton.

  • Write the one mundane, deterministic job it will own end to end. One job, done completely.
  • Define the consent boundary and the receipt before you write the logic.
  • Stand up the skeleton so the happy path runs, even if it is thin.

What good looks like: The spec fits on a page and a stranger understands exactly who it helps and how.

You ship: A scoped capstone spec, rooted in a real person's need, and a working skeleton.

Week 14
Capstone

Capstone, week two: build

Build the capstone for real, every day, with your trainer and pod reviewing each ship.

You build: A capstone that does its core job end to end, reviewed at every daily ship.

  • Ship a working slice every single day. No dark weeks, no big-bang reveal.
  • Keep it bacterial: modular pieces your pod could reuse in their own capstones.
  • Run it for your real user as you build, so the feedback never goes stale.

What good looks like: The core job works end to end for a real person, today, not in theory.

You ship: A capstone that does its core job end to end.

Week 15
Capstone

Capstone, week three: harden

Harden every edge until someone who has never met you would hand it a real task.

You build: A capstone hardened on evals, consent, UX, and reliability until a stranger can trust it.

  • Pass your own eval suite, then the two cases you were afraid to write.
  • Every action has a receipt, every failure has a soft landing, every screen earns its place.
  • Hand it to a stranger cold and let them try to break it. Fix what they find.

What good looks like: A person you have never met completes a real task and says they would use it again.

You ship: A capstone that passes the hands-on build review.

Week 16
Demo day and certification

Ship it into the Trusted Circle of Agents

Put your agent into the Trusted Circle of Agents for a real person, demo it, and defend it in front of the cohort.

You build: Your agent, live in 🤫 Agent One's Trusted Circle of Agents, doing real work for a real person.

  • Ship it into the Trusted Circle so Agent One can hand it real tasks and trust it to finish.
  • Bring evidence: a real user, the hours given back, and the receipts to prove it acted only on consent.
  • Defend the build. Answer the hard questions honestly, in the spirit of the Rude FAQ.

What good looks like: A real person keeps using it after demo day because it genuinely helps their week.

You ship: A shipped, working agent that helps a real person, a real 🤫 certification, and your place on the leaderboard.

The capstone, in one line

Ship one genuinely useful working agent into 🤫 Agent One's Trusted Circle of Agents.

One agent that owns one mundane job end to end. Real users who keep using it after demo day. Evidence it actually helps, the hours it gives back, and a receipt for every action proving it acted only on consent. You defend it in front of the cohort, honestly, in the spirit of the Rude FAQ. That is the finish line, and it is a real one.

Build the product, the business, the community

Turn your agent into something real people love and keep.

A working agent is the start, not the finish. In the back half of the semester you turn it into a real product with real users, an honest business, and a small community that loves it. This is the part most courses skip. We do not.

01

Package the product

Wrap your agent so a stranger can adopt it without you in the room. Name it, write the one promise it keeps, and make the first run effortless.

02

Price it honestly

Price against the pain it removes and the hours it gives back, not against hype. A fair price you can defend beats a big one you cannot.

03

Get your first ten users

Install it by hand for ten real people or shops outside the cohort. The install is the interview. Watch every one and write down what breaks.

04

Gather feedback that changes the build

Open one channel where users reach you, answer fast, and turn the loudest complaint into tomorrow's ship. Close the loop out loud.

05

Grow a community

Be generous and legible. Share how it works, credit your sources, and help users help each other. The strongest distribution there is.

06

Earn a base that loves it

The measure is simple: do users come back unprompted, and do they tell a friend. Retention and word of mouth over vanity numbers, always.

This is an aspirational program, and we say so plainly. We are honest about what is live and what is planned, we make no claims of outcomes we do not have, and we never invent a testimonial or a number. The proof is the working agent and the real people it helps.

What you get in return

Real certifications. Real proof of work.

You asked for structure, and something to show for the time and energy you put in. So the Academy is a path with a finish line. Complete the topics, pass the hands-on build, and ship one genuinely useful working agent into 🤫 Agent One's Trusted Circle of Agents. Do that, and you earn a real 🤫 certification, and a place on the leaderboards for the topics people love to learn, teach, and talk about.

01

Learn the track

Go three levels deeper than anyone expects, with a train-the-trainer beside you.

02

Pass the build

Hands on the keyboard on Siri AI on-device and GCP Private Cloud Compute, the way we actually build.

03

Ship one agent

Put one genuinely useful working agent into 🤫 Agent One's Trusted Circle of Agents, so it gets the job done without going back to the human.

04

Earn the cert

Get a real 🤫 certification and your place on the leaderboard. Proof of work, not a participation badge.

The design bible for the build is our own essay, coding like bacteria: small, modular, yoink-able code anyone can learn from and reuse.

Teach it. Open one.

A train-the-trainer academy, built to franchise.

The fastest way to put 🤫 Agent One in everyone's hands is to teach it, person to person, town by town. The Academy runs as a franchise: local product specialists and forward-deployed engineering grow from the grass roots, and the best teachers become train-the-trainers who coach the next class.

Everyone who loves to teach

We hire and train at every level, from 9th and 10th graders who love to coach and learn, to teachers, coaches, professionals, PhD students, and professors who build curriculum and human connection.

Hands on the real stack

Agentic AI design and development on Siri AI on-device and GCP Private Cloud Compute, taught by people who ship, not just slide decks.

Open a 🤫 Academy

A franchise playbook so you can open one where you live, certify learners, and drive Agent One installs that actually help your community.

We are hiring - funded US role

Head of the 🤫 Academy (Train-the-Trainer Lead)

A funded, full-time US role to found this Academy and the team of hands-on train-the-trainers behind it. If you love to build, teach, and learn at the same time, this one is for you.

See the role and apply

Enroll. Build every day. Ship something real.

A semester of getting your hands dirty with 🤫 Agent One end to end, until you can build a genuinely useful agent and prove it. Start where you are, go as deep as you dare.

Enroll in the semesterBuild with AI - field guideClaim your 🤫 One - free

One is a product of Hushh Technologies Corporation (brand: 🤫 “hussh”), an independent company. One runs on third-party silicon, systems, and cloud; all company names are used solely to describe the platforms on which One software runs. Hushh Technologies is not affiliated with, endorsed by, sponsored by, or partnered with any company named.