How every part of miatz actually works

What miatz is and how the program works end to end.

A quick tour of the sidebar and what each area is for.

A browsable catalogue of what AI is actually used for, across 25 categories — each entry naming its tools, its effort, its India-specific compliance question and what it does not do.

Where your AI Readiness Check result lives once you have an account, what changed since your last sitting, and when you can take it again.

How the in-browser runner and tests work.

Why the flashcards come back, and how scheduling works.

How your prompts are scored and improved.

Time-block your focus, check in, and run your daily rituals.

Track assigned and self-set work with priority, impact and done-ness.

The Saturday 3×3 — review the week and set intent for the next.

How in-app video works and what watch tracking means.

University-style courses with prerequisites, quizzes and badges.

The three gates, the daily check-in, the Gym, and your calibration curve.

Daily reflections, collected — your own record of how your thinking grew.

Investigate a simulated production incident, resolve it, and get graded like an SRE.

Pitch, de-escalate, negotiate and present against an AI that stays in character — then get scored.

Look at a real screen and reconstruct the spec that produced it — graded instantly by AI.

Five live playgrounds for tokenization, chunking, embeddings, retrieval and sampling.

QA real, live products — then study their architecture and code once you unlock the advanced tabs.

Structured defect reports on the apps under test: reviewed by mentors, valid bugs earn XP.

The in-platform editor: draft files, commit them to your own GitHub repository, and get the grade posted onto the pull request. A GitHub account is optional.

The rungs between finishing a lesson and doing work somebody else accepted: challenges, open-source contributions and bounties.

How exams are graded and how you advance.

The shareable proof you leave with.

Everything Xook remembers about how you learn, curated by you: confirm facts, bookmark concepts, set reminders, and export it.

A BYOK coach grounded in your own course, progress and reflections — powered by your own free key.

Ask course questions and get answers grounded in the actual curriculum, from a subject-expert persona.

Provision a personal autonomous agent on free cloud infrastructure, run your daily work through it, and get coached on how you operate it.

Spaces, threads, votes, accepted answers — and how to flag content or block a member.

How the XP and spoken-skills leaderboards rank you, and what the dashboard league resets.

Roles from mentors, alumni and partner employers — built for this community.

Record or upload spoken answers; they're transcribed, AI-graded, and reviewable by your mentors.

Map your skills spoke by spoke, get levels mentor-verified, and pick deep-dive tracks.

How the evidence bars work and how to request (or auto-unlock) your next level.

Your learning curve, your time on platform, and the you-vs-past-you evidence dossier.

Build a real system, submit it for mentor review, and publish it to your public portfolio.

Join real incubated builds, work mentor-assigned tasks, and ship as an apprentice.

Opt in to a public, employer-checkable profile — and how signed credential links verify.

Control what reaches you and how.

Password, email, data export and deletion.

How to generate a free API key and connect it so Xook answers grounded in your learning.

Install on iPhone, iPad or Android, set up the biometric lock, push and the app badge.

The miatz iOS app — Face ID app-lock, push notifications, Sign in with Apple — and how to use miatz on your iPhone today.

The miatz Android app — biometric unlock, FCM push notifications, Google sign-in — and how to use miatz on Android today.

How to install the miatz web app on desktop, Android and iPhone straight from your browser — and what keeps working offline.

What free actually means at miatz: founding cohorts pay nothing, no card on file, and AI runs on your own free-tier key.

The optional Chuun placement exam: what it measures, how it runs, and what happens after — you can learn on miatz without it.

For the founding cohort: one Chuun sitting every seven days, free, with no separate lifetime cap.

How miatz protects your bring-your-own AI API key: AES-256-GCM encryption, a device-only mode, automatic failover and instant revocation.

How to export a full copy of your miatz data and permanently delete your account, self-serve, from Profile → Account.

Add admin employees with granular roles and fine-tune permissions.

Choose which modules your learners see, within your plan.

See touchpoints, engagement and AI usage across your learners.

Create cohorts, review applicants and enroll learners — with seat quotas enforced automatically.

One page per learner: vitals, integrity, AI usage, every artifact they produced — and the levers to coach them.

Create flashcards, coding challenges, lessons and case studies; tune AI tutor personas and role-play scenarios.

What lands in each review queue, and what happens when you action it.

Share encrypted org AI keys with your learners, set fallback precedence, and watch usage and estimated cost.

Connect Slack and choose, per event type, where notifications go: Slack channel, in-app bell, email.

Review user-reported forum content and either hide it or resolve the report.

Retain/release scorecards, the Acquire→Activate→Habit→Master→Prove funnel, and first-party acquisition analytics.

Register the apps learners test, sync their schema and repo to unlock walkthroughs, and run the Bug Board.

Triage learner questions, platform issues and access requests from one queue.

Your organization's control plane — members, teams, invites and domain claims.

Where a staff admin starts: cohorts, grading queues and the gatekeeping engine, in one landing.

Switch the live playgrounds on for learners, keep the retrieval index fresh, and watch what gets used.

Enable the assistant module and monitor every pod — health, provider and a per-pod kill switch.

Run your organization's people, teams, invitations and domains from one control plane.

Add people, set what they can do, and organise them into teams.

Invite people individually or in bulk, and track who has accepted.

Verify a domain so colleagues join automatically when they sign up.

Set the palette, logo, wordmark and login headline your people see.

Propose, accept and suspend partnerships with other organisations on the platform.

Switch off anything your programme does not need — everyone in the organization stops seeing it.

Every recorded admin action in your organization — invitations, role changes, domain claims and seat moves.

A two-hour sitting that measures how a candidate works with AI, returning a band from one to ten.

Cohort-level fluency readiness computed from real work — coach, not cop, with no individual rows behind the page.

Pick which published courses your learners see, and whether each one feeds your assistant's retrieval.

Where a mentor sees the learners they are responsible for, and the work waiting on them.

What miatz reads from your documentation, and what it turns that into.

Point miatz at the places your product truth already lives, and run them.

A 0–100 rubric score for your documentation, with a fix queue ordered by impact.

The tracks your corpus compiles into, and the lifecycle every piece moves through.

Nothing publishes without a person on your side approving it.

What an exam measures, in what proportion, and the pass mark a panel can defend.

Draft, beta, live and retired items — and how you tell which ones earn their place.

How exams are monitored, what needs consent, and how a person reviews a flagged session.

How people are enrolled on courses, how progress is tracked, and how readiness is measured.

Group people into static rosters or dynamic, self-updating segments — and assign paths on entry.

Live adoption, progress and readiness for your organization, built from the activity stream.

Who you are responsible for, how people arrive on your list, and exactly what being assigned lets you see.

How work reaches a reviewer, why you can only hold three items at once, and what escalation and SLA actually mean here.

What you can see about one learner, which notes they can read, and why an answered question sometimes still shows.

Design credential templates, issue them to your people, and let anyone verify them at a public link — signed and endorsed by miatz.

A cited assistant over your own published knowledge that refuses anything it can't ground, and turns every refusal into a content gap.

Declare agents over your knowledge and learning ops. Every run is recorded and gated; content changes need a human approval; the execution runtime is not yet wired.

Four deeper ways to establish that someone can actually do the work: an adaptive viva, in-product Journey runs, LTI launches from your LMS, and partner tiers that follow certified headcount.

A spoken assessment that follows up where the answer was weak, scores against an SME-approved rubric, and always sends a borderline result to a human.

Grade a run inside your own product: which checkpoints they reached, how directly, how long it took, whether they recovered from their own mistakes — with anti-gaming signals that call a human rather than fail anyone.

Register your learning platform once, and your people reach miatz courses and exams from inside the LMS they already use — without miatz ever holding a shared secret.

Tier your partners by how many of their people hold a live credential, with the exact gap to the next tier always visible to both sides.

Rules notice inactivity, slipping due dates, expiring credentials and repeated quiz failures, then act. Every rule is configuration you can read and change.

One score per person, rolled up per team and per cohort, from learning done, proof earned and practice applied — with a one-click nudge for whoever is behind.

Send alerts and outcomes where your team already works. Every delivery is signed, and the signing key is shown once and never stored anywhere it can be read back.

When to use the AI Tutor, the community, or a ticket.