Community Soon Book @Human Walkthrough
Why @Human

Why @Human? Five reasons the safe way to build with AI is also the smart one.

@Human isn't a prototype tool with governance bolted on. It's a mature, open-source application platform where AI is used carefully, code is tested before it ships, and you stay in control of your data, your models and your costs.

Real products built on @Human, each shown as the app and then in the @Human project builder: @Human Answers, @Human Insight, Docs, Sheets, Guide Studio and Project Requirements
1Why @Human

Tokenomics: pay for intelligence, not repetition

Every time an agent re-reasons a routine step, you pay for it again. @Human uses AI to help design an application, then runs it as reusable code: data models, pages and programmatic automations that cost nothing in tokens, however often they run.

The usual wayAgents call a model on every ticket, claim and form, so the bill grows with your success.
The @Human wayAI helps build the app once. The app runs as code, with agents kept for the steps that need judgement.
  • Programmatic before agenticWhere both would work, @Human chooses the automation you can test and rerun for free
  • Reusable building blocksModules, fields, pages, workflows and policies carry from one project to the next
  • Data, not promptsA spreadsheet engine in @Human is 16 governed modules, not a pile of instructions to an LLM
The Spreadsheet project in the @Human builder: a full spreadsheet engine modelled as 16 modules
Sheets, in the builder. Workbooks, cells, formulas, pivots and protected ranges are 16 reusable modules: data your other projects can link to and report on.

Where the token bill comes from

An agent-first process is billed on every run. With @Human, AI helps you build once, then routine runs cost nothing in tokens.

Illustrative only. Actual costs depend on your model, provider and volumes.
Build Agent on every run @Human Runs over time
2Why @Human

Security: code you can test before anyone depends on it

AI-generated behaviour you can't test is a liability. In @Human, applications are code and configuration you can read, version and try in a draft. Every custom app runs in a sandbox and declares exactly which data it may read, write or delete.

The usual wayPrompt-driven agents behave differently on every run, and nobody can say for sure what they'll do in production.
The @Human wayPre-testable apps and automations, sandboxed permissions, signed approval gates and runtime guardrails.
  • Sandboxed apps with a manifestEach app declares its modules; writes and deletes ask the user first
  • Draft, then publishTry every change in a draft version. Approvals lapse if anything changes after sign-off
  • Least privilege, down to the fieldRoles, field-level denies and own-records-only access
The @Human Answers app manifest in the builder: 14 declared modules with read, write and delete permissions, and its sandbox rules
@Human Answers, in the builder. The real app manifest: 14 declared modules, 11 writable, only 2 deletable, and a confirmation before any write.

Tested in a draft. Guarded at runtime.

Every change happens on a draft version that can be tried before anyone signs it. Once live, runtime enforcement checks every agent reply against your rules and blocks or rephrases anything that breaks them.

Animation: a support assistant's draft promising a guaranteed refund is blocked, a safe reply is sent and a monitoring rule raises an alert
Runtime enforcement. "No refund or legal promises" blocks an unsafe reply before the customer sees it.
3Why @Human

Platform maturity: stable code, already running in the real world

@Human is built on Corteza, Planet Crust's open-source low-code platform. Its core code is already deployed by organisations including Cisco, KBR and Nemak, across many industries. You get AI on top of a foundation that's been hardened in production, not invented last quarter.

The usual wayNew AI-native tools are rebuilt every few months, and your apps break when they do.
The @Human wayA proven open-source core for data, pages, workflows and permissions, with AI and governance layered on top.
  • Open source and auditableYour security team can read the core, not just trust a vendor's word
  • A standard data modelModules, fields and relations that any developer or analyst can understand
  • Stable from day onePredictable behaviour your teams, auditors and customers can rely on
The @Human Insight data model in the builder: 11 modules from collections and data sources to metrics, dashboards, alerts and subscriptions
@Human Insight, in the builder. An analytics product as 11 related modules: data sources, datasets, metrics, questions, dashboards, alerts and subscriptions.
4Why @Human

UX without compromise: governed doesn't mean grey

Low-code usually means forms and grids. @Human gives you a governed data layer and the freedom to build any interface on top of it: custom web apps, native dashboards and familiar tools like docs and spreadsheets that people actually enjoy using.

@Human Answers built on @Human
@Human AnswersCited answers from your own sources
Docs built on @Human
DocsDocuments with versions and security profiles
Sheets built on @Human
SheetsFormulas, named ranges, pivots and charts
Guide Studio built on @Human
Guide StudioScreen capture to guides and issue reports
Native dashboards built on @Human
Native dashboardsHeatmaps, Sankey, sunburst and more
@Human Insight built on @Human
@Human InsightAsk your data, get explained charts
Any design, any layoutCustom web apps run inside @Human or open publicly by link.
Consistent by defaultApps can inherit the platform theme, so every tool feels like one product.
Governance stays invisibleUsers see a great app. Your DPO sees the register, policies and approvals behind it.
5Why @Human

Sovereignty by design: your estate, your models, your off switch

@Human is software you run, not SaaS. It sits inside your infrastructure, works with any AI provider or none, and keeps your core operations running if you unplug AI entirely.

The usual wayYour processes depend on one AI vendor's pricing, policies and uptime, and on a SaaS provider holding your data.
The @Human wayCustomer-run software, any LLM, and programmatic core processes that keep working without AI.
  • No AI lock-inEU-hosted, hyperscaler or open models. Switch without rebuilding
  • Operational if unpluggedForms, records, rules, approvals and reports keep running
  • Your cloud or your serversAzure, AWS, Google Cloud, DigitalOcean, Hetzner or on-premises
Animation: a service desk switches AI providers, then AI is disconnected and routing, escalations and reports keep running
Unplug test. The AI provider is switched off, and ticket routing, escalation and reporting carry on.

Real products we built on @Human

We use @Human to build our own tools. Each one is a governed project you can open in the builder: the app on the left, and the same project's data model, pages, app manifest or fields on the right.

Research and answers

@Human Answers

A cited-answers workspace: ask questions across the web and your own documents, organise threads in spaces, and keep confidential terms out of every answer.

  • 18 modules · Spaces, threads, sources, memory, source rules, confidential terms, audit log
  • A 100 KB custom application · Sandboxed, with a declared manifest of what it may write
  • Two named automations · Image fetch and document listing
@Human Answers app built on @Human
The application
@Human Answers in the @Human project builder: App manifest and sandbox rules
In the builder · App manifest and sandbox rules
Analytics and alerts

@Human Insight

Ask a question in plain language and get a chart, the metric behind it and an explanation, with rule-based alerts and subscriptions.

  • 11 modules · Data sources, datasets, metrics, questions, dashboards, alerts
  • Sync runs on record · Every data refresh is logged
  • Annotations · People add context to the numbers
@Human Insight app built on @Human
The application
@Human Insight in the @Human project builder: Data model, 11 related modules
In the builder · Data model, 11 related modules
Documents

Docs

Rich documents with comments, embedded charts and full version history, protected by security profiles that block risky shares.

  • 10 modules · Folders, documents, comments, versions, datasets
  • Security profiles · Confidential, internal or public, enforced as policy events
  • Every AI edit logged · AI requests are records, not side effects
Docs app built on @Human
The application
Docs in the @Human project builder: Module list with governance modules
In the builder · Module list with governance modules
Spreadsheets

Sheets

A collaborative spreadsheet with formulas, named and protected ranges, conditional formats, pivots, charts and named versions.

  • 16 modules · From workbook and cell to pivot table and formula function
  • Protected ranges · Respect project roles
  • Named versions · Restore any point in time
Sheets app built on @Human
The application
Sheets in the @Human project builder: 16-module spreadsheet engine
In the builder · 16-module spreadsheet engine
Screen capture

Guide Studio

Record a workflow once and turn it into a public step-by-step guide or a reproducible issue report, with sensitive fields blurred.

  • 6 modules · Captured projects, sessions, steps, issues, guides, files
  • Public guides by link · No login needed for readers
  • Issue reports · Steps to reproduce, attached automatically
Guide Studio app built on @Human
The application
Guide Studio in the @Human project builder: Page builder layout
In the builder · Page builder layout
Project specification

Project Requirements

Turn stakeholder interviews into a structured specification, then into a governed @Human project with policies, risks, modules and tests.

  • 7 modules · Intakes, questions, answers, stakeholders, requirements, issues, specifications
  • 15 requirement types · From objectives to compliance obligations
  • 13 build targets · Each requirement says what it becomes in @Human
Project Requirements app built on @Human
The application
Project Requirements in the @Human project builder: Field editor with real field definitions
In the builder · Field editor with real field definitions

Products built by Planet Crust on @Human. Builder views reflect each project's real modules and fields; app screens show sample content.

See @Human at work with your use cases

A 20-minute walkthrough. Bring a use case you're planning, and we'll show you how to build it in @Human as a compliance-first AI system, classified, logged and reported for EU AI Act compliance from day one.

Book @Human WalkthroughSee plans & pricing
  • 1Tokenomics and reusable code
  • 2Security and pre-testable code
  • 3Platform maturity
  • 4UX without compromise
  • 5Sovereignty by design

Early access

Reserve your @Human plan

Pick what you’d like to pay. Nothing is charged today: we’ll email you when your early access place opens.

Plan€10 a month
Due today€0.00

No payment today. @Human is in early access. Reserving your plan puts you on the list, and we will email you before anything is charged. You can change or cancel at any time.

See @Human at work with your use cases

A 20-minute walkthrough. Bring a use case, and we’ll show you how to build it in @Human as a compliance-first AI system.