AAtomarCopilot platform

Copilots · The platform

Build AI apps without handing control to the AI. The AI proposes. Your team decides.

For teams that run AI apps for customers or staff and need to know exactly who changed what, and why.

See a reviewed change
  1. Requested›
  2. Reviewed›
  3. Live
You are the reviewer
tier_config in stage test
Risk 5 of 100 · lowQuality gate passed
Raise max_tokens of the pro tier from 5000 to 6000. Free tier unchanged (1000).
- "max_tokens": 5000
+ "max_tokens": 6000
Nothing has changed yet. The request waits for a person.
This is a recorded demo request. Approving it here does not change the live app.

Every change to an app arrives as a request with a diff and a risk score. Someone on your team approves or rejects it with a reason, and only then does it reach the stage you picked. Every version is kept and can be rolled back. You build the app by describing it to the Architect, which writes those requests for you. Sign-up, roles, agent routing, data masking, processes and cost limits are already part of the platform, and a new app, a new stage or a release never needs a server deployment.

  • AI suggests, people decide.
  • Protected stages are locked in the database.
  • Personal data stays masked by default.

The results on this page come from the platform's own code or were recorded in the example app, and each block is labelled. Inputs were frozen on 1 Nov 2026, which is why the page works without an account and makes no AI calls. All people, practices, tariffs and invoices are made up.

Review and rollback

Every change is reviewed, kept and can be rolled back

Nothing the AI proposes goes live on its own. Each change shows exactly what it alters, gets a risk score and passes a quality gate. A person approves or rejects it and the reason is stored with it. Apps live inside the platform, so a new app, a new stage or a release is a reviewed configuration change. No server deployment is involved.

Review this change yourselfcomputed by the platform

  1. Requested›
  2. Reviewed›
  3. Live
You are the reviewer
tier_config in stage test
Risk 5 of 100 · lowQuality gate passed
Raise max_tokens of the pro tier from 5000 to 6000. Free tier unchanged (1000).
Quality gate: no broken references.
{
"id": "pro",
"label": "Pro",
"features": [
"chat_basic",
"claim_check",
"image_analysis"
],
- "max_tokens": 5000
+ "max_tokens": 6000
}
Nothing has changed yet. The request waits for a person.
This is a recorded demo request. Approving it here does not change the live app.

Restoring version 12 of example-app/testexamplecomputed by the platform

It writes back 3 configurations of this app and stage:
  • ↺ profile_schema
  • ↺ tier_config
  • ↺ app_config
It also restores 1 AI module. Rows of other apps and stages in the same backup stay as they are.
Added after the snapshot and kept for you to decide: custom_widgets
New app
One click in the App Registry. The platform serves it right away under its own address.
New stage
Add a stage to the registry. One test stage or ten, and each of them can be protected. No server, no pipeline.
Release
Move sections from one stage to the next inside the platform, with a review and a reason.
Rollback
Restore a version from the history or a snapshot. It takes seconds and happens inside the platform too.

Stages of the example appfrom the example app

dev
Development
open
›
test
Staging / Test
protected
›
pre_prod
Pre-production
protected
›
prod
Live
protected
+ as many as you need

Ten test stages are as fine as one. Protected stages can only be changed through one write path that asks for a reason and records the before and after. A database trigger blocks everything else. Staging compares two stages entry by entry and moves sections across, and a hotfix needs a written reason. To keep reviews short, related requests travel as one package, and an app can let the Architect write straight into its open development stage. Protected stages always need a review.

Backups

Snapshots
Numbered versions of an app's configuration with a reason, taken before a release or whenever you want.
Full backups
All configurations of all stages in one JSON file. Export it, keep it and import it into the same app or a new one.
Restore
One transaction for a whole stage, all or nothing. It runs through the governed write path, so the history records it.
Disaster recovery
Emergency rollback of an app's AI modules and configuration from the recovery console.

The Architect

How you work with the Architect

The Architect is a chat in the admin area. It knows the current configuration of your app and the rules of the platform. It does not only build what you ask for: it checks the app, compares parts that belong together, suggests what your app could do next and builds it for your review. It never changes anything on its own. Whatever it proposes becomes a change request that a person reviews.

  1. Step 1
    System check
    When you open it, the Architect looks through the app's configuration and suggests a few next steps.
  2. Step 2
    Your prompt
    You describe what you want in plain words.
  3. Step 3
    Answer and preview
    It replies with a plan and shows what would change: a field, a role, a process, a widget, a schedule.
  4. Step 4
    Change request
    Each change comes as a card with the area, a risk score and a short risk analysis. You submit it with one click, or several at once as a package.
  5. Step 5
    Review
    Someone checks the diff and the quality gate on the review board and approves or rejects it with a reason. A snapshot is taken before anything is applied.

It checks, suggests and builds for review: one recorded sessionfrom the example app

When the chat opens, the Architect reads the configuration of the app and stage and writes a health check.

Architect
Health check: yellow, action needed
  • 10 agents, routing rules complete
  • 4 business objects, claims and medical invoices with a hand-over to case handlers
  • 2 processes: claims triage (by hand) and storm precautions (daily 07:00)
  • A dashboard tile "metric" has no widget and stays empty
  • The admin dashboard has no KPIs of its own

Recorded in the example app on 2 Nov 2026, translated and shortened, no live AI calls. Findings are proposals that a person checks: the same check also reported invoice rules as missing that exist, and called all four objects handed over when two are. Those are left out or corrected here.

Built in one day

One insurance app. Built in one day.

Atomar builds AI-powered business applications. It connects data, automates workflows and brings customers and staff into the same process, with every change reviewed and versioned. The example: claims and invoices handled end to end, a mailbox for customers and a team inbox for case handlers, automated storm precautions and interactive apps. All of it configured on Atomar by talking to the Architect, with every change reviewed. Nine requests were rejected with a reason and fixed in the next one. That is exactly what the review is for.

Start
Empty template
  • Create the app in the App Registry
  • The master template is copied into every stage
  • Admin rights and a workspace are set up
  • 19 configurations per stage, 26 AI modules
50
change requests
41
approved
9
rejected with a reason
~6.5 h
configuration time
  1. 1Prompt
  2. 2Request with risk score
  3. 3Review
  4. 4Live in the chosen stage

What the day producedfrom the example app

Handling cases
  • Claims with photo, handed over to case handlers with consent, the status flows back to the customer
  • Medical invoices: the AI reads the PDF, tariff rules work out the refund, a case handler takes it from there
  • A team inbox for case handlers and a damage estimator for customers
Prevention and overview
  • Storm warning: a daily process asks a weather API and creates a task when a storm is coming
  • Cover check across insurance lines, contract cockpit with contracts, lines and claims
  • Mailbox for documents from the insurer
Interactive apps
  • Nutrient detective: a learning game with three modes, knowledge cards and a saved high score
  • Widgets are small apps in a sandbox, not only dashboard tiles

Also in the app: 5 KPIs, 4 widgets, 2 processes, 4 specialist agents with a model council, onboarding with legal consent, tiers with daily limits for widget AI and invoice checks.

Here are 25 of the 50 requests from 17 configuration areas, in order. We rewrote them without customer details. Prompts were not stored yet when this app was built, so what you see is what the Architect made of them. Today every prompt is kept in the audit log.from the example app

TimeAreaRequestRiskResult
0:00 happ_configApp name and tagline, metrics and objects switched on.5approved
0:01 happ_rolesThree roles: policyholder, family member, advisor (may invite).5approved
0:01 hprofile_schemaFour profile fields: postcode, household size, existing cover, contact preference.Rejected: A multi-select was typed as a single select. The next request fixes it.8rejected
0:03 hprofile_schemaProfile fields corrected (multi-select), template placeholders removed.18approved
0:03 hobject_registryObjects "insurance contract" and "claim".Rejected: AI field descriptions under a key the runtime never reads.10rejected
0:07 hobject_registryObjects corrected. Same content, right key.10approved
0:07 hprofile_schemaSurname, e-mail and postcode masked: the AI only sees placeholders.22approved
0:07 hrouting_capabilitiesFour specialist agents for the chat.Rejected: Sent back in review and resubmitted as a purely additive change.15rejected
0:14 hrouting_capabilitiesFour specialist agents: claims, cover & benefits, contract changes, emergencies.5approved
0:14 honboarding_legal_contentThree legal notices for onboarding (not advice, AI notice, privacy).8approved
0:14 hmetric_definitionsThree KPIs: open claims, next due date, cover check.10approved
1:24 hobject_registryPhoto field on the claim object, sent as a delta only.5approved
1:27 hprocessesProcess "claim triage" with 5 nodes.Rejected: Incomplete edges (a node without a successor).8rejected
1:29 hprocessesClaim triage with 6 nodes. It loads the claims, lets the AI check them for missing details and creates a task for each incomplete one.8approved
1:45 hrat_triggersKeywords on which the model council (several models) decides.Rejected: Would have replaced the existing word list instead of extending it.5rejected
2:08 hapi_connectorsWeather service connector that turns a postcode into coordinates.Rejected: Quality gate: writes profile fields that do not exist.5rejected
2:16 hapi_connectorsTwo connectors to a public weather service. No key needed and no writes to the profile.5approved
2:16 hprocessesProcess "storm precautions". Every day at 07:00 it checks the forecast and creates a task when a storm is coming.8approved
2:42 hobject_registryHand a claim over to case handlers with the customer's consent.8approved
3:25 hai_strategyRouting logic for all agents (which model, which context).42approved
5:41 hcustom_widgetsThree widgets: cover check, claim estimator (with AI), contract cockpit.15approved
next day 09:52claim_rulesBenefits catalogue for a made-up tariff: rules for medical fee scales, self-pay services and more.12approved
next day 09:52object_registryMedical invoice object: PDF, invoice check, result and hand-over to case handlers.12approved
next day 10:01object_registryMailbox for documents from the insurer, with a KPI for unread ones.6approved
next day 10:28custom_widgetsPrevention game for customers, "nutrient detective": three modes, knowledge cards, high score in the profile.8approved

Under the hood

One platform behind the whole application

The Architect configures connected building blocks on an existing platform. Screens are only one of them. Your app's data, interfaces, AI agents and workflows work together, with reviewed and versioned changes.

Processes and work inbox

Build business processes by pointing and clicking

Automate end to end, and keep people in the loop where you choose. A process connects data, API calls, AI steps and branches, and adds tasks for people wherever your workflow needs them. Without a task it runs on its own from start to finish. You draw it in the visual editor or describe it to the Architect, and it is reviewed like every other change. When a step needs a person, the process creates a task in that person's task list and waits. Once the task is done, it carries on with everything it has gathered so far. Cases handed over to a team land in the team inbox of the case handlers. A scheduler runs timed processes and a monitor shows every run.

Starts onSchedule (cron)Data change on an objectWebhook with a secretWidget eventManual

Claims triagefrom the example app

  1. 1
    trigger
    Start by hand
  2. 2
    object query
    Load all claims
  3. 3
    ai logic
    AI checks each open claim for missing details and urgency
  4. 4
    condition
    Any incomplete claims?
    yes: next step, no: done
  5. 5
    human task
    Complete the claim: {{item.title}}
    one task per incomplete claim
  6. 6
    end
    Triage done

Drawn from the example app's stored process configuration as of 1 Nov 2026, labels translated. It shows the structure, not a live run.

The task in the person's task listexample

Task from claims triageProcess waits
Complete the claim: water damage, kitchen
The photo and the date of the damage are missing. Please add both.
When it is ticked off, the process carries on from this step.

Team inbox: a claim from the customer to the case handlers and backfrom the example app

  1. CustomerHands the claim over and agrees. Only the shared fields go across.
  2. Case handlerTakes the case from the team inbox.
  3. Case handlerAsks the customer a question.
  4. CustomerAnswers, and the case goes back to the case handler.
  5. Case handlerCloses the case with a comment.
Shared with the case handlers: date of the damage, insurance line, description, photo. Everything else in the customer's claim stays with the customer.
Each status change shows up in the customer's own claim. The history of the case can only grow, nobody edits it afterwards.
Closing a handed-over case is reserved for people. We set that rule on purpose, and the database enforces it: only a signed-in person can take, answer or close a case, the AI and the processes cannot.

Storm precautions: the condition, evaluated by the process enginecomputed by the platform

  1. triggerDaily at 07:00 (cron 0 7 * * *)
  2. api_callPostcode to coordinates (weather service)
  3. api_callFetch the forecast for the next days
  4. conditionStorm threshold exceeded?
  5. human_taskTask: secure the basement, keep photos ready for a claim
  6. endDone
Math.max(...forecast.data.daily.wind_gusts_10m_max) > 70 || Math.max(...forecast.data.daily.precipitation_sum) > 30
Calm week
Gusts 22 / 31 / 28 km/h, rain 0 / 2.4 / 0.8 mm
No task
Storm front
Gusts 35 / 88 / 64 km/h, rain 4 / 37.5 / 12 mm
Task created

API connectors

Connect APIs visually

A connector is an endpoint with placeholders. In the editor you set the address, which values fill the placeholders, what comes back and a preview. A placeholder is filled from the process step before it, from fields you bind by hand, or from the profile field of the same name. Keys are stored on the server and never reach the browser. The storm process uses two of them, one after the other.

Postcode to coordinates
Step 2 of the storm process
Endpointfrom the example app
https://geocoding-api.open-meteo.com/v1/search?name={{plz}}&country=DE&count=1
Input: {{plz}} from the profile field plz, matched by name
Output: latitude and longitude of the first match
Address the engine sendscomputed by the platform
https://geocoding-api.open-meteo.com/v1/search?name=44139&country=DE&count=1
Two-day forecast
Step 3 of the storm process
Endpointfrom the example app
https://api.open-meteo.com/v1/forecast?latitude={{lat}}&longitude={{lon}}&daily=precipitation_sum,wind_gusts_10m_max&forecast_days=2&timezone=Europe/Berlin
Input: {{lat}} and {{lon}} from the answer of step 2
Output: daily rain and maximum gusts for two days
Address the engine sendscomputed by the platform
https://api.open-meteo.com/v1/forecast?latitude=51.51&longitude=7.47&daily=precipitation_sum,wind_gusts_10m_max&forecast_days=2&timezone=Europe/Berlin

The addresses are filled by the platform's own code for a made-up profile with the postcode 44139 and a frozen answer of the first service. A placeholder that cannot be filled stops the call instead of sending it half empty.

In the app

What your users get

Every app built on the platform comes with the same set of building blocks. The Architect decides which ones an app uses, what they are called and how they look. Sharing works across roles, so the same blocks fit very different teams. A trainer and their clients share exercises, notes and a coaching diary. In a company, a dispatcher hands jobs to technicians, and both see the notes from the site.

Onboarding
A short guided start with sign-in, role, profile and the legal notices the app needs.
Five steps in the example app
Dashboard
The start screen with tiles for KPIs, tasks, notes, quick actions and widgets. A KPI tile shows a value, takes a new entry, draws its history as bars or a line and changes icon and colour with the value. Widgets can be small tools or full-width apps.
Open claims, next due date, a traffic light for cover
Decision finder
Swipe separately, find your matches. The AI suggests options card by card, each person keeps or dismisses them, and the options you both liked become your matches. With several favourites left, the AI or the model council picks between the finalists.
Names, products, trips or activities, for yourself or together
Your own widgets
Users build personal widgets for their dashboard. On the basic tier they start from templates, on pro they describe the widget and the platform builds it, with a daily limit for new widgets and changes. Admins switch the builder on per app and stage.
Pro: 20 new widgets and 50 changes a day
Compass
The AI chat. It knows the user’s profile and objects, routes each question to the right agent and can read photos and documents.
"How do I report a scratch on my car?"
Tasks
A to-do list for the whole team. Tasks can be assigned to any member, shared with everyone whatever their role, or kept private. Processes can create them too.
A dispatcher assigns a repair job to a technician
Diary and notes
Entries are private or shared with the whole team, across roles. Each entry can be marked as relevant for the AI or kept out of it.
Coaching notes that trainer and client both read
Teams and invites
Users invite others with a link that carries a role. Who may invite whom is set per role, and everything shared is visible to the whole team.
A trainer invites a new client
User roles
Roles for customers and for staff, each with its own view and rights. Some can be picked by the user, others only by an admin.
Family and partner, trainer and client, dispatcher and technician
Consulting style
Users choose how the AI talks to them. The choice goes into every answer.
Short and clear, explained in detail, step by step, play it safe
AI model and mode
Users pick automatic routing, a single model or the model council, where several models answer and one sums up. Tiers decide what is available, and users can leave models out. An app can add its own model through an OpenAI-compatible endpoint.
Auto, Claude, GPT, Gemini, model council, your own model
Designs and wording
Each app has its own name, colours, fonts and logo, can offer several themes, and can change any text of the interface. The example app looks like its insurer's own product.
A brand theme, a high-contrast theme, "Share with technicians"
API connections
The Architect connects outside services from a prompt. Keys stay on the server and never reach the browser.
A weather service for storm warnings

Users and onboarding

Sign-up, roles and teams come from configuration

Onboarding is a list of steps in the app's configuration. The Architect writes it like everything else, and each user goes through it once per app and stage.

Onboarding of the example appfrom the example app

  1. 1 · auth
    Your account
    Sign in with Google
  2. 2 · roles
    Your role
    Only roles marked self-selectable
  3. 3 · names
    Your profile
    Fields come from the profile schema
  4. 4 · legal
    Notices
    Not advice, AI notice, privacy. Consent is recorded.
  5. 5 · team
    Join a team
    Invite link with a role

Roles and who may invite whomfrom the example app

RoleKindMay invite
Policyholdercustomerfamily members
Family membercustomernobody
Advisorcustomerpolicyholders, family members
Case handlerstaffnobody, assigned by an admin

Access per app and stage

openanyone signed in can register
inviteonly with an invite link (expiry, max uses, revocable)
privateexisting users and admins only

Privacy by default

What the model sees and what an admin sees

Fields marked as masked in the profile schema never reach the model as real values. An agent can get a documented exception for a single field. Admins see the same data masked until someone with the right permission unmasks it and gives a reason.

The user writesexample

Hi, this is Max Muster from 44139 (max.muster@example.org). Is my home contents cover enough for a household of 3?

The model receivescomputed by the platform

Hi, this is Max [MASKED_LASTNAME] from [MASKED_PLZ] ([MASKED_EMAIL]). Is my home contents cover enough for a household of 3?

Profile context for the modelcomputed by the platform

PROFILKONTEXT
- Aktuelle Rolle des Users: Policyholder (System-ID: policyholder)

- First name: Max
- Surname: [MASKED_LASTNAME]
- E-mail: [MASKED_EMAIL]
- Postcode: [MASKED_PLZ] (KI-Hinweis: Postcode of residence, relevant for regional services.)
- Household size: 3

The headings of this block are German because the platform's prompts are. The values come from the app.

The answer, translated back for the usercomputed by the platform

Hi Max, for a household of 3 in [MASKED_PLZ] it is worth checking the sum insured. I will send the details to [MASKED_EMAIL].

Hi Max, for a household of 3 in 44139 it is worth checking the sum insured. I will send the details to max.muster@example.org.

The answer itself is a fixed example. Masking and unmasking run the chat's own code.

The admin user listexample

NameE-mailRoleTier
PolicyholderPro
Family memberFree

Only global admins can unmask. They have to give a written reason, the action is recorded in the audit log, and the data is masked again after 5 minutes.

Emergency keywords are handled before any AIcomputed by the platform

“There is a fire in my kitchen!”
Immediate answer without AI: ⚠️ Call the emergency number 112 now.
“Does my policy cover water damage?”
No emergency, so the question goes on to routing.

Chat and agents

Each question goes to the agent that should answer it

A router picks a specialist agent for every question. Each agent has its own prompt, persona, model and data rights. Only the reimbursement agent sees medical invoices, for example. Models from several providers can be switched on or off per app and stage. Sensitive questions can go to a council of models. It only runs on configured trigger words or when a user picks it, because several models take longer and cost more, and every call counts against the daily limit of the user's tier. Each platform function, from the Architect to the router, can use its own model, including your own through an OpenAI-compatible endpoint.

Agents of the example appfrom the example app

AgentPurposeModelMay see
general_supportDefaultClaudeselected profile fields, contracts
claimsReport a claim, checklists per lineClaudeclaims, contracts
emergencyAcute emergenciesClaudeclaims
coverWhat am I covered for?Geminicontracts
contract_changesMoving, changesClaudecontracts, postcode (unmasked for this agent only)
medical_invoicesInvoices, reimbursementClaudemedical invoices, contracts
image_analysisPhotos and documentsClaudenothing extra

Inside one agent: what it knows and what it may seefrom the example app

Claims assistant
Model: Claude, then Gemini, then GPT if one fails
Its own instructions, excerpt
  • Never promise payments, settlements or contract changes. Only the insurer decides.
  • Ask only for what the next step needs. Never ask for diagnoses, policy numbers, bank details or ID in the chat.
  • If someone is in danger, the first answer is the emergency number 112.
  • Then: insurance line and date, only the details that line needs, a summary to report it.
May see
claims, contracts, first name, preferred consulting style
Never sees
diary, other profile fields, medical invoices, unmasked personal data
The data rights are part of the agent's configuration and are applied on the server before the model is called.

Routed in the live testfrom the example app

“I scraped the car while parking. How do I report it?”
Went to claims on Claude
Postcode: masked
“Does home contents cover a stolen bike?”
Went to cover on Gemini
Postcode: masked
“I moved, please change my address”
Went to contract_changes on Claude
Postcode: visible, a documented exception for this agent

Reviewed knowledge refinement

The model council's answers can be distilled into new knowledge or new routing rules. The result becomes a change request on the review board, never a direct write. If you choose, it also lands as memory candidates, and a candidate is only used once a person approves it.

Rules, not guesses

Invoice check: the AI reads, the rules decide

In the app, a model only reads the positions off the invoice PDF. Rules from the configuration decide whether and how much is paid back, and every reduction shows how it was calculated. Here the reading is frozen and the rules run live. The example app is German, so rules and results appear the way its users see them.

The tariff's rules, where the first match appliesfrom the example app

RuleMatchesPaid back
Optional self-pay services (IGeL)"igel", "auf wunsch", "kosmetisch"not covered
Lab services (GOÄ section M)GOÄ · 3500 to 4787100 % up to factor 1.15
Technical services (GOÄ sections E, O)GOÄ · 500 to 569, 5000 to 5855100 % up to factor 1.8
Medical services (GOÄ)GOÄ100 % up to factor 2.3
Non-medical practitionersGebüHnot covered
Glasses and lenses"brille", "kontaktlinse"80 %, at most €150.00 per invoice
Everything within the tariff · General practicecomputed by the platform
Invoice PDF
1Beratung, auch telefonischÄrztliche Leistungen (GOÄ): vollständig erstattungsfähig (Faktor 2,3 im Rahmen).€10.72€10.72paid
5Symptombezogene UntersuchungÄrztliche Leistungen (GOÄ): vollständig erstattungsfähig (Faktor 2,3 im Rahmen).€10.72€10.72paid
250Blutentnahme aus der VeneÄrztliche Leistungen (GOÄ): vollständig erstattungsfähig (Faktor 2,3 im Rahmen).€5.36€5.36paid
3550Blutbild (Laborleistung)Laborleistungen (GOÄ Abschnitt M): vollständig erstattungsfähig (Faktor 1,15 im Rahmen).€4.02€4.02paid
Invoice €30.82, paid back €30.82, own share €0.00
Billed above the tariff factor · Orthopaedicscomputed by the platform
Invoice PDF
1BeratungAbgerechnet mit Faktor 3,5. Der Tarif erstattet Ärztliche Leistungen (GOÄ) bis Faktor 2,3: 16,32 € × 2,3 / 3,5 = 10,72 €.€16.32€10.72reduced
7Vollständige Untersuchung BewegungsorganeAbgerechnet mit Faktor 3,5. Der Tarif erstattet Ärztliche Leistungen (GOÄ) bis Faktor 2,3: 32,64 € × 2,3 / 3,5 = 21,45 €.€32.64€21.45reduced
5135Röntgen Brustorgane, ÜbersichtAbgerechnet mit Faktor 2,5. Der Tarif erstattet Technische Leistungen (GOÄ Abschnitte E, O) bis Faktor 1,8: 40,80 € × 1,8 / 2,5 = 29,38 €.€40.80€29.38reduced
3550Blutbild (Laborleistung)Laborleistungen (GOÄ Abschnitt M): vollständig erstattungsfähig (Faktor 1,15 im Rahmen).€4.02€4.02paid
Invoice €93.78, paid back €65.57, own share €28.21
Not covered · Non-medical practitionercomputed by the platform
Invoice PDF
1Eingehende UntersuchungBehandlungen durch Heilpraktiker sind im Tarif nicht versichert.€20.50€0.00not covered
20.1AkupunkturBehandlungen durch Heilpraktiker sind im Tarif nicht versichert.€45.00€0.00not covered
25.4SchröpfenBehandlungen durch Heilpraktiker sind im Tarif nicht versichert.€18.00€0.00not covered
Invoice €83.50, paid back €0.00, own share €83.50
Mixed · Dermatologycomputed by the platform
Invoice PDF
1BeratungÄrztliche Leistungen (GOÄ): vollständig erstattungsfähig (Faktor 2,3 im Rahmen).€10.72€10.72paid
5Symptombezogene UntersuchungAbgerechnet mit Faktor 3,5. Der Tarif erstattet Ärztliche Leistungen (GOÄ) bis Faktor 2,3: 16,32 € × 2,3 / 3,5 = 10,72 €.€16.32€10.72reduced
A750Hautkrebs-Screening auf Wunsch (IGeL)Individuelle Gesundheitsleistungen ohne medizinische Notwendigkeit sind im Tarif nicht versichert.€35.00€0.00not covered
Invoice €62.04, paid back €21.44, own share €40.60
Capped amount · Opticiancomputed by the platform
Invoice PDF
·Brillengläser Gleitsicht, 2 StückErstattungssatz 80 % von 380,00 € = 304,00 €. Höchstbetrag für Sehhilfen: 150,00 € je Rechnung, davon noch 150,00 € offen.€380.00€150.00reduced
·Brillenfassung TitanErstattungssatz 80 % von 120,00 € = 96,00 €. Höchstbetrag für Sehhilfen (150,00 € je Rechnung) ist mit den vorigen Positionen ausgeschöpft.€120.00€0.00not covered
Invoice €500.00, paid back €150.00, own share €350.00

Widgets

Mini-apps in a sandbox, also built by prompt

More than dashboard tiles: interactive mini-apps with their own interface, animation, keyboard controls and sound. They run on their own or connect to the app's data and to AI on the server through declared inputs, events and actions. Widgets run in a sealed sandbox. They can't touch the page or its cookies, they may load libraries from four approved code CDNs and reach no other server, and they only exchange messages with the app through declared inputs and events. A widget can call an AI agent on the server, and users can build their own by prompt within the limits of their tier. Every widget below runs live in that same sandbox.

Insurance, connected to the app. This widget gets the customer's policy from the profile through declared inputs and reports back through declared events. The panel next to it shows what the platform passed in and every event the app received after validation. Pick a scenario and start a claim.

Widget lädt…
Inputs from the profile
  • customer_nameSam Keller
  • policy_tierComfort
  • deductible_eur150
  • sum_insured_eur60000
  • claims_this_year1
Events the app received

Nothing yet. Use the widget and its events appear here.

These public demos run without an account and without AI calls. Switching widgets resets the demo.

Build by prompt, inspect and refine in the editor

  • Edit HTML, CSS and JavaScript
  • Define input schemas and data bindings
  • Configure output events and action bindings
  • Watch the result in a live sandbox with a bridge monitor
  • Undo, redo and version history

Included

What every app gets without a single prompt

Governance

  • Every change is a request with a risk score, reviewed by a human (human-in-the-loop, per app)
  • Quality gate before approval: broken references, fields that don't exist
  • Protected stages enforced in the database: one write path, with a reason and a before/after record
  • Versioning: change history, numbered snapshots, export/import, one-click restore, disaster recovery
  • Any number of stages, ten test stages if you like, and each can be protected. Staging compares and moves sections, hotfixes need a reason
  • No server deployments: apps, stages and releases are configuration inside the platform

Users & access

  • Onboarding from configuration: steps, roles, legal notices with consent
  • Roles for customers and staff, sub-users and invite rights, teams
  • Access per app and stage: open, invite-only or private
  • Admin user management with masked personal data. Unmasking needs a reason and is logged

AI

  • Agent routing: each question goes to a specialist agent with its own prompt, model and data rights
  • Claude, GPT and Gemini, switched on or off per app and stage, with fallback
  • Your own models through any OpenAI-compatible endpoint (Azure OpenAI, Mistral, self-hosted). The key stays on the server
  • A model per platform function: the Architect, the router or the model council judge can each use a different one
  • Masking before the model, emergency keywords before any AI, model council for sensitive questions
  • AI calls of your users are counted, with daily limits for widget AI and invoice checks, and per-tier limits you can switch on

Automation & data

  • Process engine (BPM) with a visual editor, human tasks and resume
  • Triggers for schedules, data changes, webhooks and widget events, plus a task scheduler and a process monitor
  • API connectors whose secrets never reach the browser
  • Data kept apart per app and stage, export and erase on request, retention periods

One platform, several apps

Pregnancy companion (example)
Profile, daily tasks, notes a partner can share, a chat that knows the profile
Example app, used to develop the platform
Customer copilot (example)
Insurance customers: contracts, claims, invoices, inbox
Shown on this page

For enterprise

Built for teams that need an audit trail

Atomar keeps a record of every proposed change and every decision about it. These parts are built and running today.

Every decision on record
Each prompt to the Architect, each change request, approval and rejection is stored with its reason, the before and after, who decided and when. The log can be added to, never edited.
Company sign-in with Microsoft Entra ID
Staff sign in with their Microsoft Entra ID account. Each company is mapped to its app, stage and role. A company without a mapping gets no access.
Locked stages
Protected stages accept one write path, with a reason. A database trigger blocks everything else.
Masked by default
Personal data is masked before it reaches a model. Unmasking it in the admin area needs a reason and is logged.
Any version back
Numbered snapshots of every app and stage. A restore writes the old version back and is itself a new entry.
Your region, your models
Server and database in Frankfurt (EU) by default. Your own models through an OpenAI-compatible endpoint, with the key kept on the server.

Available on request: SAML and other identity providers such as Okta or Google Workspace and apps on a domain of their own.

Limits

What the platform doesn't do

  • The platform runs in the cloud. By default the server and the database sit in Frankfurt (EU), and the region is a setting. Masked text goes to the AI providers you switch on (Anthropic, OpenAI, Google). It is not local-first like the developer tools.
  • Sign-in is with Google, and for companies with Microsoft Entra ID. SAML and other identity providers such as Okta or Google Workspace are available on request.
  • Every app carries its own name, logo, colours, themes and wording. It runs under the platform address, and a domain of its own is available on request.
  • Inputs on this page were frozen on the snapshot date. The results are computed by the platform's code when the page is built.

Under the hood, data is kept apart per app and stage, the database uses row-level security, and every API route that touches data checks who is asking. A test fails if a new route forgets to. Users can export or erase their data, and more than 7,600 automated tests run before every release.

Next step

See it for yourself

The example apps run on the same platform as this page. For a setup with your own sign-in, domain or models, write to us.