Our AI builds your software and takes it live.

For teams with no developers to spare.

Already have code?

Connect your repository.

30 min with our founder. Live, no slides.

• Security Gate
• Quality Assurance
• Test
• Approval
• Production

Our commercial clients used to send us their underwriting data on PDF renewal forms, and we keyed it into our systems by hand. Today every client automatically receives an email with their own individual link, including reminders, and the data goes straight into our systems. If a policy needs to be endorsed, the follow-on process starts automatically. A dashboard shows us at any time which renewals are still outstanding. What used to take weeks is now done in days. All built with Nuclicore, without an in-house development team.

Using the Nuclicore platform, it took us six weeks from kick-off to a finished Customer Portal. The same version now runs on two different domains and databases. Since then, we have also built our Partner Portal, Claims Management System and Purchase Flow Builder with Nuclicore. We use Nuclicore for both new business and migration projects in our existing business.

As a travel MGA, we win or lose the customer relationship at the point of claim. We have grown considerably in recent years, and as we write more travel cover, our claims volumes rise too. With Nuclicore we continually refine and extend our AI-supported claims handling, and every step makes it more valuable to us.

Automated governance before your software goes live

Five steps stand between a new version and your customers. Our AI team does the work of a DevOps, security and QA team. You make the decision.

SecOps agent

Code and packages are scanned before the build. Critical and high findings stop the release, as does a failed scan.

A separate agent tests each version against its acceptance criteria and reports what passed, failed or was not run.

DevOps and DB agents

Each version first runs in its own Test environment, with its own database and secrets in a vault, for your review.

Human or automation

No release reaches Production without approval by an authorised person, logged in the audit trail. If you prefer, releases go live automatically, or at a time you set.

DevOps agent

Revert to an earlier release in minutes. After go-live, the agent monitors the app and reports the cause of incidents.

Two ways to build. One way to go live.

Build with our AI team, or keep building the way you do today. Either way, the governance is the same: every version takes the same five steps to Production.

For teams whose developers are busy with something else

• Describe what you need, or bring a prototype you already have.
• Our agents plan, build and test it. You approve the plan and the result.
• Short on time? Our team builds it together with you.

For teams with developers and a way of working they like

• Keep Claude Code, Cursor or any IDE, and your own AI subscription.
• Connect your repository once. Every push arrives automatically.
• Any JavaScript or modern framework. The code stays yours.
• Our AI agents can step in and build at any time.

You can assemble this yourself. Here is what it takes.

An AI coding tool writes the code. Getting that code to your customers, safely and every time, takes seven more tools and someone to run them.

What production needs

Assemble it yourself

Somewhere to run it

Choose a provider and set up three environments.

Preview, Test and Production from the first push, hosted in the EU.

A database for each environment

Database service

Create three, and keep their structure in step.

Each environment has its own. The DB agent applies every change.

Secrets kept out of the code

Set it up and fill it for every environment.

In a vault, set per environment, never in the repository.

A security check that can stop a release

Wire it into the pipeline and decide what blocks.

Security Gate before every build. A failed scan stops the release too.

Tests before go-live

Test tooling

Write the tests and keep them current.

The QA agent tests against acceptance criteria and reports the result.

Approval, release and a way back

Script the steps, the approval and the revert.

Approval by role or automatic, revert in minutes, all in one audit trail.

Knowing when something breaks

Set up alerts and read the logs.

The agent monitors the app and reports the cause of incidents.

Someone to run all of it

A DevOps engineer, or a developer doing it on the side.

Our AI team. Your developers stay on the product.

Room for your own setup

Unlimited. Every part is yours to design.

Add your own services and your own pipeline steps.

7 tools and a hire

Six agents do the work. You make the decisions.

Each agent does the job of a specialist you would otherwise hire. You describe what you need, approve the plan and approve the release.

You describe

In plain language, with a prototype or with an existing repository.

Our AI builds

Task by task. Or your developers build in their own tools.

We take it live

Every version, whoever built it. You approve.

PM agent

Captures what you need and asks back when the request is unclear.

Turns it into tasks with acceptance criteria.

Nothing is built until you approve the plan.

Developer agent

Writes the code, task by task, in a repository you own.

DB agent

Designs the database and writes every change to it.

Or your developers, in their own development environment

Your team plans and builds this part itself. The repository stays connected.

SecOps agent

Scans code and packages before every build. Critical and high findings stop the release.

QA agent

Tests each version against its acceptance criteria and reports the result.

DevOps agent

Deploys to Test, releases to Production after approval and monitors the live application.

You choose the AI models. Your workspace content is not used to train them.

If you leave, you take everything with you.

The code, the application and the data are yours. None of them needs Nuclicore to keep running.

The code

Built with our AI team: export it to GitHub at any time, or have every release copied into your own GitLab. Built with your own tools: it stays in your repository, and Nuclicore works on a synced copy.

The application

Standard containers and a Postgres database, nothing proprietary underneath. Any hosting provider can run them, with or without us.

The data

Export your database yourself, at any time. You do not need to ask us, and you do not need a reason.

Your first application, live in four weeks.

One application, with a fixed scope, a fixed timeline and a fixed price. Built by our AI team or by your developers: the four weeks are the same.

Scope

You pick one process, such as a customer portal or a renewal process. We agree what success means.

First version

Our AI team builds it, or your developers do in their own tools. Your team clicks through a working version.

Integration

It is connected to your existing systems and checked in Test.

Go-live

Tested, checked, approved by you, live.

From you: one person who knows the process, and your IT in week 3.

Every pilot has a fixed price. You get the written quote after the demo.

Who you work with

Dr. Eberhard Riesenkampff

Founder & Managing Director

Runs your demo and scopes your pilot with you.

Anel Bejtovic

Chief Technology Officer

Owns the Security Gate and answers the questions of your IT and your auditor.

Dr. Christoph Schaller

Product Director

Turns your workflow into tasks and keeps the pilot on track.

Frequently asked questions

What buyers, IT and security teams ask before a pilot.

We already use Claude Code or Cursor. Why do we need Nuclicore?

Claude Code and Cursor write the code. They do not take it live. Between a finished version and your customers stand hosting, a database, secrets, a security scan, tests, an approval and monitoring. Nuclicore does that part and adds the governance: every version passes the Security Gate and Quality Assurance, runs in Test and goes to Production once you approve. Your developers keep their tools and their repository stays connected. If you have no developers to spare, our AI team builds the software, and it takes the same five steps. A prototype from Lovable, Replit or Bolt can be brought in the same way.

We already have an application. How fast can it be live?

Your developers connect the repository, and Test and Production are set up with a database and a vault. If the application needs no changes, the first release can be live the same day. In practice your side sets the pace: scope, integrations and sign-off. That is why the pilot plans four weeks.

What kind of software do customers build with Nuclicore?

The things that sit around a core system and never make it out of the IT backlog: customer portals with self-service and status tracking, renewal processes that replace PDF forms and re-keying, partner and broker portals, claims and service-request intake, onboarding and KYC flows, commission statements, internal tools that retire a spreadsheet. Broker Collective runs a customer portal, an IAM portal, a partner portal, claims management and a purchase flow builder. TAS runs automated renewals for its B2B products. The pattern is always the same: one workflow, real roles and rules, integrated into the system of record, in production in weeks.

Who on our side works with Nuclicore, and how much time does it take?

One person who knows the workflow and can decide. No developer needed. While an application is being built, that person describes what is needed, reviews the tasks and approves each release. Your IT joins where your systems are connected. Once the application is live, the platform runs it: hosting, security scans, patches and backups. Your effort then depends on how often you change the application. If you change nothing, it is minimal. On request, a Nuclicore advisor works alongside your team.

How does it connect to our core systems?

Through the interfaces your systems already have: REST and SOAP APIs, webhooks, event streams, SFTP, batch files and middleware. That covers policy administration and broker management systems, CRM, document management, and the APIs and exports of your ERP. If a system has no stable interface or no test environment, the integration becomes its own workstream, and we surface that in week 1 so delivery stays predictable. Common building blocks are built in: e-signature to eIDAS, IBAN verification, e-invoicing with ZUGFeRD and Factur-X, OCR and text extraction, PDF generation, payments with Stripe and email with Mailgun. Each integration has its own monthly budget and limit.

How is security checked?

On every release, before the build. Access to the workspace is governed by role-based access control with Owner, Admin, Billing Admin and Developer roles, and sign in runs through Microsoft, Google, GitHub or a one-time code by email. Data is encrypted in transit and at rest. Every release passes the Security Gate: static code analysis with Semgrep and dependency scanning with Trivy, where critical and high findings stop the release and safe dependency upgrades are applied and committed automatically. ZAP scans run nightly against the running application. The workspace audit trail records approvals, releases and changes with the value before and after, so your auditor reads the record instead of taking our word for it. When our AI team builds, every task is one commit. Nuclicore runs in production at licensed insurers and regulated firms. If you fall under DORA, or your risk carrier passes it down by contract, the security pack includes the Article 30 contract addendum and the data for your register of information.

Are you certified?

Nuclicore follows the ISO 27001 and SOC 2 control frameworks. On request you receive a security pack with an architecture description, a penetration test summary, the subprocessor list, the DPA template and the DORA contract addendum. We do not currently hold an ISO 27001 certificate or a SOC 2 report. What your auditor can verify directly is more useful than a logo: the Security Gate on every release, a Test environment, a logged approval and an audit trail that records changes with the value before and after.

Which AI models are used, and is our data used to train them?

You choose: automatic, one model for all agents, or a different model per agent role. Nuclicore offers the frontier models and the cost-efficient models of the large providers, and the catalogue changes as new models ship, so nothing in your application is tied to one vendor. Your workspace content, including your code and your data, is not used to train models. If your developers build in their own tools, they use their own AI subscription.

Who responds when our application is down?

The DevOps agent monitors every live application and reports the cause of an incident. Enterprise plans include 24/7 support from our team.

Do you commit to service levels in writing?

Yes. Enterprise plans include service level agreements (SLAs). Ask for the terms in your demo.

Who owns the code created with Nuclicore?

You do. Completely. Software our AI team builds is standard source code that belongs to you, and you can export it to GitHub at any time. Code your developers write stays in your repository; Nuclicore works on a synced copy. If you leave us, you take the code, the application and the data with you.

What happens to our data if we leave?

You export your database yourself, at any time. Your code is in your own repository or can be exported to GitHub, and the application runs in standard containers on any hosting provider.

Can one application run under several brands or domains?

Yes. Deployment labels serve the same release on separate branded domains, each with its own secrets, logos and its own database schema. Broker Collective runs one portal for two underwriting brands this way. Labels are an Enterprise feature; where a policy requires it, a label can also get a separate database or single-tenant infrastructure.

How do you know the generated code even runs?

A task is handed over once the application installs, builds and starts, not when the code was written. A failed dependency install gets one automatic repair attempt, a failed build or a runtime failure gets up to ten, and each attempt reads the real error output, changes the code and runs the check again. The same error twice in a row stops the repair, and the task is marked failed with the error rather than handed over as done. If a decision from you is needed, the task pauses and asks in the thread. Preview is only reported ready once the application answers through its own frontend and its own API.

How do I keep credit and integration costs under control?

Each integration has its own monthly budget with a hard or soft limit and email alerts. Credits are visible per app and per subscription. Apps stay live if you run out; you top up or upgrade at any time, and any overage is billed at the pay-as-you-go rate.

Ready to take it live?

Bring one process or an application you already have. After the demo you get a pilot scope and a fixed-price quote in writing.

Or start free in your browser

Examples of what you can build on Nuclicore.

Real software, each with its own backend, a managed database and a release pipeline, all owned by you. Start from any of these or import what you already have.

How the work is organised

Every request becomes a task with acceptance criteria. You approve it, the team builds it, you review it. Each completed task is one clean commit in your repository, so the git history reads like a project log.

• Edit any task in chat before it is built
• Auto-accept or manual review per task
• One task, one commit, one person accountable

Handed over when it runs, not when it is written.

Before a task is handed over, the application has to install, build and start. When one of those fails, the platform reads the real error output, changes the code and runs the check again.

Dependency installation fails

One automatic repair attempt

Build fails, type check or bundle

Up to ten automatic repair attempts

Application fails at runtime

Up to ten automatic repair attempts

The same error twice in a row

Repair stops, the task is marked failed with the error

One release. Every brand's own domain.

Run one application for every brand, subsidiary or market. You approve one release, not one per brand.

• A new brand is a new deployment label: domain, design, secrets. No second codebase.
• Each brand's data sits in its own database schema. Where a policy requires it, a brand can get a separate database or its own infrastructure.

Broker Collective runs one customer portal for two underwriting brands this way.

MGAs and brokers with several underwriting brands, groups with several subsidiaries, and anyone who would otherwise copy the code for a second market.

• Hosted in the EU
• DPA with every account
• Public sub-processor list
• Your content trains no models