FAQ
Questions, answered plainly
Everything here is stated the same way across the site: no marketing answer on one page and a different one on another.
The product
- What is Sapilon?
- Sapilon is an AI-first software system that governs AI to modernize legacy systems and graduate AI prototypes into production-ready, AWS-native software. More →
- Who is Sapilon for?
- Teams with a legacy system that needs modernizing, and teams whose AI-built prototype (Lovable, Replit, Bolt, Base44, Google AI Studio, v0) has to become real production software. Sapilon sits between AI coding tools and no-code platforms, and is neither: it is a software factory and modernization engine. More →
- What can Sapilon import?
- Legacy source code, database schemas, documents and media, even screenshots, plus prototypes exported from AI app builders. These inputs seed the bootstrap that rebuilds your system on an AI-safe architecture. More →
- How much of a legacy app can Sapilon rebuild automatically?
- We don't quote a percentage, because a percentage of someone else's system tells you nothing about yours. Sapilon inspects your system first and estimates up front how much it can recreate. Whatever your old code, database schema, and screens describe can be recreated; what only ever lived in someone's head is flagged for you to decide. A working app rebuilt in days from your old system's own code, schema, and screens, ~10× faster and ~10× cheaper than a traditional rewrite. More →
- Can Sapilon move the data from my old system?
- Yes. Point Sapilon at an export, a database dump or a read-only connection; your project’s agent proposes how each old table maps onto the new schema, and you confirm every decision. The migration is rehearsed on your Rehearsal Server with a reconciliation report (matching totals, orphaned records, every code and what it became) and only runs on Live once a rehearsal has come back clean. More →
- What happens after go-live?
- The lifecycle continues: versioning, upgrade-aware diffs, monitoring, and backups keep the software healthy for years. Modernization is the entry point to lifecycle ownership, not a one-shot generation. More →
How it works
- What are the four stages?
- Design, Build, Rehearsal, and Live. Design proposes the architecture and builds the new frontend against mocked data; Build wires up backend, database, and APIs on your Build Server; Rehearsal is a full pre-production dress rehearsal on your Rehearsal Server; Live is real users on your Live Server. Each stage is gated, governed, and reversible. More →
- Is the AI safe to trust?
- Every AI action is logged, diffable, and reversible. Explicit ownership zones (//!AUTO, //!SAFE, //!DEV) define what the AI may change and what stays under human control, and automated code review runs on generated changes. More →
- What if the AI hits a decision it should not make alone?
- The governed gate stops the agent before it acts. You forward the decision to an expertise area, a verified human specialist reviews it and returns a verdict with reasoning, and your agent resumes. An approval clears the gate once, for exactly the reviewed action. More →
Ownership & trust
- Do I own the code Sapilon produces?
- Yes. Sapilon produces plain Git repositories on an open-source web and api platform, running on standard AWS services. There is no proprietary runtime and no vendor lock-in. You can export the code and leave at any time. More →
- Is Sapilon open source?
- The core is. The web and api platform every Sapilon project is built on is open source, so the foundation of your software is code you can read, fork, and run without Sapilon. The governed agent, the servers, and the experts are the paid service around it. More →
- Where does my software run?
- On production AWS infrastructure Sapilon provisions and runs for your project, across separate Build, Rehearsal, and Live Server environments with cost visibility built in. Enterprise plans can deploy into your own AWS account on request. More →
- Is my code or data used to train AI models?
- No. Sapilon does not train models on customer content, and none of your content is shared with the model provider: all AI processing runs on Claude through Amazon Bedrock in EU AWS regions, where Bedrock does not store prompts or answers and does not use them for training. More →
- Is my data shared with AI providers?
- No. Every prompt, upload, line of generated code and AI answer is processed by Claude on Amazon Bedrock in EU AWS regions. None of it is shared with the model provider or used to train any model. Sapilon runs AI in the EU under the GDPR, with AWS as the processor and no other party in the chain. More →
Pricing
- Does Sapilon have a subscription?
- No. Sapilon uses a prepaid wallet, pay-as-you-go, with no subscription and no seats. You fund a wallet and only pay for what you use; the balance cannot go negative. More →
- What do I pay for?
- Three things, all drawn from the same wallet: AI work (billed in points, one published fixed-price unit), AWS hosting (estimated before you go live, measured after, priced near cost), and expert time (published, all-inclusive prices sized to the job). More →
- What is a point?
- A point is Sapilon’s fixed-price AI usage unit with one published rate, so every AI interaction has a predictable, whole-number cost instead of raw token pricing. More →
- How is a modernization engagement priced?
- As a scoped engagement: expert time plus AI and AWS drawdown from your wallet. Every legacy system is different, so the bootstrap is scoped up front rather than sold at a fixed price. More →
Getting started
- When can I use Sapilon?
- Sapilon becomes publicly available on 15 November 2026, and its open-source core goes public the same day. Until then you can reach us at we@sapilon.com to talk about your software. More →
Something we didn't cover?
Ask us directly at we@sapilon.com. A person reads it.