In Development · Seeking Design Partners

By Innershell

Integration
that Writes
Itself.

The Magic Lizard is an AI-native enterprise service bus for healthcare — currently in active development. The architecture is proven, the vision is clear, and we're looking for a small number of healthcare teams to build it with us.

The Method

No More
Drag-and-Drop.

Traditional integration engines demand complex visual canvas mapping. The Magic Lizard inverts that model — you describe what you need, the AI writes and validates the code.

Describe Intent

Paste a sample payload and type what transformation you need in plain language. No schemas required to get started.

AI Generates Code

The LLM orchestrator produces a TypeScript transform plus a full assertion suite — including edge cases like missing fields and extreme values.

Sandbox Verifies

An ephemeral Deno subprocess runs all tests in isolation. Failures feed back to the LLM for automatic repair — no human intervention needed.

Deploy Live

Once all tests pass, one click pushes the verified artifact to the Go runtime. Zero downtime. Every message logged to the immutable WAL audit trail.

The Self-Healing Loop

Fail Forward,
Auto-Recover.

The AI execution loop never leaves you with broken code. Every failed test is a structured trace that becomes the next prompt — closing the loop automatically.

User Intent
Prompt + sample input + expected output schema
LLM Generates
TypeScript transform + JSON assertion suite
Deno Sandbox
Isolated subprocess runs deno test with strict flags
Go Runtime
WAL-logged, concurrent, zero-dependency binary
✓ All Tests Pass

The "Deploy" action unlocks. The verified artifact is pushed to the Go runtime with no downtime.

⟳ Tests Fail → Auto-Heal

The full stack trace is sent back to the LLM as a structured prompt. The engine iterates — up to N rounds — before surfacing for human review.

Capabilities

Built for
Healthcare Reality.

Clinical data is messy. HL7 segments go missing. Patient IDs change shape across systems. The Magic Lizard was designed for these conditions from day one.

AI Core

Intent-Driven Mapping

Describe transformations in plain English. The LLM orchestrator converts intent to production TypeScript with structured output guarantees — no ambiguity, no hand-coding.

Safety

Sandboxed Execution

Every transform runs in an isolated Deno subprocess with tightly scoped OS capabilities. No transform can reach outside its defined network or file permissions.

Compliance

Immutable Audit Trail

SQLite WAL mode guarantees every raw payload is durably written before execution. Point-in-time recovery and full lineage inspection for every message, always.

Developer UX

Monaco Code Preview

The AI-generated TypeScript surfaces in a live Monaco editor. Review, tweak, or override any generated code before testing — full developer control, zero ceremony.

Edge Cases

Synthetic Edge-Case Tests

Beyond user-provided examples, the engine auto-generates 3+ adversarial edge cases: missing optional keys, special characters, maximum-length fields, and malformed segments.

Operations

Real-Time Log Viewer

SSE-streamed ingestion activity flows directly into a scannable table. Inspect exact input/output payloads of any historical transaction without leaving the dashboard.

Under the Hood

Two Environments,
One Pipeline.

Designtime and runtime are fully decoupled. Build and validate in the Next.js studio; execute at high throughput in the Go daemon.

Designtime

Intent Playground

Next.js · Monaco Editor · Tailwind CSS

Designtime

LLM Orchestration

Structured JSON output · Prompt chaining · Auto-heal loop

Designtime → Runtime

Verification Sandbox

Ephemeral Deno subprocess · deno test · Scoped OS caps

Runtime

Go Engine

Single-binary daemon · MLLP + HTTP + SFTP channels

Runtime

Worker Pool

Isolated Deno workers · stdin/stdout IPC · Per-message execution

Storage

Embedded SQLite WAL

Pre-execution write · ACID guarantees · Point-in-time recovery

Zero-dependency binary

The Go runtime compiles to a single static binary. Deploy on-premises inside your data center, on a locked-down VM, or across distributed cloud nodes — no runtime dependencies to manage.

Fault-tolerant by default

Every inbound payload is durably written to the WAL before any transform executes. A process crash mid-flight never results in lost or half-processed data.

Process isolation, not threads

Each transform runs in a separate Deno subprocess. A runaway script — infinite loop, memory spike, unhandled exception — cannot affect any other active channel.

On-premises or cloud

For HIPAA-covered environments, the entire stack runs air-gapped. No patient data leaves your network. The LLM call happens at designtime only, against sample data you control.

Protocols & Standards

Speaks Every
Healthcare Dialect.

From legacy MLLP TCP streams in plasma donation centers to modern FHIR R4 REST APIs, The Magic Lizard handles inbound and outbound channels natively.

HL7 v2 ADT, ORM, ORU, MDM and all common segments
FHIR R4 REST resources, Bundles, and subscription topics
MLLP Raw TCP minimal lower layer protocol for clinical systems
SFTP Automated file ingestion and delivery to legacy systems
REST HTTP webhooks, JSON payloads, OAuth 2.0 outbound
X12 EDI 837, 835, 270/271 eligibility and claims
BECS Blood Establishment Computer System integration for blood banks and donation centers
Custom Proprietary formats handled via AI-generated TypeScript transforms

A note on where we are

We're Building This.
Want In?

The Magic Lizard is not a finished product — it's a fully-designed, actively-developed platform seeking its first design partners. That means you get direct input into what gets built, priority access when it ships, and a pricing structure that reflects the trust you're placing in us. In exchange, we ask for honest feedback and a real integration challenge to build against.

Shape the
Roadmap
Your real integration problems directly drive what gets built first — not a generic backlog.
Founder-Level
Access
Work directly with the architect building this, not a sales team. Feedback loops measured in hours, not sprints.
Design Partner
Pricing
Early partners receive preferred terms that reflect the risk and collaboration they're contributing.
No Lock-In
Until Ready
We'll be transparent about timelines and milestones. You don't commit to production until the platform earns it.

Build It With Us

The Blueprint Exists.
Let's Build Together.

The architecture is designed, the technology is chosen, and development is underway. We're looking for a small number of healthcare teams ready to co-build this with us — and get a platform shaped around their actual integration pain.

Become a Design Partner By Innershell

Contact

Let's Build
This Together.

Reach out to start a conversation. There's no sales pitch here — just a direct discussion about your integration challenges and whether this is something worth building together.

What "design partner" means

You bring a real healthcare integration problem. We bring the architecture, development capacity, and AI-first approach. We build the parts that matter to you first, you give us honest feedback, and we both end up with something better than either of us would have built alone.

Part of the Innershell family

The Magic Lizard is being built by Innershell — medical software specialists with deep experience in plasma, blood & transfusion systems.

Visit Innershell.com