Compiled
Now available on Azure Marketplace

Your enterprise
needs an immune system.
Not another firewall.

Compiled converts any described threat into a mathematical antibody that scans every AI action and communication in real time, inside your environment. Sub-100ms. Zero egress. No LLM in the path.

0.995 AUCdetection accuracy
<100msscan latency
~7KBper antibody
0 egressarchitecturally

Trusted by security and compliance teams at

Meridian CapitalAshford GroupCrestline HealthVantage SecuritiesNordvik PartnersSolis FinancialKestrel Asset Mgmt
0.000AUC — detection accuracysynthetic + real-world validated
<0msScan latencymatrix multiply, no LLM inference
~0KBPer antibodyships inbound; your data never leaves
0Data egress — by architecturescanner runs inside your tenant

The problem

AI is moving faster than governance.
By a lot.

Every approach built for the last decade — rules, signatures, LLM-as-judge — has a structural defect that AI-native threats expose. The tools exist. The architecture is wrong.

300ms–2s
added per message

LLM-based scanners add 300ms–2s per scan.

That is not a product decision — it is a fundamental architecture choice. If intelligence runs at scan time, latency compounds with every API call, every agent action, every email.

Rule sets
go stale overnight

Signature and rule-based systems break on paraphrase.

Adversaries do not repeat themselves verbatim. A behavioral model trained on the shape of intent — not the exact words — generalises. Keyword detectors do not.

Your data
leaves your perimeter

Cloud-routed scanners send your communications to a third party.

Regulated industries cannot accept that. Compiled's scanner runs inside your environment. Only a 7KB math function crosses the boundary — inbound, at deploy time.

How it works

Security that compiles your policy.
Not one that reads it at runtime.

Intelligence is frozen into a mathematical object before it ever touches your production traffic. Scanning is arithmetic, not inference.

TechnicalCompile → Deploy → Scan
ComplianceDescribe → Protect → Audit
01
Compile
aka Describe

Write one sentence. We do the rest.

Describe the threat in plain English: "Detect communications that may constitute insider trading." Our pipeline synthesises thousands of behavioural examples, trains a contrastive embedding model, and distils the result into a ~7KB weight vector. No labelled data from you.

  • Synthetic data generation via language model
  • Contrastive training — 0.981 linear AUC on held-out real data
  • Hard-negative style-confound test before any antibody ships
02
Deploy
aka Protect

A 7KB function ships in. Nothing ships out.

The compiled antibody is a tiny weight vector. It deploys into your Azure or AWS tenant as a sidecar container. Your messages, documents, and agent outputs never leave your perimeter — they are embedded locally and scored against the vector in memory.

  • Azure Container App or AWS Fargate — your tenant, your VNet
  • Embedding model runs locally (Azure OpenAI or bge-small air-gap)
  • Vector update = replace 7KB file; no redeployment of your stack
03
Scan
aka Audit

Sub-100ms. No language model in the path.

At runtime the scanner is a single matrix multiply: embed the text, dot-product with the antibody vector, threshold. Intelligence lives in the vector, not in a model running live. That is why we are categorically faster than every LLM-based approach.

  • Throughput: thousands of messages per second per node
  • Score output: 0–1 float + Safe / Flagged / Blocked verdict
  • Full audit log inside your tenant; SIEM-ready JSON

Products

One compiler. Two surfaces.
Any described threat.

AI Agent Governance

Every action an AI agent takes — tool call, file write, API request, email send — is scored against your policy antibody in real time. Agents that drift from policy are flagged or blocked before the action completes.

  • Inline action interception — pre-execution scoring
  • Multi-agent orchestration support (LangChain, AutoGen, Semantic Kernel)
  • Policy per agent role, not per rule
  • Audit trail: every decision, every score, immutable log

Communications Surveillance

Email, chat, voice transcripts — every communication is scanned for behavioural patterns that indicate insider trading, market manipulation, or regulatory policy violations. Zero egress. Audit-ready output.

  • SEC, FINRA, FCA, MiFID II regulatory coverage
  • Covers email, Bloomberg, Teams, voice-to-text
  • 0 false positives on real Fed/earnings comms in validation
  • Calibrated on your communications distribution before go-live

Proven out-of-the-box — compile once, detect anywhere

0.995AUC — Insider trading
0.983AUC — Prompt injection
0.996AUC — Market manipulation
0.985AUC — Phishing

The network

Every customer makes every
other customer smarter.
Without sharing a single byte of data.

When a new threat pattern emerges at one institution, the geometry of that threat — its mathematical centroid in embedding space — is aggregated with differential privacy guarantees and shared across the network. Raw messages are never shared. Individual embeddings are never shared. Only the mathematical shape of behaviour crosses tenant boundaries.

0.74 → 0.86 AUCCold-start improvement from network geometry alone
0.63 re-id rateDP centroid sharing is near-random for individual identification
Matmul costAdding a new concept to the network fabric
Read the network architecture

What teams are saying

The architecture does the persuading.

We had an LLM-based scanner in pilot for six months. Latency was 800ms average and it still missed paraphrase variants. Compiled went live in a week, runs at 60ms, and the style-confound test gave us the confidence our legal team needed.

Head of Surveillance Technology
Global investment bank

The zero-egress architecture was non-negotiable for us. The fact that it deploys into our Azure tenant and the only thing that crosses the boundary is a 7KB weight file was the deciding factor over three other vendors.

CISO
Mid-market asset manager

We described our insider trading policy in one paragraph. Two days later we had a working detector. That is not an exaggeration. The compile time for a new antibody is measured in hours, not quarters.

Chief Compliance Officer
Regional broker-dealer

Integrations

Deploy into your existing stack.

Compiled installs as a container into your cloud tenant. No new SaaS vendor relationship. No data processor agreement for message content. Available on Azure Marketplace for one-click tenant deployment.

Azure MarketplaceFeatured

One-click tenant deployment. Runs inside your Azure subscription — VNet-isolated.

Get on Azure Marketplace
AWS Marketplace
Azure OpenAI
Microsoft Teams
Bloomberg
Splunk / SIEM
LangChain
AutoGen
Semantic Kernel

Ready to give your enterprise
a behavioral immune system?

A 45-minute call with our team covers your threat model, your architecture constraints, and what a compiled antibody would look like for your specific regulatory context.