COMPLiQ hero image

COMPLiQ

The Global Standard for Secure, RESPONSIBLE AI Deployments

Role: Product Owner & System Architect
Timeline: 2024
Type: Platform
Live →
Design Systems AI Integration
Python OpenAI HuggingFace AWS Blockchain
13 people
Pod Size

The Problem

Enterprises deploying AI face shadow usage, data leakage, compliance violations, and no audit trail. Traditional security has 7 layers-none address AI behavior.

Patent-pending
Architecture
6 months
Build Time

The Process

Led a 13-person pod for 6 months building toward an AI Chief Compliance Officer. Hit external dependency wall when custodian APIs were blocked. Pivoted architecture to broader enterprise AI security market.

The Outcome

Live product at compliq.ai. Patent-pending scanner architecture. Successful pivot from narrow RIA focus to enterprise-wide AI compliance tool.

Design Decisions

Decision Why Engineering Tradeoff
Model-agnostic API Enterprises want flexibility and cannot lock to one LLM Additional abstraction layer but future-proofs the platform
Trust calibration system High confidence equals auto-pass, low equals human review Requires confidence scoring infrastructure
Blockchain audit logs Immutable proof for compliance audits Added complexity but essential for enterprise trust

STAR Summary

SituationEnterprises deploying AI faced a security gap: traditional 7-layer security models weren’t built for AI behavior. Shadow AI, prompt injection, data leakage through conversations, and zero audit trails created compliance risk-especially in regulated industries like financial services.
TaskDesign and lead development of an AI compliance platform. Initially targeted RIAs (Registered Investment Advisors) with an “AI Chief Compliance Officer” that could monitor, audit, and ensure regulatory compliance.
ActionLed 13-person development pod. Designed patent-pending scanner architecture. Built trust calibration system. Wrote core scanner rule logic. When custodian API access was blocked after 6 months, pivoted from RIA-specific tool to enterprise-wide AI security platform.
ResultLive product at compliq.ai. Patent-pending architecture applicable across regulated industries. Successful pivot preserved 6 months of technical work while opening broader market.

Multi-Layer Architecture

LayerFunction
Pre-ScreeningQuick boolean check on incoming data
ValidationL2/L3 distributed validation
AI EnsembleMultiple micro-models for accuracy
ProcessingTemporary Processing Model assembly
AuditImmutable blockchain logging

Every AI interaction is validated before processing and logged after completion.


The Pivot

PhaseWhat Happened
6 months buildingScanner architecture, trust calibration, blockchain audit logs
The blockerCustodian APIs denied-RIA-specific vision couldn’t function
The pivotReframed from “RIA compliance” to “enterprise AI security”
The saveModular, API-agnostic architecture preserved all technical work

Lesson: External dependencies can invalidate months of work overnight. Build modular first.


Trust Calibration

ConfidenceActionRationale
90%+Auto-pass + loggingDon’t slow obvious safe interactions
70-90%Soft alert + enhanced loggingProceed with monitoring
< 70%Human reviewCompliance officer decides

System learns from human decisions on edge cases, improving scoring over time.


AI-Assisted Rule Development

Before AIAfter AI
Legal SME → I translate → Review cyclesLegal SME → AI generates → SME refines → I validate
Days per rule~60% faster

The pattern-AI generates, human validates-became core to how we build.


Pod Leadership

CadenceFocus
DailyScanner rule logic, architecture decisions, blocker resolution
WeeklyPod coordination, stakeholder alignment, roadmap
MonthlyArchitecture reviews, security audits, patent documentation

13-person pod: Solution Architect, BA, PM, 10 developers. Bridging product requirements with technical implementation.

Gallery