RIAOS: AI-Powered Operations Platform for an RIA
By Colter Mahlum, Founder & CEO of Mahlum Innovations — published 2026-03-01.
Colter Mahlum architected and shipped this case study end-to-end. Mechanical engineer turned AI builder, based in Bigfork and Kalispell, Montana. 11 production AI systems shipped across healthcare, wellness, legal, wealth management, fitness, and consumer apps.
Consolidating 40+ Wealth Management Workflows Into One Compliance-Grade Platform
App: RIAOS | Industry: Wealth Management / FinTech | Client: Confidential — boutique RIA serving ultra-high-net-worth clients | Company size: Independent wealth management firm (UHNW individuals, families, organizations) | Duration: Ongoing iterative build with full mobile companion app
Summary
An AI-powered operations and intelligence platform that automates document management, client data, compliance, trading, and advisory workflows for a wealth management firm.
The Challenge
The firm was managing client onboarding, document classification, compliance tracking, trading operations, financial planning, and advisor workflows across disconnected spreadsheets, email, and manual processes — with limited audit trails and 8 separate Excel workbooks per client.
Our Approach
- Built multi-stage GPT-4o document classification with structured data extraction across the firm's full document corpus
- Created an AI-powered dictation engine that parses natural speech into structured client data across 8 categories (accounts, net worth, household, meeting agendas, etc.)
- Layered an AI Assistant with function-calling tools for natural language querying of clients, KPIs, pipelines, and documents
- Implemented an AI Coaching engine for advisor performance analysis and AI Meeting Intelligence for transcript analysis, summary generation, and action-item extraction
- Built a real-time trading desk with candlestick charts, AI-generated BUY/SELL/HOLD signals, and SEC Rule 606 best-execution compliance
- Added Monte Carlo financial planning simulations and risk analytics with stress testing
- Integrated Salesforce CRM with OAuth 2.0, Change Data Capture, and Bulk API 2.0
- Shipped a React Native (Expo) mobile app mirroring all 40+ web features, deployed via TestFlight
- Implemented session-based auth with TOTP 2FA and compliance-grade audit logging
Outcomes & ROI
- 40+ — Workflows Consolidated: Manual operational workflows unified into one AI-enhanced platform
- Assisted — Document review: AI classification supports a human review and sorting workflow
- 8 → 1 — Workbooks Per Client: Client 360 structured data hub replaces 8 separate Excel workbooks per client
Human-in-the-loop review queue ensures 100% compliance oversight on all AI decisions. Real-time KPI dashboard replaces monthly manual reporting. Full iOS mobile app gives advisors on-the-go access to all platform capabilities.
Technologies Used
GPT-4o / GPT-4, Salesforce (OAuth 2.0, CDC, Bulk API 2.0), React Native (Expo), PostgreSQL + Drizzle, TOTP 2FA, Monte Carlo simulations, SEC Rule 606 compliance
Key Takeaways
- Compliance-grade AI in wealth management requires a human-in-the-loop review queue on every AI decision — anything less is unacceptable to regulators and to UHNW clients
- Salesforce Change Data Capture + Bulk API 2.0 is the right pattern for keeping a custom platform synchronized with an existing CRM without breaking either system
- Voice-to-structured-data dictation is the unlock for advisors who don't want to type during client meetings — adoption is dramatically higher than typed entry
Frequently Asked Questions
How is compliance handled?
Every AI decision flows through a human-in-the-loop review queue, all activity is captured in compliance-grade audit logs, and authentication uses session-based auth with TOTP 2FA.
How does the trading desk meet SEC Rule 606 requirements?
Best-execution data is captured at order placement and reflected in the trade record so quarterly Rule 606 reports can be generated directly from the platform.
Is there a mobile app?
Yes — a React Native (Expo) iOS app deployed via TestFlight that mirrors all 40+ web features, so advisors have full platform access on the go.
Related Services
About the Builder
Mechanical engineer turned AI builder. Colter personally architected and shipped RIAOS end-to-end — strategy, model development, and the production MLOps work — alongside 10+ other AI systems across manufacturing, wealth management, healthcare, and consumer apps. Read full bio · LinkedIn.
More Case Studies
- Peak AI Engine — An all-in-one AI-powered fitness facility management platform that unifies member management, personal training, group fitness, HR, and operations into a single intelligent system.
- Mahlum Properties — A private, invite-only family property reservation system with owner-approval workflows, utility cost tracking, and role-based access control.
- Axiom AI — A multi-agent AI orchestration platform that lets users deploy, coordinate, and monitor swarms of specialized Claude/GPT/Gemini agents from a single command center to autonomously execute complex software, research, and operational workflows.
- Axiom Trading Agent — An autonomous multi-vertical trading agent that finds, validates, and executes positive-EV trades on Kalshi prediction markets and Robinhood crypto end-to-end, with no human in the loop.
- Chronos AI — A HIPAA-aligned document chronology platform that ingests legal and medical record sets and produces structured, citation-linked event timelines, built on React, TypeScript, Node, and Supabase Postgres with pgvector for semantic search across document corpora.
- Montana Athletic Club App — A member mobile application for a regional Montana health club, featuring Apple HealthKit integration for activity and health data sync, member account management, and class scheduling.