PROJECTS
Smith Advanced Systems is an independent AI and technology research lab. We build software where we've felt the gap ourselves: tools that integrate into existing stacks, don't require vendor lock-in, and are designed to be owned by the engineers using them.
Synthetic test data for systems that fail on tidy demos.
generate-data.com is a synthetic test data platform for teams evaluating matching, scoring, and other intelligent systems. Unlike generic faker tools, you can configure quality characteristics such as exact duplicates, fuzzy duplicates, and realistic field-level variation, so test datasets look like the messy production inputs your models and pipelines will see. That makes regression suites and QA datasets honest about failure modes tidy unique rows would hide.
The problem it solves
Most synthetic generators invent clean, unique rows. Matching systems, quality scorers, and evaluation harnesses fail on duplicates, typos, and field-level drift. If your tests never inject that mess, they pass while production still breaks. generate-data treats input quality as configuration, not an afterthought script.
Who it's for: Engineers and researchers testing matching and quality systems. QA teams building regression datasets for intelligent pipelines.
Orchestrate agents. Ship production AI workflows.
skailr is an agent orchestration and deployment platform for teams building with AI. It helps you route work across specialized agents, enforce guardrails, and ship production workflows that are composable, observable, and designed to evolve as your system learns.
Who it's for: Teams building agentic products and internal automation who need a platform to deploy, manage, and evolve multi-agent workflows in production.
Agentic intelligence for wealth managers. Parallel agents reconcile signal, precedent, and portfolio exposure into advisor-ready recommendations in under 30 seconds.
olios.io is an agentic intelligence platform that mirrors how a high-performing investment team thinks, but runs in parallel, at machine speed, with full compliance controls. When a market event occurs, Olios activates a coordinated pipeline of AI agents that surface the right signal, retrieve the firm's own historical precedent, and assess per-client portfolio exposure, then reconcile those inputs into a single actionable recommendation ready for advisor review in under 30 seconds.
The problem it solves
Wealth managers operate in a world of parallel complexity. A single market event (a Fed announcement, an earnings miss, a rate move) can affect hundreds of client portfolios at once. It demands updated risk assessments, triggers client communications, and needs historical context that lives across years of investment committee notes and trade rationale. The information exists. The problem is synthesizing it fast enough to act. Insight arrives too late, actions are inconsistent across client segments, and advisors spend hours on synthesis that should take minutes.
Who it's for: Wealth managers, RIAs, and investment teams operating multi-portfolio, compliance-conscious workflows where timely, consistent synthesis is the bottleneck.
HOW WE BUILD
Every project in the Smith Advanced Systems portfolio starts from the same design principle: it should integrate into the systems teams already run rather than forcing a rebuild around a black box. We expose the logic so teams can own it. We design for operators first, and we ship research tools and software meant to be adopted like any other piece of stack they control.