About
Jacob builds institutional intelligence infrastructure: the memory and coordination layer that protects, compounds, and activates the knowledge inside a firm. His background in quantitative finance, organizational leadership, and product delivery shaped a practitioner's understanding of how firms actually lose knowledge and what it costs them. Project Symmetry provides the solution.
What We Build
Most firms using AI are building on rented ground. The tools are powerful and the data protections are real. But the accumulated knowledge of how that firm thinks, decides, and operates lives in someone else's ecosystem. When the session ends, the context resets.
Project Symmetry is built on a different premise. While the reasoning engine uses best-in-class models, the institutional intelligence layer, the decisions made, the patterns recognized, and the methodologies that proved out, are entirely the firm's. They compound. What the firm knows at year five is built directly on what it learned at year one.
Useful from inception. Exponentially irreplaceable over time. Scalable from boutique to enterprise.
The platform's core differentiator is a five-stage memory pipeline grounded in cognitive science. Each experience moves through a deliberate encoding and consolidation process before becoming part of the function's permanent knowledge base.
Engrams are stored in a temporal knowledge graph: a web of typed connections rather than a flat list. When a task begins, the system traverses the graph from the current context outward, surfacing only the knowledge with direct relational bearing on this conversation, this person, this domain. As the archive grows, token cost stays bounded. The firm's knowledge isn't retrieved. It's navigated.
Picture finding your way by the stars rather than sailing aimlessly through the sea. Your destination is inferred by fixed points above and their relationships to each other, to the horizon, and to time itself. With sextant and map, not blindly in the dark. Engrams work the same way. When a task begins, the system doesn't search the entire archive. It reads the sky from wherever it stands.
The platform deploys specialized functions configured entirely around the firm's domain. Each operates within a defined scope, contributes to shared institutional memory, and coordinates through a structured communication protocol. The architecture is extensible by design: any function can be built, deployed, and integrated without rebuilding the underlying intelligence layer.
The system is built on the premise that intelligence without accountability is noise. Every output passes through a structured decision hierarchy: signals are sequenced, indicators are weighted against each other, and conflicting data triggers circuit breakers rather than cascade failures. Quality gates and contrarian reviewers challenge every output before it reaches you.
Variant strategies run continuously in shadow evaluation against live decisions, and parameters that outperform are promoted automatically. The result is a platform that improves with every cycle it runs. Every output is auditable. Every parameter is reversible.
The trading system runs Bayesian parameter optimization, hybrid decision architecture, and a two-tier risk governance framework against 25 years of historical market data. Fully autonomous, daily operations.
$500K starting capital. Paper trading through February 2026. Live deployment began March 2026.
Most tools in this space are built to do the work for you. The result is faster output, but a quieter, duller version of yourself.
This is a partner built around how you think, what you dream, and how you strive to be heard. An editor offering just the right contrarian view you never knew you needed. Built to learn your instincts, your tendencies, the places where old habits masquerade as choices. A simple language model is a blank canvas. This is a world you've painted over a lifetime.
A collaborator that helps you be the best version of you.
Methodology
The question driving the architecture is not "what can AI do?" It is "what does a firm need to know, how confidently does it need to know it, and what happens when it is wrong?" That is an epistemological problem, not a technical one. The engineering follows from the answer.
The approach: define the knowledge requirement first. Build the system to meet it. Challenge every output before trusting it. Let the parameters that perform earn the right to stay, and promote them automatically when they do. Convictions formed without evidence are opinions. Systems built without accountability are liabilities. Processes that do not improve are already obsolete.
The cognitive science came after the architecture existed. Tulving, Tonegawa, Müller and Pilzecker confirmed the design. They did not inspire it. When research validates what already works, the problem was real from the start. That is how good systems get built.
Contact
J. I. Ashley Consulting is not currently accepting new clients. For partnership inquiries, press, or investment conversations: