Ingest the world
Live SEC filings, earnings calls, central-bank prints, OPEC headlines, social-media noise. NER + embedding indexes everything in seconds.
Asymmetric Yield Via Intelligent Decisions
An AI-native hedge fund. Swarms of LLM agents read every 10-K, earnings call, and SEC filing in real time, trace the consequences through a live causal graph of the global economy, and size, hedge, and route the trades — end-to-end, no humans on the trade path.
Operations console
Each panel below is wired to the same engine that places the trades. Walk-forward 2018 → 2025 across 20 named historical shocks. No hindsight. No staging data.
An AI-native hedge fund built end-to-end around causal reasoning. We don’t bolt LLMs onto a quant stack. We use them to find strategies that didn’t exist before.
About the firmCapabilities
Milestones
AYVID founded
Apr 2026Engine v0 · modular monolith
Causal graph + agent swarm
Apr 2026Neo4j + LangGraph integration
IB Paper · live shock catalog
Apr 202620 named shocks · walk-forward
YC S26 · seed conversations
In progressAllocator outreach
How it works
A simple, four-stage pipeline that turns unstructured language into structured, sized, risk-limited orders.
Live SEC filings, earnings calls, central-bank prints, OPEC headlines, social-media noise. NER + embedding indexes everything in seconds.
A live Neo4j graph of suppliers, customers, indices, and shared inputs propagates each shock N hops outward to find the unobvious beneficiaries and victims.
Four LLM specialists — Strategist, Mapper, Auditor, Supervisor — debate every signal. Bayesian reconciliation across them is how we estimate conviction.
Sized, hedged, risk-limited orders route to Interactive Brokers in under 100 ms. A C++ kill-switch watchdog can flatten the book in milliseconds.
What we run
Live Neo4j topology of suppliers, customers, indices, and shared inputs. Shock propagation in milliseconds.
Four LLM specialists debate each signal. Disagreement is itself a signal that the trade is fragile.
From 8-K to broker order in one modular monolith. No humans on the trade path. Tier 1 sub-100ms.
Independent C++ kill-switch watchdog. Position-level VaR, drawdown, and concentration limits enforced pre-trade.
Why AYVID
Most quants will bolt LLMs onto an existing book. We started from language and worked outward to execution. The architecture is the edge.
We trace each shock through suppliers, customers, and indices. We trade the unobvious second-order beneficiaries.
Lagged factors, momentum residuals, value premia. Linear models on non-linear consequences.
Four specialists debate every signal. Disagreement is conviction-discounted.
One PM's mental model bottlenecks the entire firm. Disagreement is dampened, not measured.
8-K to broker order in one system. No humans on the trade path. Risk pre-checked.
Analysts hand-off to traders. Latency in seconds-to-minutes. Behavioural drift in execution.
Live shock catalog, walk-forward equity curves, runner status — all reproducible from the console.
Aggregated, smoothed, lagged. Hard to attribute alpha to actual decisions.
By the numbers
Voices
“The next Renaissance, Bridgewater, and D.E. Shaw will be built on AI. The biggest funds will be slow to adapt.”
Charlie Holtz
Y Combinator · Request for Startups
“The alpha is in using AI to come up with strategies that didn’t exist before — language comprehension, causal reasoning across thousands of filings.”
Charlie Holtz
Y Combinator · Request for Startups
“Causal inference on supply chains is the most underweighted edge in markets. The data has been there for years; the reasoning hasn’t.”
Working note
AYVID Research · 2026
FAQ
Most of what we hear from allocators on the first call falls into one of these. The rest is in the operations console.
Ask anotherEngage with AYVID
For LPs, family offices, and YC partners. Walk through the live shock catalog, signal book, and IB Paper trades. Sign an MNDA for equity-curve and risk-figure access.
Public research notes on causal inference, agent-swarm calibration, and walk-forward methodology. No live PnL.