scroll or click empty space to release

Blanc Quant Services  ·  founded by Jean Blanc

BLANC QUANT

tl;dr — founder, Blanc Quant Services · senior quantitative engineer, 15+ years across utilities, industrial R&D, standards and energy analytics. On my own time: deterministic C++ trading infrastructure whose CI fails if latency regresses, and GOTHAM, the AI second brain rendering this page.

The reliability infrastructure layer for mission-critical AI systems. AI and quantitative systems that survive production — Blanc Quant Services designs and deploys governed AI, automation, analytics, and performance infrastructure for organizations operating in complex, high-consequence environments. 20+ systems shipped. The edge: seeing connections others miss, synthesizing across domains, designing frameworks that make both operational. One standard: the system must work, measure itself, and produce evidence.

Proof of capability: you're inside GOTHAM, my personal AI operating system — a privacy-scrubbed export of the real thing. 5,208 notes, indexed and answerable by six agents on seven models, plus an 18-sage council for the hard calls. Real structure, real counts, content stripped; it rebuilds itself at 3 AM every morning and scores itself nightly. Click a cluster to fly in.

scroll to enter

01 — the galaxy

5,208 notes, exported from a live system

cluster // people2,545

Every professional connection, mapped as a constellation.

cluster // inbox555

Entry nodes — where every new thought lands before the graph files it.

cluster // personal423

Life, family, the questions behind everything else.

cluster // career330

Strategy, moves, the long game.

cluster // tech226

Systems, tools, and how they break.

cluster // entities170

The companies, tools and places my notes keep mentioning.

02 — how i can help

Four engagements

Every engagement begins the same way: a 30-minute assessment call, then a defined problem, fixed scope, measurable acceptance criteria, and a clear evidence package.

OFFER 01

AI Governance & Evidence

For regulated teams where governance is the system that blocked the thing — controls that live in PDFs, AI approvals measured in months, and zero usable traces to hand an examiner.

You get policy that runs at the moment of use: eval gates and kill criteria enforced in CI, and evidence that writes itself — so the governed path is the fastest one.

assessment → gate installevidence, not slides
OFFER 02

AI Systems Integration

For teams whose models, data, agents and workflows don't talk to each other — pilots that never reach production, AI output nobody can audit.

You get one governed production system: retrieval, routing, permissions, evaluation and observability, with an evidence trail for every consequential action.

assessment → 4–8 wk buildfixed scope
OFFER 03

Operational Intelligence & Automation

For infrastructure-heavy organizations — utilities, industrial, operations — where decisions live in spreadsheets, tribal knowledge and manual reporting.

You get decision tools, analytics pipelines, knowledge systems and automated workflows that measure themselves.

assessment → 4–6 wk sprintor advisory
OFFER 04

Quantitative Performance Infrastructure

For trading desks and compliance teams where performance claims are anecdotes.

You get deterministic replay, p50–p999 latency gates enforced in CI, digest verification and retained evidence bundles — via BQL Engine.

4–6 wk pilot, your workloadpatent pending

03 — the numbers

Counts, read from the export at build time

20systems shipped
5,208notes in the corpus
1,365conversations mapped
28topic clusters
6agents on call

where the galaxy comes from

GOTHAM is one expression of that philosophy. What you're flying through is a privacy-scrubbed export of the real system — genuine structure and counts, regenerated from the live corpus, with the content stripped. GOTHAM itself is locally hosted on my own hardware: loopback-bound, kill-switched, encrypted at rest. Nothing on this page holds a live connection to my private data, models, accounts, or production environment.

selected results — full record on the founder page

AI TRAINING · 2024–PRESENTContracted domain expert — training & evaluation across multiple frontier AI modelsunder NDA
RANKED #1 · 2023Exelon Analytics Academy — outperformed 100+ participants enterprise-wideutility-scale analytics
PATENT ISSUED · 2021"Best of the Best" Chairman's Safety Award for patented safety innovationgas infrastructure R&D
BQL ENGINE · 20251.96M events/sec deterministic replay, 100% digest consistency, p999 gates in CIpublic harness, reproducible

04 — case study · gotham

GOTHAM: six agents,
one router

Genesis · Oracle · Tars · Hugo · Aegis · Max · armed with 100+ licensed skills · six agents × seven models — 117,649 possible fleet configurations

A governed multi-model operating system — one engineer, run daily in production. What transfers to a client engagement:
  • ▸multi-model orchestration — each task routed to the model tier it needs; cheap work stays cheap, hard calls escalate to an adversarial 18-sage council
  • ▸secure knowledge retrieval — thousands of notes indexed and answerable; sensitive content never leaves local hardware
  • ▸permissioned agent actions — every skill licensed to exactly one agent, enforced at the call site
  • ▸evaluation & observability — nightly rebuild and self-scoring, receipts for every consequential action (the audit)
GMAIL (GEMINI) CHATGPT CLAUDE LINKEDIN OCR nightly ingestion 3 AM rebuild ↻ VAULT · 5,208 notes episodic · semantic vectors · graph · files — all local one prompt ROUTER GENESIS ORACLE TARS HUGO AEGIS MAX 117,649 fleet configurations hard call? 18-SAGE COUNCIL ARISTOTLESOCRATESSUN-TZUADAAURELIUSMACHIAVELLI LAO-TZUFEYNMANTORVALDSMUSASHIWATTSKARPATHY SUTSKEVERKAHNEMANMEADOWSMUNGERTALEBRAMS panels of three or the full bench — 817 panel configurations every consequential action leaves evidence — receipts · egress gates · audit log

hover any node — agents, sages, stages — for its roletap a node for its role — swipe sideways to pan the diagram

gotham router // try it● simulation
>
GENESISplanning · memory · approvals ORACLElive web research TARSquant · red-team · debug HUGOwriting · synthesis · comms AEGISsecurity · privacy · claims MAXchief of staff · default

A browser-side simulation of GOTHAM's routing rules — no live connection to the real system: name an agent to address it directly, and anything unclaimed defaults to MAX. In the real fleet, saying GOTHAM fans one prompt across six agents in parallel over four model families, then MAX synthesises. Every skill is licensed to exactly one agent and enforced at the call site — an agent cannot perform an operation it does not hold.

05 — blanc quant services

BQL Engine: latency gates
CI enforces on every commit

Three names, one engineer — said once, plainly: Blanc Quant Services (this site) is the consultancy — the engagements in section 02. Blanc Quant Systems is the product company — quantitative proof and AI-governance infrastructure, starting with BQL Engine. GOTHAM is the internal system both are proven on, built to the same evidence standard.

The product: Blanc Quant Systems — BQL Engine 2.0 — deterministic proof infrastructure for market systems. It replays market workloads, verifies identical behaviour, and blocks latency regressions in CI — catching what no ordinary test can: a change that silently alters book state or tail latency. Performance claims in trading are anecdotes, a benchmark someone ran once on a machine no one still has. This turns them into a contract CI enforces on every commit.

canonicalise inputs → replay deterministically → gate everything = same digest + evidence bundle

1.96Mevents/sec · tier a · match-only
1.23Mevents/sec · tier b · in-process
1.20Mevents/sec · tier c · pipeline
100%digest consistency, all tiers
p999deepest gate enforced in ci
4–6week pilot, your workload

Deterministic C++20 replay for limit-order-book workloads, p50/p95/p99/p999 gates enforced in CI, canonical digest verification, and retained evidence bundles (manifest · bench.jsonl · metrics · summary) a regulator or a new engineer can re-derive months later. The bundle is the unit of proof — artifacts a regulator can re-run. Built for HFT and prop desks where “it feels faster” is not an answer, and for compliance teams who need the receipt.

Run a design-partner evaluation Request the pilot brief

06 — software portfolio · 20 builds

20 builds, with first-commit dates

Every build below measures itself and leaves evidence.

07 — the audit

Self-audit, weakest score shown first

Ten dimensions, self-scored. Lowest score shown first. Total 85/100. The three lowest scores from the first audit, organisation, memory and resilience, were fixed and re-scored.

the kill certificate — governance, as evidence

The same standard governs AI-proposed trading strategies. LLMs propose, tests decide: every candidate runs a gauntlet of statistical gates, and each verdict writes a signed evidence digest as it happens. This is a real verdict: a strategy the gates rejected. It is the artifact a buyer shows their examiner.

GAUNTLET VERDICT · V-00003 / S-00003 strategy — long when EWMA(20) > EWMA(50), flat otherwise · from H-00003 deflated sharpe ........ FAIL monte carlo ............ pass sharpe ................. pass max drawdown ........... pass walk-forward splits .... pass positive expectancy .... pass verdict KILLED · evidence digest 114aa7336f452b08 lifetime — 5 validation runs · 2 strategies killed · 0 promoted to live capital

One gate failed, so the strategy died — five passing gates bought it nothing. That is the point: a control that can't kill anything isn't a control. Offer 01 installs this discipline on your stack.

08 — the ask

Book the assessment

Everything on this page runs for real, every day — built by the same engineer who ships a deterministic C++ order-book engine where CI rejects any p99 breach. The fleet gets the same discipline: security gates on every egress, failover that survives rate limits, receipts for every claim. If your firm needs AI that survives production, bring Blanc Quant onto the problem.