scroll or click empty space to release

// Blanc Quant Services

JEAN BLANC

tl;dr — senior quantitative software engineer. Everything on this page is built and running, not rendered. Flagships: BQL Engine 2.0, deterministic market replay whose CI fails if latency regresses, and GOTHAM, the six-agent AI second brain that runs my life — with an archive of builds behind them. You're inside GOTHAM now.

This is my actual memory, running live. 4,611 notes; every conversation, document and professional connection I've kept, indexed, connected, and answerable by five AI agents on four different models — plus an 18-sage council for the hard calls. Nothing on this page is a mockup: it rebuilds itself at 3 AM every morning and scores its own accuracy nightly. Click a cluster to fly in.

scroll to enter

01 — the galaxy

Every dot is a real thought.

cluster // people2,545

Every professional connection, mapped as a constellation.

cluster // inbox555

Captures waiting to be filed — the system's front door.

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 — the numbers

Real data. No renders.

20ai projects shipped
4,578notes in the corpus
1,365conversations mapped
28topic clusters
6agents on call
2,545people in the network

where the galaxy comes from

03 — gotham · the fleet

Six agents.
One prompt.
G.O.T.H.A.M.

Genesis · Oracle · Tars · Hugo · Aegis · Max

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

This is GOTHAM's real routing model, not a demo script: name an agent to address it directly, add ? to make it read your notes first, and anything unclaimed defaults to MAX. Say god mode and five agents answer in parallel across 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.

04 — blanc quant services

Prove it didn't get slower.

The company: 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 usually 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 — forwardable artifacts, not slides, not anecdotes. 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

05 — the archive · 20 builds

Built, not rendered.

The same hands built both halves of this archive: a deterministic C++ limit-order-book engine whose CI rejects any build that breaches its p99 latency budget — and GOTHAM, the agent fleet above, held to the same standard. Probabilistic models, deterministic harness: egress gates, failover paths, replayable receipts. Quant rigor, applied to LLMs.

06 — the audit

Scored, not spun.

Eleven dimensions, graded honestly — including the ones that were weak. Overall: 92/100 today. The three lowest scores from the first audit — organisation, memory and resilience — were closed, not renamed.

the snowball — road to 100

07 — the ask

Now deploy it at scale.

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, put me on the problem.