Skip to content

Dylan Mérigaud · Freelance AI Engineer · Fintech

Code decides the money.AI reads the mess.

I ship the AI and the product around it: orchestration, integrations, evals, the parts that survive real usage. 9 years full-stack, ex-Pivot (procurement fintech).

See the work[email protected]

the trace

Selected work

Three public reference systems. Live where a browser can show it, every repo open.

A · match / ledgerloop

ledgerloop

An agent reads a company's HRIS and derives the whole approval workflow. Then invoices route through it.

A vendor PDF is extracted by a vision model, matched 2/3-way against open purchase orders captured from a live QuickBooks org, and routed through an approval DAG derived from real BambooHR data. Nobody draws a workflow canvas: the agent derives it from the org chart and you maintain it in plain language.

AI sits only where it earns its keep: reading messy documents, mapping org titles to signing authority, investigating flagged exceptions. The money path is deterministic, unit-tested code, and nothing posts before a human approves. Every run lands as an append-only audit row, replayable with zero tokens. Swap the QuickBooks adapter for NetSuite and nothing downstream changes.

Live demo
  • Mastra
  • Next.js
  • TypeScript strict
  • Zod
  • Drizzle
  • QuickBooks
  • BambooHR
The approval workflow ledgerloop derived from a client HRIS: manager review by Riley Carter for anything over 1,000 dollars, director review by Cameron Diaz over 10,000, department head review by Sam Patel on product only, then the bill posts to NetSuite
fig. 01 · derived approval DAG · ledgerloop

B · route / approvals-ui

approvals-ui

The approval workflow screen, as shadcn components.

Quorum gates, amount thresholds, a policy lint that knows what segregation of duties means, and plain-language editing where a human reviews the diff before anything lands. One command and the code lands in your project, yours to edit. Built on react-flow-auto-layout, my published npm package that lays out React Flow graphs the way dagre should.

Live playground
  • shadcn registry
  • React Flow
  • react-flow-auto-layout
fig. 02 · plain-language edit · approvals-ui

C · audit / fintech-roast

fintech-roast

An agent that roasts the code that touches money.

A rulebook of 41 researched rules across 10 domains, from ledger integrity and rounding to FX, tax, webhooks, and time, applied per-language to TypeScript, Python, and Java, with every finding adversarially verified before it is reported. Read-only: it never edits your code. Run it on your own repo in two commands.

  • Claude Code plugin
  • 41 rules
  • read-only
fig. 03 · verified findings · fintech-roast

also in the trace

AI Invoice Parser, a schema-validated extraction demo with an eval harness across 9 messy real-world formats. Live demo · GitHub

vouched for

People who shipped with me at Pivot

  • Dylan doesn't just write code, he thinks strategically about the user experience, business goals, and long-term scalability. He's the kind of engineer who proactively identifies problems before they arise, suggests smart solutions, and executes with precision.
    Christian HamelinChristian HamelinCo-founder @ Sprout
  • His full-stack expertise and sharp product sense made a real difference. He has this rare ability to switch effortlessly between backend and frontend, always spotting potential issues early and offering smart, pragmatic fixes.
    Reda BenchraaReda BenchraaSenior Software Engineer
  • Dylan combines incredible speed of execution with a laser focus on quality: he gets things done fast, and he gets them done right. What really sets him apart is his strong customer-first mentality.
    Pascal GreilichPascal GreilichSoftware Engineer

01 · trace / nine years of runs

Experience

Pivot · procurement fintech, Paris

Shipped the PO approval flow and the NetSuite integration. Cut client onboarding time ~90% by automating the approval setup.

Neige · founder

AI software company. Ships and runs its own products, empty repo to revenue, solo.

Runtime · 9 years

Full-stack, exclusively in startups and scale-ups.

02 · policy / no llm on amounts

How I build AI for fintech

An LLM never decides a payment amount.

Deterministic where it must be, agentic only where the trajectory is genuinely open-ended. AI reads the documents, derives the workflows, and investigates the exceptions. Code moves the money.

  • Next.js
  • TypeScript
  • Node
  • Python / FastAPI
  • Postgres
  • Supabase
  • Mastra
  • OpenAI & Anthropic APIs

03 · record / published here first

Notes

Long-form writing on the parts that survive real usage. Published here first, syndicated after.

All notes

04 · scope / how we start

Work with me

Start with a paid pilot.
One scoped problem, a fixed one to three week sprint, a deliverable you run in your own repo. Low risk for you, fast proof for both of us. It grows into a larger build or it doesn't, and either way the work is yours to keep.
A bridge while you hire.
A senior hire takes months to land. I ship the AI piece that can't wait now, on a defined scope, while you run the search. The contract ends whenever you want it to. Open to a permanent role later if it clicks on both sides.
Available now.
Remote, working US hours with full overlap, on-site in NY or SF for key milestones, Paris too. Fixed-scope pilots and two to four week builds.

Pilots and builds are fixed-price, hourly for open-ended work, rates on the call.

05 · approve / let's talk

Building AI into a fintech product? Let's talk.

[email protected]Book 30 min

Remote, working US hours. On-site in NY/SF for key milestones. Paris available too.

APPROVED

trace complete · human approved

Dylan Mérigaud
Dylan Mérigaudfreelance ai engineer

Follow updates in Google