Mathieu Haye is a French freelance builder based in Île-de-France who designs and ships custom web apps, AI agents, n8n automation workflows and Salesforce platforms for SMEs, scale-ups and B2B clients. Since October 2025, he sells the third-way thesis between no-code-only and traditional agencies: a solo builder augmented by Claude Code, n8n, Next.js, Supabase and Stripe Connect, shipping in weeks what used to need a team of four. One single point of contact, from spec to production. Three packages: a 1-week Sprint from €400 depending on scope, a 4-to-6-week MVP, and a monthly Retainer (MVP and Retainer priced on quote). Contact: contact@mathieuhaye.fr. Reply within 24h Monday to Friday.
I build with AI as a daily reflex: agentic workflows, scoring pipelines, automations that move business KPIs. Freelance consultant since 2025, four active clients, French and English.
I am Mathieu Haye, 22, based in the Paris region. Freelance consultant in CRM, data engineering and applied AI since October 2025. Background in Economics & Management, then Digital Innovation. Now building full-time for my clients.
I build with AI as a daily reflex: agentic workflows, LLM scoring pipelines, AI-powered automations, decision dashboards, CRM and sales orchestration. Multi-client freelance practice, four active engagements, hands-on with Claude API, n8n (93+ nodes), Salesforce Apex, Brevo, HubSpot, Pipedrive. I ship tools that move business KPIs, not slides.
Claude API as a daily reflex, agentic workflows, AI scoring pipelines, prompt engineering, n8n (93+ node workflows), Make, Apps Script.
pandas, numpy, scipy, scikit-learn, SQL, ETL, APIs, scraping. Power BI, Looker Studio.
Salesforce (Admin, Apex, SOQL, LWC), Pipedrive, HubSpot, Brevo, Odoo.
Commercial pitching, business reading, multi-client account handling, sector watch. Bloomberg BMC certified, side curiosity: ETF and crypto investing.
Pourquoi un builder solo augmenté livre ce qui prenait une équipe il y a 3 ans.
Click any card for the full breakdown.
Fully automated weekly newsletter: ingest from 20+ sources, AI scoring & summarisation, HTML rendering, delivery via Brevo. Runs on autopilot, no human in the loop.
Aggregates WTTJ, JobTeaser and LinkedIn via APIs, applies a weighted scoring algorithm against my profile. For each high-scoring offer, auto-generates an ATS-optimised CV and cover letter in PDF, tailored to the job description.
Salesforce build-out for the 3018 child protection hotline: Apex REST APIs, Lightning Web Components, 3CX telephony integration, Einstein Bot triage and CSP rules.
Windows desktop app that intercepts USB devices before they can talk to the OS. Blocks BadUSB, Rubber Ducky, O.MG cables, juice-jacking and removable-media payloads via Raw Input keyboard challenges, composite-device detection, on-insert read-only scan and optional VirusTotal lookup. Python + Tkinter, ~4,900 lines, single-file installer.
Personal multi-asset tracker (crypto, stocks, ETF) with technical indicators, AI-generated commentary on market open/close, DCA tracker and Telegram alerts.
TradingView indicator for long-term stock picking: bounce detection, trailing 15% stop loss, higher timeframe candles. Backtest on AAOI (5y): +187%, 54% WR, PF 1.62, MaxDD 24%. Trades return for drawdown protection, not alpha.
Tooling to compare SCI / IS vs LMNP regimes, model mortgage scenarios, and rank French cities on a rental yield index. Used to size my own portfolio.
Mean reversion on BTC and ETH with RSI + Bollinger entries. Paper ran +3.2% over 90 days. Live pilot ended at -2.1%: taker fees plus slippage ate the edge. Next iteration on maker-rebate orders.
Certified. Covers economic indicators, currencies, fixed income, interest rate risk and equities. The shared language for any business-and-markets conversation.
Verify certificate →Information systems, digital innovation, project management, quantitative methods.
Macro, micro, corporate finance, financial analysis, econometrics, applied statistics.
Programming fundamentals, algorithms, object-oriented design.
ChatGPT, Perplexity, Google AI : un score sur 100, un verdict clair, et le temps estimé pour corriger. 30 secondes.
Lancer le test →6 ou 20 questions, votre niveau, vos leviers prioritaires et le temps que vous pourriez gagner avec l'IA et l'automatisation.
Faire le test →Parlez-moi directement. Dites-moi votre projet, votre équipe, ce que vous cherchez à construire. Si cela correspond à ce que je fais, nous poursuivons la discussion hors de la page.
Freelance briefs, business and AI conversations, partnership ideas, or a coffee to talk shop. Pick the channel that fits.