Oil-Market Intelligence System for CrudeFlash
CrudeFlash
CrudeFlashA full oil-market intelligence platform for CrudeFlash — a deep, Supabase-backed system that pulls live WTI data from authoritative public sources and turns it into structured, plain-English signals across deliberately designed, editorial-grade dashboards. A hybrid rule-engine-plus-LLM design keeps every reading grounded in real numbers: the model only phrases what the rules detect, so it can't invent a claim.
Oil-market intelligence is scattered across EIA releases, CFTC Commitments-of-Traders reports, rig-count tables, price feeds, and a constant churn of geopolitical headlines — each in its own format and cadence. Reading it by hand is slow and error-prone; most tools either drown people in raw numbers or let an AI 'explain' the market with claims the data doesn't support — and few give a trader a disciplined way to apply that market picture to their own decisions.
- 01
Built automated ingestion from authoritative public sources — EIA weekly petroleum stocks, CFTC disaggregated futures positioning (WTI, Brent, RBOB, heating oil), Baker Hughes North America rig counts, WTI spot prices, and GDELT geopolitical news — on scheduled (pg_cron) pipelines into a structured PostgreSQL database.
- 02
Built a deterministic signal engine that scans the data and emits typed conditions backed by numeric evidence — stock draws and builds, SPR effects, positioning shifts, rig-count moves — each paired with a plain-English note on why it matters.
- 03
Layered an LLM that only phrases those rule-detected conditions in a calm, institutional tone — it cannot introduce a claim, and falls back to deterministic templates if it's unavailable — so commentary stays tied to the actual figures.
- 04
Surfaced it through live dashboards — an EIA report, markets-intel, a CFTC positioning-bias read, a geopolitical/conflict feed, and an auto-drafted weekly briefing (saved as a draft for review, never auto-published).
- 05
Designed the entire front end deliberately, for an institutional, editorial feel — a considered typographic system (Inter Tight for the interface, JetBrains Mono for figures and data, a serif for long-form analysis), a restrained palette, custom data-visualisation (charts and sparklines), and measured motion — so a data-dense terminal reads as calm and trustworthy rather than cluttered.
- 06
Added a private workspace designed to help traders apply those same fundamentals to their own edge — a clean, disciplined representation of the market picture rather than anything exotic — kept behind tiered gated access, with admin tooling for provisioning and content. The platform runs on a deep backend of 13 edge functions and 40+ database migrations.
- Automated ingestion of EIA stocks, CFTC positioning, Baker Hughes rigs, WTI prices & GDELT news (pg_cron)
- Deterministic signal engine — typed conditions backed by real numeric evidence
- LLM phrases only what the rules detect — it can't invent a claim (with template fallback)
- Live dashboards: EIA report, markets intel, CFTC positioning bias, geopolitical/conflict feed
- Deliberate, institutional front-end design — typographic system (Inter Tight · JetBrains Mono · serif), restrained palette & motion
- A private workspace designed to help traders apply the same fundamentals to their own edge
- Auto-drafted weekly briefing — saved as a draft for human review, never auto-published
- Deep Supabase backend — 13 edge functions, 40+ migrations, tiered gated access & admin tooling
A running, multi-surface intelligence platform — 13 edge functions and 40+ database migrations deep — that turns scattered market data into structured, plain-English signals, refreshes automatically as new EIA, CFTC, rig-count, price, and geopolitical data lands, and gives traders a disciplined space to apply that picture to their own decisions. Every reading traces back to real figures, and the weekly recap arrives as a review-ready draft rather than an unchecked auto-post.
A deep, full-stack automation-and-AI build, not a dashboard skin: scheduled multi-source ingestion, a real data backend, a deterministic signal layer, an LLM kept strictly to phrasing, and a trader workspace grounded in the same fundamentals — all wrapped in a deliberately designed, institutional-grade interface. It's how we build AI that decision-makers can trust: grounded in the numbers, with a human gate before anything ships.
// Want a system like this for your business?
Frequently Asked Questions
Related case studies
StaysDxb FinOps Portal
A FinOps portal for Dubai short-stay operator StaysDxb (37+ units) — a fully operational operations dashboard, an event-driven automation layer, and “Joey”, a read-only AI ops assistant the team runs from Slack. Joey answers questions and drafts guest messages across bookings, payments and units; the platform handles the recurring finance and lead work. Together they save the team at least four hours a day.
Website Redesign, Technical SEO & Ads Tracking for Atom Inspections
Ongoing web, SEO and Google Ads work for Atom Inspections, a Dubai property inspection and snagging consultancy. We redesigned the homepage, built a dedicated Ads landing page with conversion tracking that fires on real clicks, repaired the site's structured data and cut homepage weight by 76%. Since November 2025 its Domain Rating has gone from 7 to 18, its index has shrunk from about 226,000 junk URLs to about 110, and it has earned its first citations in Google's AI Overviews.
Platform Build & 12-Month SEO Turnaround for LYM Real Estate
A full Next.js real-estate platform for LYM Real Estate, plus a 12-month SEO turnaround. After building the platform, we took over a stalled, outsourced SEO effort in mid-2025 — and from a near-zero base grew it into a real organic-and-AI search presence: Domain Rating from 1 to 16, monthly impressions from ~11K to 150K+, and citations across every major AI engine.