Bakiano
001The price of everything in Venezuela.
Live market data across supermarkets, retail, real estate and telecom — connected by an AI analyst that brings all sources together to build a clearer picture of Venezuela’s economy. Over 200,000 rows tracked daily, normalized to USD at the official BCV rate, with every movement recorded.
-
AI analystA connected view of the economyCross-references data from all sources and sectors to connect market signals and help explain what is happening across Venezuela’s economy.
-
ChatAI analyst over live dataAsk in plain language and get real prices, never invented ones. Quotes your whole shopping list in one pass and shows its work while it searches.
-
Shopping listThe basket, optimizedEvery item priced at every chain, stores ranked by coverage and total, and a two-stop split suggested only when it genuinely saves money.
-
AlertsWhat changed todayReal price moves, net of currency noise. Follow products, filter by chain and magnitude, compare against yesterday or the fortnight.
-
DashboardSeries, minimums and candlesPer-product charts: median, daily minimum, bands and distribution candles — every point traceable to the exact products inside it.
-
MenuThe week, costedPlan the week's meals and price them against one chain's real catalog. What the cooking consumes and what you pay at the register are two numbers — you see both.
-
Real estateSearch with historySearch listings by zone, price and surface across more than a million historical records from the major networks.
Technical pipeline
From infrastructure to the product. Open a stage to go deeper.
InfrastructureGCP · Terraform · Docker · GitHub Actions
Terraform defines the jobs, schedules, storage, warehouse, IAM, and networking. Changes ship through pull requests; the deployment workflow builds the changed Docker images and applies infrastructure changes after merge. Cloud Run hosts the collection jobs and the product.
Network accessTailscale · gateway VMs
Tailscale gateways support the collectors that need Venezuelan network access. The gateway VMs start and stop on a schedule around the collection window. This is supporting infrastructure for scraping, not a stage that transforms the data.
Scraping & orchestrationCloud Scheduler · Cloud Run Jobs · Scrapy / nodriver
Collectors are organized by vendor and domain. Cloud Scheduler triggers the Cloud Run jobs, and each run produces a CSV snapshot. Scrapy or browser automation handles collection depending on the source; refresh cadence varies by domain.
Archive & ingestionGoogle Cloud Storage · Cloud Functions
CSV snapshots land in GCS, organized by domain, vendor, and date. An object-finalize event triggers the loader, which appends records to BigQuery and records the run’s health. The archive retains the source snapshots for reprocessing and backfills.
Data warehouseBigQuery · raw / staging / product layers
Raw tables preserve the collected values and history. Staging holds cleaned, deduplicated data; product tables and serving views support analysis and the application. Operational tables track vendors, collection runs, and exchange rates. Supermarket and retail raw data is partitioned by ingestion date.
Transformations & currencyScheduled SQL · idempotent MERGE · BCV rates
Scheduled queries process a rolling three-day window, allowing recent missed runs to recover on the next execution. They clean the data and produce daily summaries. Raw prices stay unchanged: serving views derive USD values from vendor currency rules and the BCV rate associated with the ingestion date.
AI enrichmentGemini batch · Vertex AI · BigQuery
A separate branch from raw data classifies new supermarket products: product type, brand, units, weight, and other catalog attributes. Classification is stored separately from prices. Current prices are joined from the latest raw partition, so enrichment does not freeze yesterday’s price into the catalog.
Serving & analystNext.js · Cloud Run · Gemini on Vertex AI
The product combines warehouse views and catalog enrichment for chat, dashboards, and a scoped data API. The AI analyst uses a defined set of tools rather than unrestricted SQL. Metered, byte-capped queries and a shared result cache control warehouse usage; run-health monitoring closes the operational loop.