← back to case

Axera Flow · Case · Axera Flow

Multi-tenant WhatsApp AI for two markets

One n8n workflow, one Evolution instance, one Postgres database serving multiple markets — each with its own language, persona, and escalation rules. Adding a market is a database row, not a code fork.

Client
Axera Flow
Sector
Technology · Micro business
Timeline
Since May 2026
Status
In production

The problem

Axera Flow operates across two markets that speak different languages, expect different conversational tones, and fall under different privacy regimes (LGPD in Brazil; PIPEDA, Law 25, PIPA in Canada). Hand-rolling two separate bots would mean two codebases, two pipelines, and two credential sets — a non-starter for a one-person operation.

The solution

A multi-tenant architecture: one n8n workflow, one Evolution API instance, one Postgres database, with every market-specific setting (system prompt, language, owner phone, business name) stored as a row in a per-market config table. The webhook reads the instance from the inbound message and injects everything dynamically. Adding a market is a new row — no code fork.

Stack

  • n8n — Automação self-hosted, fluxos visuais
  • Claude API — Modelos da Anthropic via API (Opus, Sonnet, Haiku)
  • OpenAI API — GPT, embeddings, Whisper
  • Postgres — Relational database
  • Evolution API — Self-hosted WhatsApp gateway
  • Hetzner — VPS hosting

Measured impact

To add a market

9 min

Workflow changes

0

Markets (BR + CA)

2

Axera Flow · AI & automation, built and operated axeraflow.ai