We have raised $7.5M to help grow your business
Answrable
Sign up
← BLOG/ENGINEERING

Inside Answrable's database-per-tenant architecture

It took six days to go from shared storage to isolated PostgreSQL schemas per tenant.

Infrastructure Team
Infrastructure Team—Systems & Security
SEP 14, 2026
Answrable
tenant data

Inside Answrable's database-per-tenant architecture

Scaling to thousands of enterprise call streams demanded zero cross-tenant contamination. Here is how we automated dedicated PostgreSQL schema provisioning, RLS policies, and encrypted audio bucket storage.

Agents are the ones building now. They need voice primitives.

Until now, building an AI voice agent required cobbling together disparate vendors: a speech-to-text transcriber, an external LLM completion API, a text-to-speech voice synthesizer, and a legacy SIP trunk aggregator.

This chained architecture created 2,000ms+ roundtrip latencies, robotic speech turn jitter, and clipped conversations whenever callers tried to interrupt. By engineering our own 8-billion parameter foundation model (Answrable HCM-1), we achieved native full-duplex speech-to-speech comprehension with sub-180ms reflexes.

agent-workflow.tsAnswrable HCM-1 8B
import { AnswrableAgent, tool } from "@answrable/core";

export const clinicReceptionist = new AnswrableAgent({
  model: "answrable-hcm-1-8b",
  temperature: 0.2,
  turnReflexLatencyMs: 180,
  systemPrompt: "You are the autonomous voice receptionist for CareClinic...",
  tools: [
    tool({
      name: "verifyInsuranceAndBookSlot",
      description: "Checks real-time calendar availability and schedules patient",
      parameters: { patientId: "string", desiredTime: "string" },
      execute: async ({ patientId, desiredTime }) => {
        return await db.appointments.create({ patientId, slot: desiredTime });
      }
    })
  ]
});

What's included in Answrable GA

HCM-1 Foundation Model

8B parameter speech-to-speech weights with human-grade turn taking.

Direct Carrier SIP

Connect your own carrier numbers with zero transcoding overhead.

With full-duplex interruption handling, callers can speak naturally, pause to think, or change topics mid-sentence without robotic clipping.

What's next for voice telephony

We are expanding our regional edge points of presence across North America, Europe, and Asia Pacific to guarantee sub-50ms carrier jitter worldwide.

In the meantime, we want to see what you build with these tools. Tag us on X, send us feedback, and we're in Discord too.
▶MORE FROM ANSWRABLE