Assembler — Voice Agentic Systems

Voice AI can talk. Businesses need it to act. Assembler turns business intent into reusable, executable voice-agent workflows through a simple flow: Describe → Assemble → Run. A prompt tells a model what to say. An Assembler Blueprint defines what it is allowed to do: the workflow, data, tools, rules, connections, and outcomes. A shared runtime executes these Blueprints, so each business does not require a separate, hard-coded orchestration system. AssemblyAI provides the real-time voice interaction layer; Assembler manages business actions. Six starter workflows cover Auto Repair, Ecommerce Support, Real Estate, Restaurant, IT Helpdesk, and Property Management. Our recorded Auto Repair browser demo shows a brake-risk request triggering deterministic safety enforcement. The runtime executes escalate_issue, records the outcome as escalated, and the agent continues responding after the tool result. A separate deployed Harbor Table Restaurant integration test verified Google Calendar availability, booking persistence, Calendar event creation, and Google Sheets synchronization. This is server/integration evidence, not a second recorded voice conversation. Its configuration includes Europe/London scheduling, confirmation calls, and customer feedback. Engineering verification includes 53 passing automated tests, a passing TypeScript check, and a successful production build. The production application and source code are publicly accessible. Assembler targets service businesses handling recurring calls, and agencies deploying agents for clients. This hackathon MVP demonstrates a reusable workflow layer with observable execution; it does not claim that all six starters have received identical live testing.