Oronts AI Assistant
The production Mastra agent system answering on this site: five agents, four tools, streaming responses, and a hardened API layer. Try it in the corner of this page.
At a glance
- 5
- Specialized agents in production
- 4
- Lead-pipeline tools behind the quote agent
- 100%
- Tool calls authenticated through the internal proxy
- 0
- Prices invented by the agent, by design
The Challenge
AI capability claims are cheap. The honest proof is an agent system running in production, with the same constraints clients face: rate limiting, CSRF, prompt injection surface, cost control, observability and a real lead pipeline behind it.
Our Approach
Built on Mastra with five specialized agents (quote, chat, vision, voice, analytics) and four tools that structure conversations into qualified leads: proposal submission, call scheduling, email drafting and conversation summaries. Responses stream over the Vercel AI SDK. The API layer applies rate limiting, CSRF, origin checks and request tracing; tool calls route through an authenticated internal proxy into the Oronts API. The agent never invents prices: it qualifies, structures and hands over to a human.
System Architecture
System Architecture: Visitor, Assistant UI, /api/chat streaming/, Mastra Router, Quote Agent, Chat / Vision / Voice / Analytics, Tools: proposal, call, email, summary, /api/proxy/, Oronts API
Tech Stack
Key Outcomes
- Live on every page of oronts.com: the proof is one click away
- Qualifies leads conversationally, then hands over to a human
- Hardened API surface: rate limits, CSRF, origin checks, tracing
- Same architecture we implement for client agent systems
The Result
A working answer to the question every buyer should ask an AI vendor: show me yours. The assistant on this page is the deployment; its design decisions are documented in our guides.