delivXchange was acquired by DirectOrders. The AI-native platform we built is now powering DirectOrders' online ordering system. This case study documents the technical foundation that enables AI native operations. Try the demo to see it in action.
We model work as tasks an agent can own. Each agent has a clear goal like intake, routing, operations, or support. Agents can call tools and talk to each other when needed.
Real time speech in and speech out with streaming. The voice agent hands off to other agents when the call needs action. We keep latency low with lightweight turns and partial results.
We use MCP to plug tools and data into agents in a standard way. Tools include internal APIs, data fetchers, vector stores, and job runners. MCP lets us add or remove tools without rewiring the whole system.
We use RAG to ground answers in our data. Content is split, embedded, and stored in a vector store. We track versions. We add safety rules so the agent uses only allowed sources.
We let the system plan a few steps ahead when useful. Plans are short and checked at each step. Agents can reflect and try a different path if the result is weak.
We ship agents behind feature flags. We run offline evals on tasks and also shadow live traffic. We log inputs and outputs with scores. We keep a feedback loop for humans in the loop.
We monitor token use, latency, and error rates. We set guardrails for PII, tool scope, and rate limits. We prefer simple fallbacks over complex retries.
TypeScript and Node for services. React for ops UI. WebSockets or Server Sent Events for live updates. Postgres for source of truth. Vector store for embeddings. Queue for jobs. Infra with containers and CI and CD. This can change as we learn.
This foundation powers DirectOrders, an AI-native platform for restaurant and retail ordering. The technical shape remains the same: agents own tasks, voice enables real-time interaction, and RAG grounds decisions in live data. Explore the online ordering system or try the interactive demo.