Skip to content
Li ZhenXi, home page

The AI agent platform

AI agent platform

The AI agent platform I run.

Primustech's AI agent platform gives facility teams two agents: an operations agent that answers from the IoT platform's live readings, and a document assistant that answers from company documents. I deploy and run it on Google Cloud. Follow a request through it, see the AI infrastructure layer by layer, and switch on the lens to see which parts are mine.

Try being on call: a simulated incident on this platform

Operations agent

Answers facility managers from live building readings. A manager agent plans; a data-engineer agent queries the IoT platform and crunches the numbers.

Agno team on Cloud Run, Gemini on Vertex AI

Document assistant

Answers from a company's own documents, with citations: multi-stage RAG over Milvus, with a reranker on a GPU.

Cloud Run API and job, Milvus, Gemini via OpenRouter

Building data comes from Building IoT platform, the platform I run on GKE; it has a chapter of its own.

3
environments deployed the same way: dev, staging and production
2,014
BMS devices in the 50-storey demo building I built for the agents to query
AI agent platformPrimustech, 2026

Running an agentic AI platform

Infrastructure for the company's two AI products: an operations agent that answers from live building data, and a document assistant.

  1. Question

    from a facility manager

  2. Agent team

    Agno on Cloud Run

  3. Data

    live readings, documents

  4. Gemini

    Vertex AI, OpenRouter

  5. Answer

    traced with tokens and cost

  • Load and latency tests on the agent API
  • Token cost tracked per request
  • Models compared on latency and cost
Read the case
AI agent platform

The operations agent: a small team of AI agents that answers facility managers from live building data.

ENTRYSERVICESMODELS AND DATADELIVERY AND NETWORKFacility teamchat, web, appLoad balancerCloud Armor, TLSOperations agentAgno team, Cloud RunDocument assistantRAG API, Cloud RunDocument workerCloud Run JobIoT platformlive readings, GraphQLVertex AIGeminiOpenRouterGemini, Grok, embeddingsRerankerbge-reranker-v2-m3 on a GPUMilvusvector searchMongoDBsessions, metadataRedis queuedocument jobsCloud Storageuploaded filesLangfusetraces, tokens, costGitHubmergeCloud Buildone per environmentArtifact RegistryimagesSecret Managerkeys, parametersShared VPCfirewall, NAT, DNS
  • AI agent platform
  • Building IoT platform
  • no stripe: shared infrastructure

Step 1 of 8

A question

A facility manager asks something like "which floors ran warm this afternoon?"