it_support · saas · workflow
Solo.io uses agentgateway to govern, secure, and observe AI agent traffic to MCP servers and LLMs
As the number of internal MCP servers at Solo.io grew, the team needed a centralized way to aggregate, secure, and observe AI agent traffic without modifying individual servers or agents. LLM access through Vertex AI also provided no visibility into usage patterns or per-user, per-model costs.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Employee triggers support agent
Employees ask questions in corporate Slack by mentioning @Support.
Tools used
agentgatewayClaude CodeCursorVertex AIGrafanaClaude
Outcome
By routing traffic through agentgateway, Solo.io can now track LLM usage and spending at individual and organization levels, analyze tool usage distribution, and govern both MCP and LLM traffic without modifying agents or backend services.
What failed first
Before agentgateway, LLM access routed through Vertex AI provided no visibility into usage patterns or per-user, per-model costs.
Results
Cost replacedtrack usage and spending at both individual and organization levels
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
agentic workflowai agentsupport agentchat transcriptknowledge basenamed customerproduction runtime claimedtools describedworkflow describedsoftwarecost reductionemployee productivitytechnical build writeupback office opsit supportagentic task executionrag answering