Observability
Observability for agent API traffic: what per-agent attribution actually requiresA researched map of how teams watch AI agents calling REST and general APIs in 2026: the application-layer trace platforms, the API-gateway layer where identity actually lives, and what genuine per-agent attribution requires.9 min readObservability articles and guides
Observability for agent API traffic means knowing which agent made each call, under which key, and how it behaved. Retries, latency cliffs, and failure patterns. These guides cover the tooling landscape and the numbers from 1.2 million tool calls through Elva’s gateway.
5 posts, newest first · UpdatedMCP
MCP logging and observability tools, comparedA researched map of how teams actually watch MCP traffic today: the protocol's own shift to OpenTelemetry, the observability platforms that added MCP tracing, and the gap between debugging a server and running one.8 min readMCP
MCP servers are infrastructure. Run them like it.Weekend demos die on Monday. What we learned running MCP servers for real agent traffic, and what changes when a tool call has an SLA.8 min readMCP
23 tools, 4 agents, zero surprisesPer-agent activity, tool-level latency, and catching the schema gap before Claude does.7 min readMCP
What 1.2 million agent tool calls taught us about timeouts, retries, and the true cost of a vague error messageNinety days of production MCP traffic in numbers: retry storms, timeout cliffs, and why one ambiguous error string cost more than any outage did.4 min readShip notes, monthly
One email with what shipped and what we learned. Unsubscribe anytime.
Ship APIs anything can call
Humans, tests, partners, agents. One catalog, one contract, one place.