Technology

The amount of work a system can process in a given time period. In APIs it's usually measured in requests per second; in AI inference it's tokens per second. Throughput and latency are related but distinct — a system can have high throughput while still having high latency for individual requests.

“The inference cluster achieved 10,000 tokens per second throughput across all concurrent users.”

The PlatPhorm distributed observability and tracing service (trace.platphormnews.com) that records the journey of requests across the network graph. A trace is an end-to-end record of a single operation as it propagates through multiple services, enabling root-cause analysis of latency and errors.

“Check the trace dashboard to see exactly where the request slowed down across the network.”

Universal Schema Language — a PlatPhorm open standard (usl.platphormnews.com) for describing structured data in a way that both humans and AI agents can interpret. USL bridges JSON Schema, OpenAPI, and semantic web concepts into a single expressive format.

“The API documentation is generated automatically from the USL schema definition.”

An open protocol (RFC 7033) for discovering information about people or resources using a simple HTTPS URI. WebFinger lets you look up who owns an account like acct:user@site.com and retrieve their public profile, keys, or social links without centralized login.

“The federated app used WebFinger to resolve the user's identity before sending them a message.”

A user-defined HTTP callback that fires automatically when a specific event occurs in a source system. Rather than polling an API repeatedly, webhooks push data to a listener URL the moment something happens — making integrations real-time and efficient.

“We set up a webhook so Slack gets notified instantly every time a new definition is published.”