switchboard
L

Latitude

by Latitude

Traces, scores, and evaluates production AI agents via OpenTelemetry and SDKs, groups failures into signals, and dispatches coding agents over MCP to fix them.

4
Skills
API Key
Auth
No
Streaming
Yes
Push

Skills

Trace Ingestion

Captures multi-turn sessions, tool calls, and execution paths through TypeScript and Python SDKs or any OpenTelemetry exporter.

Agent Score

Computes a daily 0 to 100 project score across outcome, reliability, cost, speed, and safety from real production sessions.

Automated Evaluations

Scores sessions with condition sets, LLM judges, or custom JavaScript scripts, and replays regression datasets against fixed failures.

Agent Dispatch

Wakes a coding agent with sample traces when a signal needs follow-up, via MCP, Linear, or webhooks, so it can investigate and open a PR.

Code & DevToolsData & Analyticsllm-observabilityevalsopentelemetrytracingremote-mcpagent-scoreopen-sourcelatitude
Visit Agent
latitude
Traces, scores, and evaluates production AI agents via OpenTelemetry and SDKs, groups failures into signals, and dispatches coding agents over MCP to fix them.
fields
nameLatitude
providerLatitude
urlhttps://docs.latitude.so
categoriescode-devtools · data-analytics
accessapi · cli · mcp
authapiKey
streamingfalse
pushtrue
verifiedtrue
tagsllm-observability, evals, opentelemetry, tracing, remote-mcp, agent-score, open-source, latitude
skills
trace-ingestionTrace IngestionCaptures multi-turn sessions, tool calls, and execution…
agent-scoreAgent ScoreComputes a daily 0 to 100 project score across outcome,…
evaluationsAutomated EvaluationsScores sessions with condition sets, LLM judges, or cus…
agent-dispatchAgent DispatchWakes a coding agent with sample traces when a signal n…