TUTORIALS
Build a support agent in 20 minutes
A hands-on tutorial: wire a retrieval-backed support agent with guardrails and tracing from scratch.
RESEARCH
Evaluating agents without ground truth
Reference-free evaluation lets you score agent quality when you do not have labelled answers.
PRODUCT
Introducing Guardrails 2.0
Guardrails 2.0 brings policy-as-code, streaming enforcement, and per-tool scopes to every Nexora agent.
RESEARCH
Measuring hallucination rate in production
A practical framework for detecting and tracking hallucinations once your agent is live.
PRODUCT
Observability that speaks "agent"
Traces, token budgets, and replay — built for non-deterministic runs.
ENGINEERING
Streaming responses without the jank
Backpressure, flush cadence, and the 41ms p95 we hold in production.
ENGINEERING
Tracing across multi-agent systems
Following a single request as it fans out across a swarm of cooperating agents.