Blog
Highlights from the Currai blog: the posts worth reading first.
A complete, code-first guide to turning OpenAI Realtime voice conversations and text-to-speech generations into readable Currai User Stories and correctly nested traces.
A step-by-step guide to importing completed Retell AI calls into Currai with signed call-ended webhooks—without adding capture code to the live voice agent.
A step-by-step guide to importing completed Vapi calls into Currai with an authenticated webhook—without adding capture code or sharing a Vapi private API key.
Browse implementation notes, observability guides, product decisions, and workflow ideas by topic.
Open-source agent analytics gives teams a way to inspect findings, adapt quality rules, and choose how conversation evidence is operated and retained.
Read moreCompare operating responsibility, customization, costs, and retention to decide whether to run Currai yourself or use its hosted service.
Read moreEvaluate Postgres HNSW vector search with exact-search recall, latency, filters, memory, index build cost, ef_search, reranking, and downstream RAG quality.
Read moreEvaluate code-interpreter agents across planning, files, generated code, sandbox execution, artifacts, correctness, security, recovery, latency, and cost.
Read moreDesign an observable Airbyte-to-LangChain RAG ingestion pipeline with incremental sync, deterministic chunking, embedding lineage, retries, deletion handling, and retrieval evals.
Read more