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.
Tool calling is a protocol, not magic. Build the loop with validation, permissions, idempotency, parallelism, recovery, and trace-based evaluation.
Read moreA practical architecture for image URLs, base64 inputs, multiple images, structured extraction, privacy, and production evaluation.
Read moreImage generation needs more than a prompt and an endpoint. Design for model capability, moderation, retries, provenance, cost, and evaluation.
Read moreInstrument an AI agent with OpenTelemetry using useful trace boundaries, GenAI attributes, model and tool spans, secure OTLP export, sampling, and production verification.
Read moreA step-by-step guide to building an AI FAQ chatbot on top of your existing docs, from ingestion and retrieval to evaluation and safe rollout.
Read more