Transparent by design — see exactly what happens
What happens when someone talks to a daita agent, the technology behind each step, and where your data lives. No black box.
From a question to a completed task
A streaming agentic pipeline — grounded in your knowledge and catalog, bounded by guardrails, observable end to end.
- 1A visitor reaches outWeb chat, voice, phone or WhatsApp — one agent with shared memory across every channel.
- 2Verified, encrypted ingressThe request enters daita over encrypted channels; phone & WhatsApp webhooks are cryptographically verified before anything runs.
- 3Claude reasons and plansAnthropic Claude reasons through the task in a streaming agentic loop and decides which knowledge and tools it needs.
- 4Grounds in your knowledge and catalogTwo-stage retrieval finds candidates, then a neural reranker (EU) orders them by true relevance. Answers are cited, never invented.
- 5Acts with real toolsSearches your catalog, builds carts, checks orders, books calendar slots, captures leads and updates your CRM — real actions, not just talk.
- 6Responds in text or neural voiceReplies in text and natural neural voice by default — or a live speech-to-speech call if you opt in — and can even navigate the page for the visitor.
- 7Records to an EU database, escalates when neededEvery interaction is written to an EU database with an immutable audit log; when human judgement is needed, it hands off with the full conversation.
The stack inside, by layer
Best-in-class components, each with a clear role — and a clear data-residency posture.
Anthropic Claude
Reasoning, language understanding, tool use (agentic loop)
BM25 + Jina Reranker (Berlin)
Two-stage retrieval over your knowledge, with citations
ElevenLabs neural voice
Natural spoken replies — the default voice
OpenAI gpt-realtime
Live speech-to-speech voice — optional, owner-enabled
Twilio · Web · Shopify
Phone, WhatsApp, embeddable web widget & Shopify app
Firestore (eur3, Europe)
Leads, bookings, transcripts and immutable audit logs
Resend (SPF/DKIM/DMARC)
Branded, fully deliverable confirmations and calendar invites
Self-hosted observability
Latency, tool use and errors — your data, no third-party analytics
Where your data lives
daita is EU-first. Data at rest is stored in the EU by default (Firestore eur3) and semantic search runs in the EU (europe-west1). Some AI processing — the language model and opt-in live voice — currently runs via vetted subprocessors under EU-approved safeguards (DPF/SCCs), and is migrating to Claude on Vertex AI in the EU. Anything that can leave the EU is opt-in and clearly flagged.
Want this for your business?
Talk to a live agent on this site right now, or get your own in minutes.