Every piece you need in one place.

Train on your knowledge

Add any combination of websites (one URL or an entire sitemap), PDFs, Word docs, plain text, Notion pages, or a CSV of FAQs. We chunk, embed, and index everything automatically, then re-train on a schedule you choose.

• ✓ Daily, weekly, or manual re-indexing
• ✓ Per-source visibility & pruning
• ✓ 30+ languages, including RTL

Bring your own model

Pick the right large language model for the job: Anthropic Claude, OpenAI GPT, Google Gemini, Groq-served Llama, or Mistral. Change the model on any bot at any time without re-training your sources.

• ✓ Per-bot model overrides
• ✓ Cost dashboards per provider
• ✓ Fallback chain if a provider is down

Persona and guardrails

Give the bot a name, tone, and personality. Whitelist or blacklist topics, force citations from your sources, and add custom refusal messages. Detailed transcript reviews help you tune the personality fast.

Actions and workflows

Let the bot do more than answer. Trigger a webhook to create a ticket, capture a lead in your CRM, or escalate to a human in Slack. Define inputs the bot needs to gather before firing the action.

Channels everywhere

Embed the bubble on your site, install it as a Slack or Discord app, route it to WhatsApp Business, plug it into Intercom or Zendesk, or call it from your own backend through our REST and streaming APIs.

Insights that teach you

See top questions, bot confidence scores, dead-end conversations, sentiment trends, and per-source helpfulness. Click any answer to view the exact passages the model used to compose it.

Security by default

EU and US data regions, SSO, SCIM, audit logs, configurable retention, and customer-managed keys on the Scale plan. We never train shared models on your data.

Developer-friendly

Typed REST API, websockets for streaming, generous webhooks, a public schema, and SDKs for JavaScript, Python, Go, and Ruby. Everything you can do in the dashboard, you can do in code.

99.95% uptime SLA

Multi-region deploys, automatic failover, and a public status page so you always know what's happening.

Streaming responses

Token-by-token streaming keeps replies snappy. Users see the first word in under 300 ms on most plans.

Rate limits you control

Set per-bot and per-user caps so a viral spike never wrecks your monthly budget.

Human handoff

One click for the user, one channel for your agents — Slack, email, or a dedicated inbox in the dashboard.

Knowledge gaps

Every "I'm not sure" gets logged with the user's question so you can add the missing answer in seconds.

Versioning

Snapshot a bot before changing the prompt or sources. Roll back instantly if metrics dip.