An index of the major platform capabilities and deep-dive documentation. Click any feature to read a detailed explanation of how it works, why it matters, and what to expect on the roadmap.
20 articles
Authentication verifies identities and controls access to the platform, covering user logins, API credentials, token rotation, and revocation to keep customer data secure.
Read article02How the responder assembles context, retrieves knowledge, builds prompts, runs safety checks, and returns fast, cited answers — the end-to-end flow behind every customer interaction.
Read article03How the embeddable chat widget is styled, sandboxed, previewed, and securely configured so it fits customer sites while remaining safe and performant.
Read article04Layered defenses — rate limits, CSP, and circuit breakers — that protect the platform from abuse, control costs, and keep service reliable for all customers.
Read article05End-to-end observability: trace IDs, token/cost accounting, per-org dashboards and alerts to understand usage, cost spikes, and ROI of AI features.
Read article06Operational visibility into ingestion status, per-source stages, reprocess controls, and live logs so content teams can keep the knowledge base accurate without engineering help.
Read article07How tenant isolation, per-org branding, and scoped configuration keep customer data private while enabling per-customer features and limits.
Read article08Processes and tooling to keep locale files complete, block deploys when critical translations are missing, and auto-generate per-locale sitemaps for better search visibility.
Read article09Processes for export and deletion requests, soft-deletes with recovery windows, background job processing, and audit trails to meet GDPR/CCPA needs.
Read article10Secure machine-to-machine integrations: client credentials, scopes, hashed secrets, rotation, per-integration quotas and audit trails.
Read article11Invitations, role assignments, audit logs, and safeguards to prevent lockouts — a full membership lifecycle tailored for enterprise teams.
Read article12In-product feedback controls (thumbs, stars, comments) that surface signals to analytics and alerting so you can iterate on assistant quality quickly.
Read article13The multi-stage ingestion pipeline (fetch, extract, chunk, embed, index) with partial reprocess controls, versioning, and sensitive-content handling.
Read article14Definition and safe rollout of assistant behaviors: instructions, knowledge scope, canary rollouts, versioning, and audit trails for safe iteration.
Read article15Get an email the moment a visitor asks for a human, the moment your AI hits a question it can't answer, and a Monday digest that summarises the week — so nothing slow-rots in a dashboard nobody opened.
Read article16Tickets, alerts, and AI replies in the chat tool your team already lives in. Stop bouncing between email, dashboard, and inbox.
Read article17Turn the same content your AI uses into a public, searchable docs site — same source, two surfaces. SEO-friendly pages that deflect tickets before they're ever filed.
Read article18Your assistant answers wherever your customers ask — embedded widget, support email, Slack workspace, or wherever you connect it next.
Read article19One-click data exports, deletion requests, and audit logs to handle GDPR, CCPA, and SOC 2 obligations without writing a custom script.
Read article20Let your assistant *do* things, not just retrieve information. Look up an order, book a meeting, file a Jira ticket, refund a purchase — wired to your real systems.
Read article