Tekst

Tekst ingests customer messages from multiple communication channels (email, SMS, chat, social media) and normalizes them into a unified message format before routing to workflows. The platform uses channel-specific adapters that translate protocol-specific metadata (sender IDs, timestamps, attachments) into a common schema, enabling downstream workflow logic to operate channel-agnostically without reimplementation per channel.

Tekst encrypts all customer messages at rest and in transit using TLS 1.3 for network transport and AES-256-GCM for storage encryption. The platform implements key management with per-tenant encryption keys, ensuring that even Tekst infrastructure cannot decrypt customer data without explicit key access. Encryption is applied at the message ingestion point before any processing, and decryption occurs only at the point of display or workflow execution.

Tekst provides a library of pre-written response templates that agents can use to quickly reply to common customer inquiries. Templates support variable substitution (e.g., {{customer_name}}, {{ticket_id}}) and conditional sections (e.g., show billing info only if category is 'billing'). Agents can search templates by keyword, create custom templates, and track template usage. Templates can be organized by category and shared across teams. The system suggests relevant templates based on message category or customer history.

Tekst maintains a complete conversation history for each customer across all channels and time periods, enabling agents to view full context when responding to new messages. The system automatically retrieves relevant past conversations (e.g., previous issues, purchases, complaints) and displays them alongside the current message. Context includes message text, attachments, resolution status, and associated tickets. Agents can manually search for specific past conversations or use AI-powered context suggestions (if enabled).

Tekst provides dashboards and reports showing key support metrics: message volume, response time, resolution time, customer satisfaction (CSAT), agent utilization, and SLA compliance. Metrics are aggregated by time period (daily, weekly, monthly), team, agent, and category. Reports can be scheduled and emailed automatically. The system supports custom metrics and KPIs via formula-based calculations. Data is visualized in charts (line, bar, pie) and tables for easy analysis.

Tekst uses rule-based and machine-learning-based categorization to automatically classify incoming messages by intent, urgency, or topic, then routes them to appropriate teams or workflows. The system learns from historical message labels and routing decisions, building a classifier that improves over time. Routing rules are expressed as a declarative workflow language that supports conditional logic (if-then-else), team assignment, priority escalation, and SLA-based queuing.

Tekst provides a workflow engine that executes multi-step automation sequences triggered by message events (arrival, categorization, customer response). Workflows are defined declaratively using a state machine pattern, supporting branching (if-then-else), loops, delays, and external action invocations (API calls, CRM updates, email sends). The engine maintains workflow state across message interactions, enabling context-aware responses and multi-turn automation.

Tekst provides pre-built connectors for popular CRM (Salesforce, HubSpot) and helpdesk (Jira Service Desk, Freshdesk) systems, enabling bidirectional data sync without custom API development. Integrations use webhook-based event streaming for real-time updates: when a message arrives in Tekst, customer data is fetched from the CRM; when a ticket is resolved in Tekst, the status is pushed back to the helpdesk. Integrations are configured through a UI with field mapping and transformation rules.

Tekst indexes all messages and metadata (sender, timestamp, channel, category) in a searchable store, enabling full-text search across customer conversations. Search results return message snippets with surrounding context (previous/next messages in the thread) to help support agents understand conversation flow. Search supports filters (by date, channel, customer, category) and sorting (by relevance, recency, priority). For encrypted messages, search requires decryption, adding latency.

Tekst enables support teams to assign messages to individual agents or team queues, with visibility into assignment status, SLA timers, and agent workload. Agents can claim messages from shared queues, reassign to colleagues, or escalate to supervisors. The system tracks assignment history and provides dashboards showing queue depth, average resolution time, and agent utilization. Assignments can be automated via workflow rules (e.g., route to 'billing' team if category is 'billing').

Tekst maintains immutable audit logs of all system actions: message access, encryption key usage, workflow executions, user logins, and configuration changes. Logs include actor (user/system), action, timestamp, and result (success/failure). The system generates compliance reports (GDPR data access, HIPAA audit trails, PCI-DSS access logs) that can be exported for regulatory review. Logs are stored separately from operational data and cannot be modified retroactively.

Tekst provides APIs and UI tools to export all customer data (messages, metadata, attachments) in a portable format (JSON, CSV) and to permanently delete customer records on request. Deletion is performed securely: encrypted messages are deleted along with their encryption keys, making recovery impossible. The system tracks deletion requests in audit logs for compliance verification. Export and deletion can be triggered manually or via API for programmatic integration with privacy workflows.

Tekst sends real-time notifications to agents when new messages arrive, SLAs are about to breach, or messages are assigned to them. Notifications are delivered via multiple channels (in-app, email, SMS, Slack) based on agent preferences. The system supports notification rules (e.g., 'alert me only for high-priority messages') and quiet hours (e.g., 'no notifications after 6 PM'). Notifications include message preview and action buttons (claim, assign, escalate) for quick response.