Kwal

Kwal's voice agents initiate outbound calls to candidates using telephony APIs (likely Twilio or similar) and route conversations through a natural language understanding pipeline that interprets candidate responses in real-time. The system converts speech-to-text, processes intent via LLM inference, and routes to appropriate dialogue branches based on candidate answers, enabling multi-turn conversations without human intervention.

Kwal analyzes candidate responses during voice calls using LLM-based evaluation against configurable qualification criteria, generating real-time scores based on experience level, skills match, availability, and salary expectations. The system likely maintains a scoring rubric that weights different factors (e.g., 30% skills, 25% availability, 25% salary fit, 20% communication) and produces a structured qualification output that recruiters can use for pipeline prioritization.

Kwal extracts candidate availability from voice conversations and automatically creates calendar invites by integrating with recruiting platforms (likely Greenhouse, Lever, or Workday) and calendar systems (Google Calendar, Outlook). The system parses temporal references from speech (e.g., 'I'm free Tuesday afternoon' or 'next week works better'), converts to structured time slots, checks recruiter availability, and sends confirmation to both parties without manual scheduling.

Kwal maintains conversation context across multiple turns of dialogue, enabling the voice agent to reference previous candidate answers, ask follow-up questions, and adapt questioning based on responses. The system likely uses a state machine or prompt-based context window that tracks conversation history, candidate profile data, and dialogue state, allowing natural follow-ups like 'You mentioned you worked at Company X — how long were you there?' without re-asking basic information.

Kwal converts candidate speech to text in real-time using a speech recognition API (likely Google Cloud Speech-to-Text, Azure Speech Services, or Deepgram) with domain-specific vocabulary adaptation for recruiting terms (job titles, company names, technical skills). The system likely maintains a custom vocabulary list that improves recognition accuracy for industry-specific terminology and candidate names, reducing transcription errors that could impact qualification scoring.

Kwal extracts key candidate information from voice conversations and call transcripts, converting unstructured speech into structured data fields (name, email, phone, experience level, desired salary, availability, skills, etc.). The system uses LLM-based entity extraction with recruiting-specific schemas, mapping candidate statements to standardized fields that can be imported into ATS or CRM systems, enabling downstream automation and analytics.

Kwal handles regulatory compliance for voice calls including automatic consent capture, call recording with encryption, and audit logging. The system likely implements jurisdiction-specific compliance (TCPA for US, GDPR for EU, PIPEDA for Canada) by obtaining explicit consent before calling, storing recordings securely, and maintaining audit trails of all calls for regulatory review. Call recordings are likely encrypted at rest and in transit, with access controls limiting who can listen to or download recordings.

Kwal generates analytics dashboards and reports on voice agent performance, candidate funnel metrics, and hiring outcomes. The system tracks metrics like call completion rate, qualification rate, interview scheduling rate, and time-to-hire, enabling recruiters to measure agent effectiveness and identify bottlenecks. Reports likely include funnel visualization (candidates screened → qualified → interviewed → offered → hired) with drill-down capability to analyze specific cohorts or time periods.