Get Started

AI Interview System

Build, run, and manage AI-powered interview workflows at scale.

The AI Interview System is a multi-tenant platform for creating, running, and evaluating AI-powered technical interviews. It provides a complete pipeline from interview creation to candidate assessment with human-in-the-loop approval at key stages.

The system is built around three layers: the REST/A2A API for integrations, the Agno agent runtime for AI planning and assessment, and the HITL workflow for recruiter oversight. From a single interview request to a completed assessment, everything runs as one coherent architecture.

Layer	Responsibility
API Gateway	REST endpoints, JSON-RPC 2.0 A2A protocol, webhook notifications, JWT/API-key authentication
Agno Agents	Skill validation, interview plan generation, real-time interview conduction, post-interview assessment
HITL Workflow	Recruiter approval gates for plan generation, interview scheduling, and assessment verdicts

What You Can Build

The AI Interview System powers real workflows built from the same primitives:

ATS Integration — Push interview requests from your Applicant Tracking System via REST or JSON-RPC
Webhook-driven pipelines — React to state changes (plan generated, approved, completed) via signed webhooks
Custom HITL interfaces — Build recruiter review tools that integrate with the approval workflow API
Assessment automation — Receive structured AI assessments and pipe them into your HR systems

API Reference

Complete REST endpoint documentation with request/response schemas.

A2A Protocol

JSON-RPC 2.0 and webhook integration guide for agent-to-agent systems.

Architecture

System design, Kafka events, multi-tenancy, and agent integration.

Start Building

The system is designed to scale with you from a single API call to production multi-tenant deployments.

Quickstart — Authenticate and create your first interview in under 5 minutes
A2A Protocol — Integrate your ATS or HR platform via JSON-RPC 2.0
Webhooks — Set a callbackUrl to receive real-time state-change events
HITL Workflow — Build custom recruiter interfaces against the approval API

bash

# 1. Create your first interview
curl -X POST http://localhost:3009/api/v1/a2a/interview \
  -H "X-API-Key: demo_api_key_12345..." \
  -H "Content-Type: application/json" \
  -d '{
    "candidateName": "Jane Smith",
    "candidateEmail": "jane@example.com",
    "position": "Senior Engineer",
    "level": "SENIOR",
    "skills": ["TypeScript", "React"],
    "jobDescription": "Join our platform team to build scalable web apps.",
    "callbackUrl": "https://your-ats.com/webhook"
  }'

# Response: { "runId": "...", "state": "VALIDATING_SKILLS" }

Built for Production

AI Interview System runs in your infrastructure, not ours.

Multi-tenant with row-level security at the PostgreSQL level
Horizontally scalable — all services include HPA manifests
Event-driven via Kafka for 10K+ events/sec throughput
Full audit trail via structured logging and Kafka event history
JWT + API Key + OAuth 2.0 authentication
HMAC-signed webhooks with exponential backoff retry

New to the platform? Start with the Authentication guide then follow the A2A Protocol overview to integrate your first external system.

Agentic software requires a new architecture.

AI Interview System is the platform for building it.

Was this page helpful?

NextQuick Start →