Software Engineering & Digital Products for Global Enterprises since 2006
CMMi Level 3SOC 2ISO 27001
View all services
Staff Augmentation
Embed senior engineers in your team within weeks.
Dedicated Teams
A ring-fenced squad with PM, leads, and engineers.
Build-Operate-Transfer
We hire, run, and transfer the team to you.
Contract-to-Hire
Try the talent. Convert when you're ready.
ForceHQ
Skill testing, interviews and ranking — powered by AI.
RoboRingo
Build, deploy and monitor voice agents without code.
MailGovern
Policy, retention and compliance for enterprise email.
Vishing
Test and train staff against AI-driven voice attacks.
CyberForceHQ
Continuous, adaptive security training for every team.
IDS Load Balancer
Built for Multi Instance InDesign Server, to distribute jobs.
AutoVAPT.ai
AI agent for continuous, automated vulnerability and penetration testing.
Salesforce + InDesign Connector
Bridge Salesforce data into InDesign to design print catalogues at scale.
HumanDISC
AI-powered behavioral assessments and DISC profiling for smarter hiring.
View all solutions
Banking, Financial Services & Insurance
Cloud, digital and legacy modernisation across financial entities.
Healthcare
Clinical platforms, patient engagement, and connected medical devices.
Pharma & Life Sciences
Trial systems, regulatory data, and field-force enablement.
Professional Services & Education
Workflow automation, learning platforms, and consulting tooling.
Media & Entertainment
AI video processing, OTT platforms, and content workflows.
Technology & SaaS
Product engineering, integrations, and scale for tech companies.
Retail & eCommerce
Shopify, print catalogues, web-to-print, and order automation.
View all industries
Blog
Engineering notes, opinions, and field reports.
Case Studies
How clients shipped — outcomes, stack, lessons.
White Papers
Deep-dives on AI, talent models, and platforms.
View all resources
About Us
Who we are, our story, and what drives us.
Co-Innovation
How we partner to build new products together.
Careers
Open roles and what it's like to work here.
News
Press, announcements, and industry updates.
Leadership
The people steering MetaDesign.
Locations
Gurugram, Brisbane, Detroit and beyond.
Contact Us
Talk to sales, hiring, or partnerships.
Request TalentStart a Project
AI & Machine LearningHR Tech & Recruitment

Building an immersive, real-time multimodal AI interviewer with LiveKit, screen recording, and advanced LLM tool calling.

We engineered an immersive multimodal AI Interview Agent for ForceHQ using LiveKit, giving the AI the ability to present media, track time, and record sessions via LLM Tool Calling.

LiveKit · WebRTC · OpenAI
Client: ForceHQ
AI Interview Agent for ForceHQ using LiveKit

Project Overview

ForceHQ needed an immersive, highly interactive AI Interview Agent capable of conducting real-time, human-like interviews. The AI needed to do more than just speak—it had to interact visually with candidates by presenting multimedia objects, track interview time limits, transcribe the conversation live, and record the entire session (screen and audio) for later review by human recruiters.

LiveKit Multimodal Streaming

We built a highly responsive WebRTC pipeline using LiveKit to handle ultra-low latency audio and video streaming between the candidate and the AI.

Advanced LLM Tool Calling

We utilized advanced LLM Tool Calling to give the AI agent agency over the interview environment. The AI can dynamically trigger multimedia popups and manage the interview timer based on the conversational context.

Have a similar challenge?

Our experts can help you build custom integrations and plugins tailored to your business workflows.

Book a free consultation

Real-Time STT Transcription

Integrated live Speech-to-Text (STT) for real-time transcription, allowing the AI to process candidate answers instantly and displaying closed captions on the UI.

LiveKit Egress for Cloud Recording

Implemented LiveKit Egress to capture and composite the audio, video, and shared multimedia objects into a single MP4 file, securely saving the interview to the cloud for human recruiters to review later.

Key Challenges

01

Challenge 1

The AI needed agency to control the UI, such as showing technical diagrams or code snippets during the interview.

02

Challenge 2

Achieving ultra-low latency audio/video streaming so the conversation felt natural and fluid.

03

Challenge 3

Recording the entire session (audio, video, and screen) reliably in the cloud without degrading the candidate's local browser performance.

04

Challenge 4

Ensuring the AI could track time and gracefully transition between different phases of the interview (e.g., Intro, Technical, Behavioral, Outro).

Results & Outcomes

10,000+
Hours Saved
100%
Automated Recording
15+
Disciplines Supported
<500ms
Interaction Latency
FAQ

Frequently Asked Questions

Common questions about this topic, answered by our engineering team.
During the conversation, if the AI determines it needs to show a technical diagram, it emits a specific JSON "tool call" to the frontend via LiveKit data channels. The React frontend interprets this signal and renders the multimedia object instantly.
Local recording (like MediaRecorder API) relies on the candidate's hardware, which can cause lag or fail if the browser crashes. LiveKit Egress handles the compositing and recording entirely on the server-side, ensuring a highly reliable, high-quality MP4 file regardless of the candidate's device.
The AI is equipped with a background timer tool. We inject the current timestamp and elapsed time into the LLM's system prompt at regular intervals, allowing the AI to naturally wrap up questions and move to the next phase when time is running short.
Yes. We utilized advanced STT models fine-tuned for specific technical domains. Because the platform supports over 15 disciplines, the AI dynamically loads the appropriate jargon dictionary for the specific interview type (e.g., Software Engineering vs. Financial Modeling).
Absolutely. We built a robust interruption handling mechanism. If the candidate starts speaking while the AI is talking, the system instantly halts the TTS audio playback, clears the AI's audio buffer, and listens to the candidate, mimicking natural human conversation.
Have a similar challenge?

Let's build your success story.

A 30-minute call with a principal engineer. We'll discuss your challenges, propose architecture, and outline a roadmap.

Talk to a strategist
Have a similar project? Let's discuss your requirements.
Book a call
EmailWhatsApp