November 2025: A Month of Major Updates

November was our biggest month yet. We shipped 8 major features that fundamentally change how you can conduct research with Terac. From real-time video interviews to AI-powered research synthesis, here's everything that's new.

Live Interview Experience

We completely rebuilt the technical infrastructure that powers interviews. The result is a dramatically better experience for both researchers and participants.

Live transcripts appear in real-time as participants speak. No more waiting for post-interview transcription—you can read along as the conversation happens, take notes in context, and identify key moments as they occur.

Video and audio streaming with adaptive bitrate technology maintains quality across varying network conditions. Participants can turn on their camera for a face-to-face feel.

Screen sharing lets participants share their entire screen or a specific application window. The AI interviewer can see and reference what's on screen, asking contextual questions like "I notice you hesitated there—what were you thinking?"

End-to-end encryption (E2EE) protects all interview sessions. Video, audio, and screen shares are encrypted before leaving the participant's device, and encryption keys are never accessible to Terac servers.

Deep Research

You've conducted dozens of interviews. The transcripts are full of valuable insights. But turning all that qualitative data into actionable findings? That's where most research projects stall.

Deep Research is an AI-powered system that analyzes your interview data at scale and produces structured insights and reports automatically. When you trigger a run, the system:

1. Reviews your research guide and project context
2. Identifies the key questions your research should answer
3. Gathers all relevant interview transcripts and notes
4. Generates patterns, themes, and notable quotes
5. Synthesizes everything into a structured report with visualizations

You can watch the process unfold in real-time, and reports include auto-generated charts and visualizations. Whether you have 10 interviews or 100, Deep Research handles the volume.

AI-Powered Research Guide Editor

Creating a great research guide is both an art and a science. Our new AI-powered editor makes this process faster and more collaborative.

Chat with AI to build your guide conversationally. Describe what you're trying to learn, and the AI will suggest questions, recommend probe points, and help you structure topics logically. This isn't just auto-complete—it's a collaborative partner that understands research methodology.

Upload files and images directly into your guide. These become available to show participants during interviews, grounding discussions in concrete artifacts. The AI interviewer can reference these materials during the conversation.

Full version history tracks every change to your guide. You can see exactly what changed between versions, restore any previous version with one click, and never lose work.

Project & Organization Context

AI is only as good as the context it has. Project and Organization Context lets you provide background information that helps the AI understand your research environment—product documentation, company background, research objectives, previous findings, and domain knowledge.

Organization-level context applies to everything in your organization. Project-level context applies to all studies within that project. Once set, context persists across all studies, so you don't need to re-explain your product for every new research guide.

When context is set, the AI asks better questions, generates more relevant insights, uses correct terminology, and connects findings across studies.

Reports & Insight Tracking

Research generates insights. But insights scattered across transcripts, notes, and team conversations don't drive action. We've built a complete reports and insights system to solve this.

Create and share reports with key insights, supporting evidence, direct quotes, visualizations, and recommendations. Reports are shareable via link with access controls.

Real-time insight generation lets you watch the extraction process as it happens. New insights appear as they're generated, and you can pause and adjust parameters if needed.

Insights mapped to your guide are automatically tagged to relevant questions, making it easy to see which areas have rich findings and which might need more data.

Advanced filtering lets you search, filter by study or date range, sort by relevance or recency, and tag insights for organization.

Enhanced Panel & Invitation Management

Great research depends on great participants. We've rebuilt panel and invitation management to make this work faster and more transparent.

Every participant invitation is now tied to a specific sourcing run. You can see exactly where each participant came from, when they were invited, and how they progressed through your study.

New features include an interactive map view for visualizing participant geography, richer participant profiles with demographics and past participation data, and an internal dashboard showing invitation status, conversion rates, and bottlenecks.

Smarter AI Interviews

The best research interviews don't follow a script—they follow the conversation. We've completely rebuilt our AI interviewer to conduct natural, free-flowing conversations instead of rigid scripts.

Previously, our system used a state-machine architecture: ask Question 1, wait for answer, move to Question 2. This worked, but it felt robotic.

The new system gives the AI interviewer freedom to:

• Follow interesting threads when a participant mentions something relevant
• Ask natural follow-ups instead of moving on after one answer
• Return to topics if something comes up later that relates to earlier questions
• Adapt to the participant's communication style

Screen sharing now works throughout the interview, and data collection happens conversationally without breaking the rhythm. Your research guide still defines topics and depth required—the AI just achieves them through natural conversation.

Demo Interviews & Guide Previews

Launching a research study can feel high-stakes. How do you know the interview will flow naturally before your first real participant joins?

Demo Interviews let you test any research guide with a single click. The AI interviewer will ask questions from your guide, respond to your answers, and follow up naturally—just like it would with a real participant.

Demo mode works with unpublished drafts, so you can test changes before committing. Generate preview links to share with colleagues for feedback. Demo interviews are stored separately from real participant data.

---

What's Next

We're heads down on the next wave of features. If you have feedback on any of these updates or ideas for what we should build next, we'd love to hear from you.

Try Terac free or book a demo to see these features in action.