Building Earmark: How a Two-Person Team Turned Meetings into Finished Work

Guests

• Mark Barbir – CEO, Earmark
• Sanden Gocka – Co-Founder, Earmark

What we cover in this episode:

• How Earmark differs from generic AI notetakers by producing finished work, not just summaries
• The pivot from Apple Vision Pro presentation coaching to a web-based meeting assistant
• Running multiple agents in parallel during live meetings
• Template-based agents: Engineering Translator, Make Me Look Smart, Acronym Explainer
• Personas that simulate absent team members (security architect, legal, accessibility)
• Why ephemeral mode (no data storage) became a selling point for enterprise
• Reducing AI costs from $70/meeting to under $1 through prompt caching
• Why GPT 4.1 still beats newer models for prose quality in their use case
• The limits of vector search for analysis questions across meetings
• Building agentic search with multiple retrieval tools (RAG, BM25, metadata queries, bespoke summaries)
• Designing for product managers as the extreme user to solve for everyone
• Their vision for an AI chief of staff that goes beyond automating deliverables

Resources & Links

• Earmark — Productivity suite where the work completes itself
• ProductPlan — Roadmapping tool where both founders previously worked
• Granola — AI notetaker mentioned for comparison
• Assembly AI — Speech-to-text service used by Earmark
• OpenAI API — LLM provider with prompt caching support
• Cursor — AI code editor with build integration in Earmark
• V0 by Vercel — AI prototyping tool with build integration in Earmark

Chapters

00:00 Introduction to Earmark Founders 00:28 Background and Experience 01:05 What Does Earmark Do? 01:23 AI and Productivity 03:09 Comparing Earmark to Competitors 03:41 Earmark's Unique Features 05:53 Templates and Personas 10:06 Technical Details and Development 17:12 Early Product Versions and Challenges 28:44 Understanding Prompt Caching 29:49 Managing Multiple Tools and Costs 30:59 Optimizing Transcript Summarization 35:11 Challenges with Context and Reasoning Models 38:10 Innovative Search and Retrieval Techniques 44:06 Creating Actionable Artifacts from Meetings 48:30 Ensuring Quality and Managing Hallucinations 58:20 Future Vision for AI Chief of Staff