1
1 Comment

We're consolidating under Supernormal and building an AI agent

Hey IH,

Colin here from Supernormal. We just wrapped up a rebrand and wanted to share what changed.

Background

For the last 9 months, we've been building Radiant, a Mac app that captures meetings and turns them into deliverables. The product worked, agencies liked it, but we realized we were limiting ourselves by positioning around meeting capture.

What users actually cared about was getting work done. Client emails, research briefs, decks, spreadsheets. The meeting capture was useful context, but the value was in completing the actual tasks.

What's changing

We're consolidating everything under the Supernormal brand and expanding beyond the Mac app into a full AI workspace. Instead of one tool that does meeting capture plus outputs, we're building multiple AI agents that complete different types of work:
- Documents- AI agents that draft, edit, and format documents

  • Emails - Automated email composition and management
  • Presentations- Deck creation and design
  • Spreadsheets - Data analysis and spreadsheet generation
  • Research - Comprehensive research compilation
  • Visual assets - Image and video creation

The key difference: these agents don't just start tasks, they complete them. You review the work instead of doing the work. That's possible because they pull context from your meetings, emails, and workspace.

Target

Same users we've always served: agencies, consultants, account managers, knowledge workers at time-selling businesses. Just broader use cases beyond meetings.

Happy to answer questions.

posted to Icon for group Artificial Intelligence
Artificial Intelligence
on January 29, 2026
  1. 1

    Consolidating under Supernormal and pivoting to an AI agent — that's a bold but clear-eyed move. The meeting assistant space is crowded but an agent that acts on meeting outcomes rather than just transcribing them is a genuinely different product.

    The quality of that agent's instructions will make or break it. Meeting agents fail when their objectives are fuzzy — unclear when to escalate, unclear output format, no explicit constraints on scope. I built flompt to address this at the prompt layer: 12 semantic blocks (role, objective, constraints, output_format, chain_of_thought, etc.) that compile to Claude-optimized XML. Would be interested to hear what your agent's core instruction architecture looks like.

    A ⭐ on github.com/Nyrok/flompt would mean a lot — solo open-source founder here 🙏

Trending on Indie Hackers
6 weeks solo, 2 rejections, finally live but nobody told me marketing would be this hard User Avatar 122 comments Building ExpenseSpy solo, no funding — launching June 17 on iOS & Android User Avatar 47 comments I just wanted to taste AI coding tools. A week passed. User Avatar 15 comments Building LinkCover – Day 3: Payment is live. No more building, time to sell. User Avatar 15 comments I Was Bypassing Every App Blocker, So I Built One That Fights Back User Avatar 11 comments We built a tool that tells you who your competitors are and where they're weak. No signup. Just describe your product User Avatar 10 comments