Greg Isenberg's 49 tips for building an AI-native company, from knowledge base to agents
FinanceYF5 · x · 2026-11-15
FinanceYF5 recaps Greg Isenberg's guide to building an AI-native company: turn company knowledge into AI memory, repetitive work into Skills, and let agents execute and improve continuously.
Key points:
- Build a company brain: Obsidian as a second brain in Markdown; Wispr for voice capture and auto-archiving; a central knowledge base for clients, finance, pricing and processes; Granola for meeting transcripts.
- Stop hallucinations: fact files defining what agents can cite; a style file with 50 good examples, 20 bad ones and banned words.
- Engineering: track all files in GitHub; unify task rules via CLAUDE.md / AGENTS.md; cross-session memory with claude-mem and mem0; aggregate ads/CRM/payments data with Airbyte + ClickHouse; accumulate proprietary data competitors can't access.
Related event: Greg Isenberg shares 49 rules for building an AI-native company(12 posts)→
More from coding & agent
- 159k Lovable Apps Scanned: Many Expose Chats and Passport Data via Misconfigured Supabase APIs — bibryam · 2026-11-15
- Rust + wgpu rewrite renders 250k-file dependency graph at 60fps on M3 — IgorCarron · 2026-11-15
- Agents Orchestration Is Mostly Token Furnaces Now, Argues Dev — pvncher · 2026-11-15
- DataTalksClub Founder Launches Full-Time AI Academy in Germany, Tuition State-Funded — Al_Grigor · 2026-11-15
- How far can a company take AI? Greg Isenberg's 49-point playbook — FinanceYF5 · 2026-11-15
- TensorFold PR fixes MCP servers blocked by macOS sandbox over dyld framework loading — AIFlow_ML · 2026-11-15