One Codex prompt screens 25,000 LinkedIn founders and auto-drafts personalized outreach emails
paw_lean · x · 2026-09-28
Developer @maxjendrall demonstrated an end-to-end agent outreach workflow: a single natural-language prompt to Codex finds San Francisco LinkedIn users with 'Founder' in their title, uses an LLM to verify each is a real founder from their full profile (and exclude Anthropic employees), generates personalized invite emails for an OpenAI Codex for Founders event on Oct 5, caps the list at 25,000 people, schedules sends across multiple email accounts via the emailsend connector, and returns a final approval table. A showcase of LLM agents automating search, verification, generation, and scheduling.
More from coding & agent
- Creator hooks Claude to MCP and lets it autonomously edit motion graphics — aziz4ai · 2026-09-28
- Writer lets Codex decide his book's margins, printing test to follow — santiviquez · 2026-09-28
- kindling runs every MCP server in its own Firecracker microVM, frozen at 0 RAM until called — Ascci52 · 2026-09-28
- PurzBeats demos Sentinel, an agent framework that builds its own nodes — PurzBeats · 2026-09-28
- Jev seen as fit for high-level robotics orchestration: fast schema beats LLM lag — ai · 2026-09-28
- Apple's free on-device fm paired with decision model Jev beats big-model routing in tests — jasonkneen · 2026-09-28