Run your GTM through Codex
How do you run your GTM through Codex? Bryant McCombs, an account director at OpenAI who also builds GTM tooling, shows how he wired Codex to the Salesforce CLI and the tools he already lives in, so the post-call busywork is drafted before he hears about it and he just reviews. What you'll learn: How Bryant connected Codex to Salesforce, Gmail, Slack, and internal docs, and drives most of it from his phone A morning triage skill that reads P0 to P2 emails and drafts replies for him to approve A transcript-to-closeout skill that takes a raw call transcript, figures out the right account and opportunity, creates follow-up tasks, drafts emails, routes Slack messages, and once generated a context-aware customer proposal from Salesforce data he didn't ask for Why the shift is from multi-turn chat toward long-horizon tasks that finish across surfaces Why human review still matters (accountability is the durable skill) and how to find the highest-impact points in a workflow and add determinism there Sources & further reading: Run long horizon tasks with Codex (OpenAI Developers, official) https://developers.openai.com/blog/ru... - the plan, edit, run, repair loop behind the closeout skill Work with Codex from anywhere (OpenAI, official) https://openai.com/index/work-with-co... - phone-driven Codex with local host access and approve-before-send Salesforce CLI Command Reference (Salesforce Developers) https://developer.salesforce.com/docs... - the CLI surface Codex drives for Salesforce hygiene Measuring AI ability to complete long tasks (METR) https://metr.org/blog/2025-03-19-meas... - independent benchmark behind the move to long-horizon work More from Deepline: Event recap: 6 GTM teardowns from top teams https://deepline.com/blog/gtm-ai-nyc-... This talk, written up https://deepline.com/blog/gtm-ai-nyc-... Quickstart https://deepline.com/quickstart Use cases https://deepline.com/use-cases 0:00 Intro and background 1:34 Key GTM automation use cases 3:05 The Salesforce hygiene problem 4:35 Connecting Codex to GTM tools 6:02 Moving beyond multi-step workflows 7:32 Account closeout automation demo 9:02 Automated Slack messages for routing 10:30 Mobile-first GTM workflow 12:02 Attaching photos and drafts from your phone 13:40 Q&A: human in the loop 15:05 Q&A: the review process 16:33 Closing thoughts GTM + AI NYC Lightning Talks, hosted by Deepline. Full playlist: • GTM + AI NYC Lightning Talks (June 30, 2026) Deepline is one CLI for your GTM data: enrichment, scraping, and sequencing across 44+ providers, with every run logged to a database you own. Try it from Claude Code or Codex at deepline.com (use code GTMASCODE).

Why Europe Still Refuses Air Conditioning

The AI data center oversupply crisis is coming | Ed Zitron

How Ramp let 400 reps build their own custom GTM tools

The World's Most Important Machine

The Hidden Opportunity of Robotics Datasets | James Wigglesworth

How Notion built customer hubs: one shared context layer for reps and GTM agents

My Documentary is Coming Out THIS WEEK!! – why you should watch it

What rebuilding AlphaGo teaches us about self-play, RL, and future of LLMs - Eric Jang

NVIDIA Just Upgraded Quantum-AI Hybrids — Data Centers Will Never Be the Same

Anti-Aging Expert: This Reverses Gray Hair, Fixes Health & Prevents Cancer!

How Modal built one GTM data pipeline to rule them all

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Martin Shkreli Discusses Meta Selling AI Compute — Is This A Sign Of Overcapacity?

Inside Nemotron & NVIDIA’s AI Lab | Bryan Catanzaro

Billionaire's WARNING: I'm SELLING. The Crash Is Already Here!

40Hz Binaural Gamma Waves - Ultra Deep Concentration

OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491

Stop asking which data provider is best. Your ideal waterfall is unique to you

L8 Principal's Agentic Engineering Workflow

