Sales

How Christian's Agency Builds Cold Email Lead Lists with Agent Hermes

Built by Christian (@coldemailchris) · · Source: X

Quick answer

Christian's cold email agency built Hermes, an AI agent the whole team messages in Slack. It sources companies, finds contacts, enriches them, validates emails, scrapes unusual sources and writes account research. It works from a private repo of skill files.

Result: According to Christian, Hermes now builds the lists for almost all of their clients. Its lists qualify at a much higher rate than lists built the old way, and it costs less to run than any database or workflow tool they've used, Clay included.

What they built

Christian runs a cold email agency. He says it has built $70M+ in pipeline for 100+ B2B companies. Every campaign starts with a lead list, and his team built an AI GTM agent called Hermes to build those lists. Anyone on the team can message Hermes in Slack, from a laptop or a phone, at any hour. It sources companies, finds the right people, enriches them, validates emails and researches accounts. Christian says his own part was mostly writing the skill files it works from.

How it works

  • Always on: Hermes runs on a VPS, so it doesn't depend on anyone's laptop being open. The whole team uses one Slack channel, and a single shared Codex account does the actual work behind it.
  • Connections: Christian says it's wired into 20 to 40 databases and enrichment tools. Together they cover TAM sourcing, scraping, enrichment, email validation, research and personalization. For standard lists, it pulls leads through the Clay CLI.
  • Skills repo: A private GitHub repo holds one written instruction file per task, such as how to scrape a source or how to qualify a lead. Hermes reads these before every job. Christian says a good skill covers the source, the steps, the fields to pull, the checks for a good row and what to do when a step fails.
  • Request flow: Hermes asks clarifying questions first. Then it returns a small sample with sources and evidence for each data point, and only runs the full list once someone approves it. This catches a bad brief before it burns credits.
  • Briefs: Every request has five parts: company profile, target person, custom yes/no checks (for example, "3+ SDRs" or "a live pricing page"), output fields and list size.
  • Beyond databases: Hermes scrapes public sources that no lead database offers as a filter. One example was a public group listing construction companies that build with mass timber.
  • Account research: On request, it writes a 300 to 500 word report on each account. Claude Code then writes the email copy from that research, and the team reviews everything before it sends.

The result

Christian says Hermes builds the lists for almost all of their clients. He says the lists qualify at a much higher rate than their old ones, and that Hermes costs less to run than any database or workflow tool they've used, Clay included. He's also clear about the downsides: it goes down sometimes, skills need updating when APIs change, and it had to be built from scratch.

How to build something similar

  • Pick one type of list you build every week and write a single skill file for it. Include the steps, the fields to pull, the checks for a good row and fallbacks for when a step fails.
  • Run the agent on an always-on server, connected to a chat app your team already uses, so anyone can send it a request.
  • Have the agent return a small sample for approval before it runs a full list. That way a bad brief costs a few rows, not thousands.
  • Make one person responsible for fixing broken skills and integrations as APIs change.

The original post

https://x.com/i/article/2108786567380635648 Our team has built $70M+ in pipeline for 100+ B2B companies, off 10M+ cold emails. Every one of those campaigns starts with a list. Today, the lists for almost all of our clients get built by 1 AI agent our team built, called Hermes. Anyone on the team can message it in Slack, from a laptop or a phone, at any hour. It sources the companies, finds the people, enriches them, validates the emails, and researches the accounts. Here's exactly how it's set up, what it's connected to, and what a request looks like from start to finish. What's inside: What Hermes is What it's connected to A request, start to finish How to write a request that works The lists Clay can't build Account research on autopilot Where Claude Code takes over The tradeoffs What Hermes is: Hermes is our AI GTM agent. Our team built it (full credit to them), and my part was mostly the skill files it works from. Where it lives. It runs on a VPS, a server that stays on 24/7. So it never depends on someone's laptop being open. How the team talks to it. Through Slack. Everyone on the team messages the same agent in the same channel. Behind it sits 1 Codex account doing the actual execution, so the whole team shares 1 back end. Why that matters. Say a client needs a lead list and you're out on a walk. You open Slack on your phone, message Hermes, and the list is building before you get home. Most of the time we work from a computer, but the option is always there. What it's connected to: An agent is only as useful as what it can reach. The APIs. Hermes is wired into somewhere between 20 and 40 different databases and enrichment tools. That covers the full chain: TAM sourcing Scraping Enrichment Email validation Account research Personalization The Clay CLI. For standard lists, Hermes pulls through the Clay CLI. That's 1 of our default ways of pulling leads. The skills repo. This is the part that makes it ours. We keep a full GitHub repo of skills: written instructions for every task Hermes runs, from how to scrape a source to how to qualify a lead. That repo is probably worth a million dollars on its own, which is why we'll never show it publicly. Hermes reads those skills before every job, so it works the way our team works. A request, start to finish: Here's a real example I ran on camera. The prompt. "Build me a lead list of B2B SaaS companies with 10 to 100 employees. Find the VP of Sales, Head of Sales, or any senior sales role. Every company needs at least 3 SDRs or junior salespeople, and a live pricing page." Most databases can filter on the first 2 parts. The last 2 (3+ salespeople and a public pricing page) need actual research on every company. It asks before it runs. Hermes comes back with a few questions first, like which people to target and what the delivery format should be. If the prompt already covers it, you tell it to run off the original request. It shows a sample first. Before building the full list, it returns a small sample of companies. Each one comes with: The employee estimate Where that estimate came from (it pulls from multiple sources, including PitchBook) The live pricing page The evidence it's B2B The decision maker 3 salespeople, with their LinkedIn profiles and titles You check the sample, and if it's right, it runs the full list. That sample step saves a lot of wasted credits, because a bad brief gets caught after 5 rows, before it hits 5,000. Why the extra data points matter. A company with 3+ SDRs is paying people to book meetings. A live pricing page tells you how they sell and roughly what they charge. Those 2 fields turn a generic list into a list of companies that are clearly feeling the problem you solve. The qualification rate on lists like this is much higher than anything we pulled the old way. How to write a request that works: The agent is only as good as the brief you give it. Every request we send has the same 5 parts. 1. Who the company is. Industry, size, locati
Christian (@coldemailchris) · October 17, 2026 · View on X

Want to build something like this?

Join the Shipping Skool community free. Paid members get live bootcamp calls every week.

Join Shipping Skool — Free

More use cases

← All AI agent use cases