Skip to content
ClaudeClaude

How Anthropic uses Claude in GTM Engineering

Sales reps drown in administrative work, from digging through scattered documentation to answering customer emails late into the night. Jared Sires, GTM Product Manager, shares how he went from account executive with zero coding experience to building CLAFTS (Claude Drafts), an AI email assistant powered by the Claude API that drafts customer replies in his own voice, with Claude Code. Check out the full case study to learn more: www.claude.com/blog/how-anthropic-uses-claude-gtm-engineering

Jared Siresguest
Jun 5, 20262mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Anthropic’s AE builds Claude-powered email drafting system for GTM efficiency

  1. Jared Sires describes how Claude helped him transition from a traditional startup account executive role into a go-to-market architect role by lowering technical barriers to building tools.
  2. He introduces CLAFTS (Claude Drafts), a Claude API–powered workflow that generates customer email drafts using a system prompt plus pattern matching and context retrieval.
  3. The tool integrates with internal and external knowledge sources (e.g., Google Docs and web URLs) so the model can pull relevant documentation without the AE manually searching Slack or drive folders.
  4. CLAFTS reportedly saves Jared two to three hours per day and has been used to send thousands of emails, enabling more consistent and technically accurate customer communication.
  5. He emphasizes the broader impact: non-engineers can prototype product-like solutions and partner with senior engineers to productionize them, accelerating GTM operations.

IDEAS WORTH REMEMBERING

5 ideas

Context-aware drafting turns email into an engineered workflow.

CLAFTS reframes AE email response as a repeatable pipeline: define a system prompt, retrieve relevant context, and generate a draft aligned to role and customer needs.

Integrations matter as much as the model.

By pulling from Google Docs, websites, and internal documentation, Claude can answer with up-to-date product details without the AE hunting through Slack threads and folders.

Role- and persona-specific system prompts improve consistency.

Capturing the sender’s name, role (e.g., account executive), and what they help customers with creates reliable tone and scope across many customer interactions.

AI assistance can meaningfully reduce GTM operational load.

Jared reports saving 2–3 hours daily, suggesting that high-volume customer communication is a strong early ROI area for Claude-enabled automation.

LLMs can enable non-technical builders to prototype real tools.

Jared attributes his career shift to being able to design solutions himself and then collaborate with senior engineers to take them “the final stretch.”},{

WORDS WORTH SAVING

5 quotes

If you told me I was going to be a go-to-market architect at Anthropic a year ago, I would be pretty surprised.

Jared Sires

I don't think I've ever had the technical chops to be in these conversations, but with Claude, I'm able to design and build things that allow me to see things differently.

Jared Sires

I was probably working until eight, nine o'clock at night just answering emails back and forth, scouring through Slack, uh, knowledge bases, Google Docs, Google Drives.

Jared Sires

That's when I asked myself the question: how could I bring Claude into the loop?

Jared Sires

I was able to move into this role, go-to-market architect, and now my career I feel like has almost changed completely.

Jared Sires

Role transition: AE to GTM architectCLAFTS (Claude Drafts) email generationSystem prompts for sales workflowsContext retrieval via Google Docs and web URLsReplacing manual search across Slack/Docs/DriveTime savings and email throughputLowering technical barriers for non-engineers

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.