# How AI Agents Let GTM Teams Scale — Justin Joyce, Cloudflare

## Executive summary

Justin Joyce details how Cloudflare utilizes a three-pillar approach powered by AI agents to solve scaling issues in traditional Go-To-Market (GTM) operations. The core problem—that manual processes and knowledge gaps limit efficiency—is addressed by building self-service capabilities, automating data analysis, and proactively pushing insights to users. This framework allows non-technical staff to query complex data using 'skill files' and enables reps to access expert-level information via an internal agentic workspace (Cloudflare OS).

## Key takeaways

- The GTM Scaling Problem: Traditional GTM processes suffer from the 'context gap' (switching between different customer calls) and the 'expert gap' (inconsistent execution among reps), leading to significant inefficiency. Back-office teams often rely on manual work in Excel or limited dashboards, which fail to meet all operational needs.
- Pillar 1: Scaling Analysis via Skill Files: To empower non-SQL users, the team built role-specific 'skill files.' These allow business users to ask questions of data directly and quickly, eliminating bottlenecks that previously required a dedicated data engineer. This capability is used both for back-office analysis and building GTM skills.
- Pillar 2: Scaling Insight (Pushing the Story): Instead of forcing users to search dashboards, insights are proactively delivered through synthetic weekly summaries. This is achieved by transforming data dimensions (time, manager, metric) and using a multi-agent workflow: a first draft agent, a second reviewer agent for veracity checks, and a third 'tone agent' that crafts the message, ensuring risks and opportunities are weighted equally.
- Pillar 3: Self-Service via Cloudflare OS: The internal tool, Cloudflare OS, is an agentic workspace running on Workers and Durable Objects. It allows GTM teams to perform complex tasks—such as building QBR decks, account plans, or forecast briefs—by interacting with curated expert skills without needing manual intervention.

## Technical details

- Agentic Architecture: The insight generation uses a multi-agent workflow: Data -> Draft Agent (calls MCPs) -> Reviewer Agent (verifies data veracity) -> Tone Agent (crafts message using multi-shot prompts). Observability is maintained by tracking every LLM call.
- Cloudflare OS Implementation: The self-service workspace utilizes Cloudflare Workers and Durable Objects for compute and persistent storage, enabling reps to pull data and execute jobs using curated expert skills.
- Data Structuring: To simplify analysis for AI agents, the raw data is transformed by dimension (time, manager, metric), allowing for both wide-to-long and long-form trend processing.

## Practical implications

- Implementing a three-pillar strategy (Analysis, Insight, Self-Service) can significantly increase GTM team efficiency and standardize execution.
- Focusing on skill curation is critical; embedding business knowledge into 'skill files' allows non-technical users to interact with complex data systems deterministically.
- The process of automating reporting by pushing synthesized stories (Pillar 2) ensures that key performance indicators reach all stakeholders, regardless of their dashboard usage habits.

## Topics

Sales Operations, AI Agents, Data Engineering, Go-To-Market Strategy, Workflow Automation, Cloudflare OS, Workers / Durable Objects, Salesforce

Source: https://www.youtube.com/watch?v=Qw_tC68KKes