Don't expect an AI agent to invent a successful sales process. First, have your human team identify and document what works—effective emails, scripts, and objection handling. Then, train the AI on this proven playbook to execute it flawlessly and at scale. The AI is a scaling tool, not a strategist from day one.

AI won't magically fix a broken strategy. The key is to identify what already works—your best emails, responses, and processes—and use that proven data to train the agent. This approach scales your known successes rather than hoping AI will invent a winning formula from scratch.

The overhead of maintaining personal AI agents is too high for most employees. The successful model, seen at Shopify and Ramp, is a centralized, company-wide "super-agent" managed by a dedicated team, ensuring it remains reliable and useful for everyone.

Klaviyo's internal "Dark Factory" system uses a team of agents to take a high-level prompt, decompose it into specs and engineering subsystems, write code, and establish API contracts. This automates the software toolchain, from prototyping to load testing, with minimal human intervention.

To scale her system, a power user taught her AI agents to create new agents independently. The parent agents handle the entire setup and training process, leading to faster, more effective deployment without any human intervention.

Sales organizations can run leaner by empowering their teams to train custom AI agents. These agents handle analysis, surface risks, and automate workflows, reducing the need for a large RevOps headcount and an expensive, complex software stack.

Once you have successfully configured an AI agent with the right tools, models, and prompts, you can simply clone it. This allows you to rapidly create a 'fleet' of AI employees, each of which can be tasked with a different specialized function, such as one for email outreach and another for checking its work.

Prioritize using AI to support human agents internally. A co-pilot model equips agents with instant, accurate information, enabling them to resolve complex issues faster and provide a more natural, less-scripted customer experience.

Visual AI tools like Agent Builder empower non-technical teams (e.g., support, sales) to build, modify, and instantly publish agent workflows. This removes the dependency on engineering for deployment, allowing business teams to iterate on AI logic and customer-facing interactions much faster.