The value of an AI agent is unlocked through a mental shift. Instead of treating it as a passive tool like a dashboard, actively engage with it as a coworker. SaaStr's team talks to their agent and bounces ideas off it, incorporating it into daily creative sessions and workflows.
SaaStr avoids a single, monolithic AI. Instead, they create distinct agents (VP of Marketing, VP of Customer Success) and treat them as separate entities. This architectural choice keeps them focused and allows for tailored interactions without creating a complex, all-knowing system.
The sophisticated AI agent '10k' didn't start with a grand vision. It was created to solve a founder's personal annoyance: manually copy-pasting data from various dashboards into Notion every Sunday night. This highlights starting with a small, tangible problem.
An AI agent's recommendations are based solely on the data it's given, not on creative preferences, office politics, or favorite agencies. This makes it a powerful tool for objective decision-making, ensuring that marketing campaigns are driven by performance data rather than human intuition.
Instead of attempting to build a fully-featured AI from the start, SaaStr advocates for "stair-stepping." This means building and perfecting one specific workflow at a time (e.g., a dashboard, then a campaign generator). This iterative approach avoids being overwhelmed and ensures steady, manageable progress.
To ensure optimal performance, each AI agent at SaaStr is given one primary objective. The AI VP of Marketing's goal is to "own the number." This singular focus ensures all its data analysis, campaign ideas, and actions are goal-seeking and aligned, preventing it from getting overloaded.
To safely deploy a powerful AI agent, create clear guardrails. SaaStr distinguishes between tasks the agent can perform autonomously (pulling data, generating ideas) and actions that require human approval (sending a mass email). This two-layer approach builds trust and prevents potentially costly mistakes.