Even though modern AI coding assistants can handle complex, single-shot requests, it's more reliable to build an application in stages. First, build the core functionality, then add secondary features, and finally add tertiary elements like download buttons. This iterative approach prevents the AI from getting confused.

Resist building complex, multi-agent systems from day one. Instead, start with a single agent and build its skills based on actual workflows. Add sub-agents only when a clear productivity need arises. This approach is more effective than scaling for what looks impressive.

A practical framework for developing agentic AI is to first map the human workflow. Break down the task into discrete steps, identify which ones can be automated, ensure the necessary data is available, and then build the underlying tools and code blocks. Don't start with the technology; start with the human process.

Don't try to build a complex AI agent from day one. SaaStr's AI VP of Customer Success started as a basic project management portal to replace a clunky tool. Its advanced, agentic capabilities were layered on over months as real user needs became clear post-launch.

Counter the hype by following a clear progression: Skills -> Workflows -> Agents. If you cannot create a reliable, deterministic workflow with a predefined path, an autonomous agent attempting to improvise will almost certainly fail. This structured approach mitigates risk and ensures reliability.

Don't ask an AI agent to build an entire product at once. Structure your plan as a series of features. For each step, have the AI build the feature, then immediately write a test for it. The AI should only proceed to the next feature once the current one passes its test.

Instead of immediately building an AI agent, founders should first manually perform the target workflow as a service. This process allows them to deeply understand the pain points, map edge cases, and acquire initial clients. Only after mastering the job manually should they incrementally add vertical agents to automate specific steps.

The rapid pace of AI development is overwhelming. Instead of trying to automate everything, the most effective approach is to maintain a playful curiosity. Focus on experimenting with AI to solve a single, specific, repeatable problem in your workflow, making adoption both manageable and effective.

Onboard users (or yourself) to an AI agent like a new human teammate. Start with easy, high-frequency tasks (e.g., summarizing Slack threads). Progress to harder, multi-step tasks (e.g., scheduling a meeting based on replies). Only then, attempt to automate an entire workflow (e.g., running daily growth experiments).