# Stop Using AI Agents Like Chatbots. (Do This Instead) Source: https://www.youtube.com/watch?v=3sXGt0MKmY8 Recap page: https://rapidrecap.app/video/3sXGt0MKmY8 Generated: 2026-01-26T14:04:01.712+00:00 --- ## Quick Overview To stop using AI agents like simple chatbots, developers should leverage them as collaborative partners by providing a detailed plan and defining verification steps, such as using custom slash commands like `/frontend-design` and integrating browser automation tools like Chrome DevTools for verification, instead of relying on sequential, unverified outputs. **Key Points:** - The main takeaway is to shift AI agent usage from simple chatbot queries to structured, planned workflows with defined verification, exemplified by building a Text-to-Image generator. - The workflow involves three steps: planning (using `/plan` mode), execution (using `/agent` mode), and verification, which can be automated using tools like Chrome DevTools. - The speaker demonstrates creating a custom slash command, `/frontend-design`, which encapsulates complex instructions for building high-quality UIs, moving beyond generic AI aesthetics. - Verdent's parallel execution capability allows multiple agents to work simultaneously, significantly speeding up complex development tasks compared to sequential execution. - The final product, an ImageGen app, successfully generates four images using the Google Nano Banana Model, confirming that the structured approach works. - Verification included checking features like API key persistence, dark/light theme toggling, and image generation correctness, all verified using Chrome DevTools commands. ![Screenshot at 00:40: The video begins by showing the Verdent interface where the user sets up a task to build a Text-to-Image generator, immediately selecting the 'Plan' mode to define the project structure and requirements before execution.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-00-40.jpg) **Context:** The video demonstrates an advanced methodology for utilizing AI agents within the Verdent development environment, contrasting it with typical, less effective chatbot interactions. The core concept is to move from simple prompting to a structured, multi-step development process involving planning, execution, and automated verification, using custom commands and external tools to ensure quality and fidelity to design specifications. ## Detailed Analysis The video argues against using AI agents purely as chatbots, advocating instead for a structured, planned approach to development using the Verdent platform. The speaker outlines a three-phase process: Plan, Implement, and Verify. The planning phase involves switching the agent to 'Plan' mode (01:39) to create a detailed implementation plan, including API integration specifics (like using the Gemini API) and UI/UX design directions (01:41-03:15). The speaker then creates a custom slash command, `/frontend-design`, to encapsulate complex design principles, ensuring the agent adheres to a specific aesthetic rather than generic AI output (06:34-06:55). For implementation, the agent switches to 'Agent' mode (03:55) and executes the plan, running tasks in parallel (07:21). Finally, verification is performed using Chrome DevTools commands integrated into the agent's capabilities (07:56-08:13), confirming that all features, including the theme toggle and image generation, meet the specified criteria (08:14). The successful generation of high-quality images for both the initial prompt and a redesigned coffee shop theme validates this structured workflow over simple sequential prompting. ### Agent Workflow - Agent operates in two modes: 'Plan' mode for initial structure and feature definition (01:35) - 'Agent' mode for execution (01:37) - Parallel execution enabled for faster iteration (07:20) ### Custom Command Implementation - Created a custom slash command, `/frontend-design`, to enforce specific design principles like 'Photographic Darkroom' aesthetic (06:34-06:55) - This provides better context than generic prompts (08:41) ### Text-to-Image Demo - Built a Text-to-Image Generator using Google Nano Banana API (01:55) - Successfully generated images matching complex prompts, like 'Llama wearing sunglasses' (05:04) and 'cozy coffee shop' (08:47) ### Verification Process - Utilizes Chrome DevTools commands via the MCP integration for automated testing (07:56) - Verification summary confirmed all features working, including API key persistence and theme toggling (08:14) ### Benefits of Structure - Structured planning and verification lead to faster, more reliable execution and better adherence to desired design outcomes compared to simple chatbot use (09:24-09:38) ![Screenshot at 00:00: The speaker begins the video, emphasizing the need for a new approach to using AI agents beyond basic chatbot interaction.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-00-00.jpg) ![Screenshot at 00:40: The initial setup in Verdent shows the agent starting the planning phase for building a Text-to-Image generator application.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-00-40.jpg) ![Screenshot at 02:25: The agent generates a detailed plan, including API integration specifics for the Google Nano Banana Model and UI/UX design requirements.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-02-25.jpg) ![Screenshot at 05:57: The result of the initial prompt execution shows four generated images of cats wearing colorful hats, demonstrating the system's capability.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-05-57.jpg) ![Screenshot at 08:14: A verification summary screen shows all implemented features, including image generation and theme toggling, passing checks verified by Chrome DevTools.](https://ss.rapidrecap.app/screens/3sXGt0MKmY8/00-08-14.jpg)