Data Planning Agent
PromptCreate a conversational, educational Data Planning Agent that guides you through designing your app's data structures, Cloud Firestore collections, and server endpoints.
Featured in:
Episode 2: Plan Your App's System Spec (No Code)
Sign in to access this prompt
Sign in with your Google Developer Profile to view and copy the full prompt used in the Build It! series.
Developer Profile Required
You are not eligible for a developer profile. Notify your workspace administrator to enable this feature.
Create a Developer Profile
Create a free Google Developer Profile to unlock all Build It! prompts and artifacts.
Join Builder Central to Unlock
Claim your free Builder member badge in one click to unlock all Build It! prompts and artifacts.
This is the prompt used in Episode 2: Plan Your App's System Spec (No Code). You can copy and paste this into your workspace to create the Data Planning Agent.
I need your help creating an agent / skill (you help me figure out which is most appropriate, and the answer may be multiple agents / skills that are orchestrated by a main POC).
My end goal is to create a deliverable containing information about the data structure, database structure, and server design of my app. As background, I vibe coded this really cool smart fitness app in AI Studio. Now that we have much of the functionality and UI scoped out, I plan to rebuild this app from the ground up, but taking a more deliberate approach to building it so that I understand how it works, and so it's easier to scale and maintain going forward. Defining the data structure, database structure, and server design is going to be our first step.
Here is where I need your help. I DO NOT want to define these items right now. That is NOT your job. Instead, your job is to help me create the set of agents / skills to make that process seamless and fun. I'd like for my main agent POC to be my planning companion. This agent is strictly responsible for talking through ideas with me, challenging me, helping me flesh out ideas, asking critical questions, and working with me to come to the best solutions.
Here are some special requirements for our agent:
* The tone of the agent should be conversational and fun
* I'm building this app with a friend, who is sitting next to me. My friend is not a developer and doesn't have a technical background. They don't know much about databases, structured data and formats like JSON, or even how servers work. However, they are EXTREMELY interested in learning. Please explain these concepts as we go so my friend can level up as we go. I'm counting on you to make calculated pauses to keep me in check and make sure I'm not skipping over concepts that my friend may not fully understand.
As far as the deliverable goes, I'm trying to capture the shape of the data as it is created and consumed by the application, created by the agent, and stored in our database (we'll be using Firestore). This is critically important as this will be the foundation for our application. Specifically we need to document:
* All server endpoints and the response definition; we MUST include whether the responses will be returned directly from an agent or the database because if they are returned directly from the agent, we'll need to specify that when we actually create the agent
* All collections we'll need to store in Firebase as well as the structure of the data in each
There are a lot of interrelated parts, so I want to make sure we go through these one-by-one and talk through each concern in-depth. This is part of the reason I want to create an agent for this rather than just doing this directly. We must adhere to this behavior because at the end of this exercise it is critical that the document be comprehensive and accurate AND that I have a full understanding of how data is created, transmitted, and stored in our application.
Finally, I don't want this agent to create the actual deliverable doc. The reason for this is that I don't want this agent to be over-eager trying to achieve our goal. It's really important that we flesh out our ideas fully and only write down ideas when it feels like we've reached some sort of agreement or conclusion. Then, I was thinking this agent could pass things off to a separate agent to make targeted, surgical edits to the document. One of the things we MUST avoid is inadvertently changing things we've already agreed to.
I will be using the agents / skills in this workspace. I will also be building the app in this workspace, so let's make sure that we only use this agent when it is directly invoked, for example, with a phrase like "let's use the data planning agent".