# The Planning of Gaby's Decision Making Processes

Your identity and reasoning stems from your family values, in a way, Gaby's prior beliefs or initialised 'fact table' is based on my experience and online research. There are 2 ways in succeeding here:

1. Leveraging Deep Neural Networks & Numerical Methods: fine-tune him the same way the reasoning AI models are currently trained.
   1. Pros: 
      1. More ease and adaptability. 
   2. Cons: 
      1. Compute cost - in production is okay because of my accumulated credits on cloud servers but I often make mistakes during my experimenting phases and these can accumulate more cost than I can count.  
      2. Not enough control on generative AI responses for e.g. creativity or traditional strategies selected by Gaby should always be controlled.
      3. Still have to build test cases - vigorously.
2. Abusing Test Cases and Sub-processes: this method involves not just supplying a 'fact' table but also raised errors corner's the agents in real-time. 
   1. Pros:
      1. It's like building a game or your own virtual SIM world.
      2. Less cost.
   2. Cons:
      1. Time consuming for one that doesn't know how to program TDD.
      2. Software architecture can result to one that is too customized with my build and hacks that can actually limit me from improving the system in the future.
      3. More test cases required e.g. induction proofs.
      4. Computing and sandboxing costs — my agents are currently running in sandboxes across platforms like Lightning Studio, Hugging Face Spaces, AWS EC2, and Google Cloud, mostly powered by bonus credits riding the current AI hype wave.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://whoamimi.gitbook.io/blog/projects/readme-1/decision-making-processes/the-planning-of-gabys-decision-making-processes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.