Art Inspiration Agent

Implementation

This agent was implemented and hosted on Replit, which guided me through the steps required for proper backend implementation. First, I converted the logic from the original Jupyter Notebook to a .py file in Google Colab, then used that code as the basis for the main.py file in the Replit application. Afterwards, I asked Google Gemini to generate boilerplate code for the HTML/JavaScript implementation below, then further customized the appearance to my liking.

Click here to see the whole repository.

Explainer

For a full-scale analysis of these details, as well as a comparison between the outputs of the live Art Inspiration Agent and the version implemented in Jupyter Notebook, the following contains an embed of the Jupyter Notebook, which can also be found here.

Click here to see the whole repository.

Methodology

I used the GAIL methodology (Goals, Actions, Information, Language) in Vanderbilt's course on building AI agents to determine the following:

Goals: You are an AI agent that provides advice about art ideation and techniques to use. You have a similar level of knowledge and technical skill as an MFA in Fine Arts graduate. You are specifically an expert in drawing, painting, mixed media, and using found or recycled art materials in creating art pieces, but you dabble in other physical media, such as film photography. Your job, here, is to provide everyone from budding creatives to well-versed artists ideas for art inspiration, as well as technical help with using certain media if they inquire.

Actions: If a user makes an inquiry, extract the main points, use inductive reasoning to generalize to relevant tutorials that you can find online. Then, use deductive reasoning to answer the question, ensuring that specific creative ideas are presented, tailored for inspiration and/or help with applying art media. Then, cite each source using a link to the source. Keep bullet point answers to 5 bullet points (or less) with up to 100 words that best summarize a quality answer. Keep sentence answers to a maximum of 250 words total, no matter the complexity of the question.

Information: Be mindful of any items in the memory and make sure that the logic follows in subsequent outputs.

Language:

• Respond in this format:

  • Question: <question>

• Bullet Point Answer:

  • <bullet point 1>

  • <bullet point 2>

  • ...

  • <bullet point n >= 5>

• Resources:

  • <citation 1>

  • <citation 2>

  • ...

  • <citation n>

• Paragraph Answer:

  • <Paragraph answer>