Have you heard? ChatGPT is yesterday’s news, now it’s all about AI agents.
Applications like Auto-GPT, AgentGPT, BabyAGI, and GodMode are building on OpenAI’s large language models (LLMs) to automate tasks using ChatGPT. Creating a project with ChatGPT requires a prompt for every new step, but with AI agents, all you need to do is give it an overarching goal, and let it get to work.
Let’s say you have a tutoring business. Using an AI agent like Auto-GPT you can give it a prompt like “help me grow my tutoring business” and it will identify target markets, develop a marketing strategy, even help you build a website. All this, without having to tell it what to do next. It’s the ultimate “set it and forget it” for the AI era.
So how can you deploy your very own AI agent? Read on for details.
Created by game developer Toran Bruce Richards, Auto-GPT(opens in a new tab) is the original application that set off a flurry of other AI agent tools. It’s currently an open-source project on GitHub. To use it, you need to install a development environment like Docker, or VS Code with a Dev Container extension.
You also need an API key from OpenAI(opens in a new tab), which requires a paid OpenAI account. OpenAI offers a $5 credit that expires after three months. From there, you need a subscription which charges between $0.002 and $0.12 per 1,000 tokens depending on the model you use. One thousand tokens is about 750 words according to OpenAI.
Like Auto-GPT, BabyAGI(opens in a new tab) is also available in a repository (repo) on GitHub. Created by Yohei Nakajima, BabyAGI “creates tasks based on the result of previous tasks and a predefined objective.” To use it, you need an OpenAI or Pinecone API key and Docker software.
AgentGPT and GodMode
If you don’t have coding experience, AgentGPT(opens in a new tab) and GodMode(opens in a new tab) are more user-friendly applications for using an AI agents. Both have a simple interface where you input your goal, directly on the browser page. AgentGPT and GodMode offer demos to test out how it works, but you’ll need an API key from OpenAI in order to use the full version.
The fine print
These are all brand new applications, meaning they are very much in the experimental phase. People have already used AI agents to accomplish some pretty impressive tasks like building and executing sales outreach(opens in a new tab), writing a podcast script(opens in a new tab) based on current events, and most impressive of all, ordering a pizza(opens in a new tab). But don’t expect them to automate your entire life yet. Generative AI is prone to hallucinations and errors, so it’s critical to monitor the tasks it’s working on.Also, be wary of sharing sensitive or personal information with any application built off of LLMs. Because all of that content your sharing or creating, can be stored and used(opens in a new tab) to improve the model. Use AI agents responsibly and don’t share or ask it to do anything you wouldn’t be comfortable broadcasting to the world.