Any Agent. Any Task. Any LLM Model. Anytime. 2 Mins.
AI Agents have become powerful at transcribing human instructions into tasks like:
This is guide for any AI Engineer looking to build autonomous AI Agents. Let’s get a few things cleared up before we start:
How we Go From LLM Outputs to AI Agents Performing Tasks
Agents = LLM outputs + Task Completion Based on that Output.
The simple answer: we make the LLM output a precise & actionable response that the AI Agent can parse into further tasks.
Let me give you an example — let’s say you wanted to:
In that case, you would prompt the LLM via a prompt template to output the desired code:
task1 = '''
This recipe is available for you to reuse..
<begin recipe>
**Recipe Name:** Analyzing and Visualizing Application Domains in Arxiv Papers
**Steps:**
1. Collect relevant papers from arxiv using a search query.
2. Analyze the abstracts of the collected papers to identify application domains.
3. Count the number of papers in each application domain.
4. Generate a bar chart of the application domains and the number of papers in each domain.
5. Save the bar chart as an image file.
Here are the well-documented, generalized Python functions to perform the coding steps in the future:
```python
import requests
import feedparser
import matplotlib.pyplot as plt
from typing import List, Dict
def search_arxiv(query: str, max_results: int = 10) -> List[Dict[str, str]]:
"""
Search arxiv for papers related to a specific query.
:param query: The search query for arxiv papers.
:param max_results: The maximum number of results to return. Default is 10.
:return: A list of dictionaries containing the title, link, and summary of each paper.
"""
base_url = "http://export.arxiv.org/api/query?"
search_query = f"search_query=all:{query}"
start = 0
max_results = f"max_results={max_results}"
url = f"{base_url}{search_query}&start={start}&{max_results}"
response = requests.get(url)
feed = feedparser.parse(response.content)
papers = [{"title": entry.title, "link": entry.link, "summary": entry.summary} for entry in feed.entries]
return papers
def generate_bar_chart(domains: Dict[str, int], output_file: str) -> None:
"""
Generate a bar chart of application domains and the number of papers in each domain, and save it as an image file.
:param domains: A dictionary containing application domains as keys and the number of papers as values.
:param output_file: The name of the output image file.
"""
fig, ax = plt.subplots()
ax.bar(domains.keys(), domains.values())
plt.xticks(rotation=45, ha="right")
plt.xlabel("Application Domains")
plt.ylabel("Number of Papers")
plt.title("Number of Papers per Application Domain")
plt.tight_layout()
plt.savefig(output_file)
plt.show()
```
**Usage:**
1. Use the `search_arxiv` function to collect relevant papers from arxiv using a search query.
2. Analyze the abstracts of the collected papers using your language skills to identify application domains and count the number of papers in each domain.
3. Use the `generate_bar_chart` function to generate a bar chart of the application domains and the number of papers in each domain, and save it as an image file.
</end recipe>
Here is a new task:
Plot a chart for application domains of GPT models
'''
This code would result in the following bar chart!
And that is how AI Agents work under the surface. Taking these agents into production environments entails few more steps:
Here are some of the most popular frameworks for building AI Agents:
Alrighty, here are the 3 Steps to building an autonomous AI Agent:
Let’s go through them 1 by 1.
Let’s bring in the Llama-2 model in.
In this example, we will be building a simple color changer based on prompt. A JSON-parsed output is prompt-engineered into our Llama-2 model.
The process_command function ensures the LLM outputs get transcribed correctly into resulting tasks. This is the true AI Agent step.
That’s it. That’s the simple 3-step process for defining any AI agent.
Thanks for getting to the end of this article. My name is Tim, I work at the intersection of AI, business, and biology. I love to elaborate ML concepts or write about business(VC or micro)! Get in touch!
Subscribe for free to get notified when I publish a new story.
