Construct Higher AI Brokers with Google Antigravity Abilities and Workflows

# Introduction

 
Likelihood is, you have already got the sensation that the brand new, agent-first synthetic intelligence period is right here, with builders resorting to new instruments that, as a substitute of simply producing code reactively, genuinely perceive the distinctive processes behind code era.

Google Antigravity has loads to say on this matter. This instrument holds the important thing to constructing extremely customizable brokers. This text unveils a part of its potential by demystifying three cornerstone ideas: guidelines, expertise, and workflows.

On this article, you may discover ways to hyperlink these key ideas collectively to construct extra strong brokers and highly effective automated pipelines. Particularly, we’ll carry out a step-by-step course of to arrange a code high quality assurance (QA) agent workflow, based mostly on specified guidelines and expertise. Off we go!

# Understanding the Three Core Ideas

 
Earlier than getting our arms soiled, it’s handy to interrupt down the next three parts belonging to the Google Antigravity ecosystem:

• Rule: These are the baseline constraints that dictate the agent’s conduct, in addition to the way to adapt it to our stack and match our fashion. They’re saved as markdown information.
• Ability: Think about expertise as a reusable bundle containing information that instructs the agent on the way to deal with a concrete process. They’re allotted in a devoted folder that incorporates a file named SKILL.md.
• Workflow: These are the orchestrators that put all of it collectively. Workflows are invoked through the use of command-like directions preceded by a ahead slash, e.g. /deploy. Merely put, workflows information the agent by an motion plan or trajectory that’s well-structured and consists of a number of steps. That is the important thing to automating repetitive duties with out lack of precision.

# Taking Motion

 
Let’s transfer on to our sensible instance. We are going to see the way to configure Antigravity to overview Python code, apply appropriate formatting, and generate assessments — all with out the necessity for extra third-party instruments.

Earlier than taking these steps, be sure to have downloaded and put in Google Antigravity in your pc first.

As soon as put in, open the desktop utility and open your Python mission folder — if you’re new to the instrument, you’ll be requested to outline a folder in your pc file system to behave because the mission folder. Regardless, the best way so as to add a manually created folder into Antigravity is thru the “File >> Add Folder to Workspace…” possibility within the higher menu toolbar.

Say you’ve gotten a brand new, empty workspace folder. Within the root of the mission listing (left-hand aspect), create a brand new folder and provides it the title .brokers. Inside this folder, we’ll create two subfolders: one known as guidelines and one named expertise. Chances are you’ll guess that these two are the place we’ll outline the 2 pillars for our agent’s conduct: guidelines and expertise.

Let’s outline a rule first, containing our baseline constraints that can make sure the agent’s adherence to Python formatting requirements. We do not want verbose syntax to do that: in Antigravity, we outline it utilizing clear directions in pure language. Contained in the guidelines subfolder, you may create a file named python-style.md and paste the next content material:

# Python Type Rule
At all times use PEP 8 requirements. When offering or refactoring code, assume we're utilizing `black` for formatting. Hold dependencies strictly to free, open-source libraries to make sure our mission stays free-friendly.

If you wish to nail it, go to the agent customizations panel that prompts on the right-hand aspect of the editor, open it, and discover and choose the rule we simply outlined:

Customization choices will seem above the file we simply edited. Set the activation mannequin to “glob” and specify this glob sample: **/*.py, as proven beneath:

With this, you simply ensured the agent that shall be launched later at all times applies the rule outlined after we are particularly engaged on Python scripts.

Subsequent, it is time to outline (or “train”) the agent some expertise. That would be the ability of performing strong assessments on Python code — one thing extraordinarily helpful in at this time’s demanding software program improvement panorama. Contained in the expertise subfolder, we’ll create one other folder with the title pytest-generator. Create a SKILL.md file inside it, with the next content material:

Now it is time to put all of it collectively and launch our agent, however not with out having inside our mission workspace an instance Python file containing “poor-quality” code first to attempt all of it on. If you have no, attempt creating a brand new .py file, calling it one thing like flawed_division.py within the root listing, and add this code:

def divide_numbers( x,y ):
  return x/y

You will have observed this Python code is deliberately messy and flawed. Let’s have a look at what our agent can do about it. Go to the customization panel on the right-hand aspect, and this time give attention to the “Workflows” navigation pane. Click on “+Workspace” to create a brand new workflow we’ll name qa-check, with this content material:

# Title: Python QA Examine
# Description: Automates code overview and take a look at era for Python information.

Step 1: Evaluation the presently open Python file for bugs and elegance points, adhering to our Python Type Rule.
Step 2: Refactor any inefficient code.
Step 3: Name the `pytest-generator` ability to write down complete unit assessments for the refactored code.
Step 4: Output the ultimate take a look at code and recommend operating `pytest` within the terminal.

All these items, when glued collectively by the agent, will remodel the event loop as a complete. With the messy Python file nonetheless open within the workspace, we’ll put our agent to work by clicking the agent icon within the right-hand aspect panel, typing the qa-check command, and hitting enter to run the agent:

After execution, the agent can have revised the code and mechanically urged a brand new model within the Python file, as proven beneath:

However that is not all: the agent additionally comes with the excellent high quality test we have been on the lookout for by producing quite a few code excerpts you need to use to run various kinds of assessments utilizing pytest. For the sake of illustration, that is what a few of these assessments might seem like:

import pytest
from flawed_division import divide_numbers

def test_divide_numbers_normal():
    assert divide_numbers(10, 2) == 5.0
    assert divide_numbers(9, 3) == 3.0

def test_divide_numbers_negative():
    assert divide_numbers(-10, 2) == -5.0
    assert divide_numbers(10, -2) == -5.0
    assert divide_numbers(-10, -2) == 5.0

def test_divide_numbers_float():
    assert divide_numbers(5.0, 2.0) == 2.5

def test_divide_numbers_zero_numerator():
    assert divide_numbers(0, 5) == 0.0

def test_divide_numbers_zero_denominator():
    with pytest.raises(ValueError, match="Can't divide by zero"):
        divide_numbers(10, 0)

All this sequential course of carried out by the agent has consisted of first analyzing the code beneath the constraints we outlined by guidelines, then autonomously calling the newly outlined ability to provide a complete testing technique tailor-made to our codebase.

# Wrapping Up

 
Wanting again, on this article, we’ve proven the way to mix three key parts of Google Antigravity — guidelines, expertise, and workflows — to show generic brokers into specialised, strong, and environment friendly workmates. We illustrated the way to make an agent specialised in appropriately formatting messy code and defining QA assessments.
 
 

Iván Palomares Carrascosa is a frontrunner, author, speaker, and adviser in AI, machine studying, deep studying & LLMs. He trains and guides others in harnessing AI in the true world.