Picture by Editor
# 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 an alternative of simply producing code reactively, genuinely perceive the distinctive processes behind code era.
Google Antigravity has rather a lot to say on this matter. This software holds the important thing to constructing extremely customizable brokers. This text unveils a part of its potential by demystifying three cornerstone ideas: guidelines, abilities, and workflows.
On this article, you may learn 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 abilities. Off we go!
# Understanding the Three Core Ideas
Earlier than getting our fingers soiled, it’s handy to interrupt down the next three components belonging to the Google Antigravity ecosystem:
- Rule: These are the baseline constraints that dictate the agent’s conduct, in addition to how one can adapt it to our stack and match our model. They’re saved as markdown recordsdata.
- Talent: Contemplate abilities as a reusable bundle containing data that instructs the agent on how one can tackle 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 by utilizing 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’ll see how one can configure Antigravity to overview Python code, apply right formatting, and generate checks — all with out the necessity for added 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 software and open your Python challenge folder — if you’re new to the software, you’ll be requested to outline a folder in your pc file system to behave because the challenge folder. Regardless, the best way so as to add a manually created folder into Antigravity is thru the “File >> Add Folder to Workspace…” choice within the higher menu toolbar.
Say you will have a brand new, empty workspace folder. Within the root of the challenge listing (left-hand facet), create a brand new folder and provides it the identify .brokers. Inside this folder, we’ll create two subfolders: one known as guidelines and one named abilities. You could guess that these two are the place we’ll outline the 2 pillars for our agent’s conduct: guidelines and abilities.
The challenge folder hierarchy | Picture by Writer
Let’s outline a rule first, containing our baseline constraints that may 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. Maintain dependencies strictly to free, open-source libraries to make sure our challenge stays free-friendly.
If you wish to nail it, go to the agent customizations panel that prompts on the right-hand facet of the editor, open it, and discover and choose the rule we simply outlined:
Customizing the activation of agent guidelines | Picture by Writer
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:
Setting the glob activation mode | Picture by Writer
With this, you simply ensured the agent that might be launched later all the time applies the rule outlined once we are particularly engaged on Python scripts.
Subsequent, it is time to outline (or “teach”) the agent some abilities. That would be the talent of performing strong checks on Python code — one thing extraordinarily helpful in in the present day’s demanding software program growth panorama. Contained in the abilities subfolder, we’ll create one other folder with the identify pytest-generator. Create a SKILL.md file inside it, with the next content material:
Defining agent abilities throughout the workspace | Picture by Writer
Now it is time to put all of it collectively and launch our agent, however not with out having inside our challenge 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’ll have observed this Python code is deliberately messy and flawed. Let’s examine what our agent can do about it. Go to the customization panel on the right-hand facet, and this time concentrate on 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 Test
# Description: Automates code overview and check era for Python recordsdata.
Step 1: Evaluate the at the moment 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` talent to write down complete unit checks for the refactored code.
Step 4: Output the ultimate check code and recommend operating `pytest` within the terminal.
All these items, when glued collectively by the agent, will rework the event loop as an entire. 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 facet panel, typing the qa-check command, and hitting enter to run the agent:
Invoking the QA workflow through the agent console | Picture by Writer
After execution, the agent can have revised the code and mechanically instructed a brand new model within the Python file, as proven beneath:
The refactored code instructed by the agent | Picture by Writer
However that is not all: the agent additionally comes with the great high quality test we have been searching for by producing various code excerpts you should use to run several types of checks utilizing pytest. For the sake of illustration, that is what a few of these checks might appear 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="Cannot 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 talent to provide a complete testing technique tailor-made to our codebase.
# Wrapping Up
Wanting again, on this article, we now have proven how one can mix three key components of Google Antigravity — guidelines, abilities, and workflows — to show generic brokers into specialised, strong, and environment friendly workmates. We illustrated how one can make an agent specialised in appropriately formatting messy code and defining QA checks.
Iván Palomares Carrascosa is a pacesetter, author, speaker, and adviser in AI, machine studying, deep studying & LLMs. He trains and guides others in harnessing AI in the actual world.
