Home / Articles

geminimanaged-agentsantigravityagentssandboxgoogle-genai

Managed Agents in the Gemini API: Sandboxes, Skills and Persistent Agents

A hands-on walk through Google's Antigravity Managed Agents: the remote Linux sandbox, egress proxy, multi-turn state, skills, named agents and production patterns.

Publisher: REACTAPP.TOP40 min read9197 words

This article is published in English.

Sources: Antigravity Managed Agents Tutorial: Ship Production AI Agents

The wall every agent builder hits

Anyone who has built an AI application knows this snag. A language model is asked to help launch a website and replies with tidy code. Then nothing happens, because the model can't open an editor, save the file or press "Run" to see whether it works. All the heavy lifting lands on the developer.

Existing agent tools do cover more ground, including starting servers and running tests. Running one yourself still means handling several chores:

  • providing a sandbox so the model can execute code without wiping your files
  • writing the glue that moves data between modules
  • configuring tools so the model can call them, reach your data or run a script

More operational overhead follows, all of it needed to keep things running safely. Here's what that looks like when a model has to write and test a Python script.

from google import genai
import subprocess

client = genai.Client()

# Step 1: Ask the model for code
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Write a Python script that checks password strength and saves a report."
)

# Step 2: YOU must manually extract the code block from the text response
code = extract_code_from_markdown(response.text)  # You wrote this function

# Step 3: YOU must save the file and run it locally
with open("password_checker.py", "w") as f:
    f.write(code)

# ⚠️ Danger: Running untrusted AI-generated code on YOUR machine!
result = subprocess.run(["python3", "password_checker.py"], capture_output=True, text=True)
print(result.stdout)

The developer carries all of it: pulling the code out of the reply, file I/O, risky local execution, and the error loop that inevitably kicks in when something fails.

Could a single API call take over all of that? Google's Managed Agents framework and its flagship Antigravity agent are meant to. The model becomes a service: in place of a chatbot that only returns text, it receives a secure cloud computer that Google manages, a Linux workspace connected to the live internet.

The table below compares three levels of AI systems.

The core agentic loop

Given a task, an Antigravity agent doesn't just guess. It works inside a continuous loop backed by real hardware.

┌────────────────────────────────────────┐
│          1. PLAN & REASON              │
│  (Analyzes objective & breaks it down) │
└───────────────────┬────────────────────┘
                    │
                    ▼
┌────────────────────────────────────────┐
│               2. ACT                   │
│ (Executes a tool: Bash, Python, Web)   │
└───────────────────┬────────────────────┘
                    │
                    ▼
┌────────────────────────────────────────┐
│             3. OBSERVE                 │
│ (Reads execution output, errors, data) │
└───────────────────┬────────────────────┘
                    │
                    └─── Loop back until task is complete

This goes beyond a single prompt and reply. The agent drafts a script, executes it, sees a SyntaxError in the terminal output, repairs the bug and tries again, repeating until the task is complete.

The remote sandbox

Each time an agent is invoked, Google starts a dedicated workspace.

The result is a genuine Linux computer in the cloud, owned by the agent for the duration of its task.

Two planes behind the API

Working with Managed Agents involves two separate planes, both reached through the Gemini API.

                  ┌─────────────────────────────────┐
                  │           YOUR APP              │
                  └────────┬───────────────┬────────┘
                           │               │
      1. Define/Configure  │               │ 2. Run Task
      (System rules, ID)   │               │ (Send Prompt)
                           ▼               ▼
 ┌───────────────────────────────────┐   ┌───────────────────────────────────┐
 │        THE CONTROL PLANE          │   │         THE RUNTIME PLANE         │
 │          (Agents API)             │   │        (Interactions API)         │
 ├───────────────────────────────────┤   ├───────────────────────────────────┤
 │ Saves persistent identity, system │   │ Spawns the Ubuntu sandbox, logs   │
 │ instructions, and data mounts.    │   │ live traces, and processes loops. │
 └───────────────────────────────────┘   └───────────────────────────────────┘

The control plane, the Agents API, is where an agent gets configured and registered. It's like writing an employee profile: a name, system instructions, custom skills and repositories to clone. It returns a static Agent ID.

The runtime plane, the Interactions API, is where work happens. A task goes to an Agent ID as an "Interaction", and this plane takes care of provisioning the sandbox, running tools, recording reasoning traces and driving the agentic loop.

Security through an egress proxy

Letting an autonomous agent run unverified scripts is risky. Google isolates the environment with an egress proxy layer.

 ┌─────────────────────────┐
 │ REMOTE UBUNTU SANDBOX   │
 │ (No internal secrets)   │
 └───────────┬─────────────┘
             │ Agent attempts outbound API call
             ▼
 ┌─────────────────────────┐
 │   EGRESS PROXY LAYER    │ ◄── Checks Domain Allowlist
 ├─────────────────────────┤
 │ Intercepts connection,  │
 │ injects secrets securely│
 └───────────┬─────────────┘
             │ Safe, Authenticated Request Sent
             ▼
    [ External Target API ]

It provides three guarantees:

  • No secrets inside the sandbox. API keys and database passwords never get stored in the agent's workspace.
  • Domain allowlists. You decide which external domains the agent may reach.
  • Header transformation. For calls to an outside API, the proxy catches the request, checks the domain against the allowlist and adds the auth token on its own. Data comes back to the agent while the private key stays hidden from it.

A first agent in about five minutes

Requirements

  • Python 3.10 or newer, with 3.12 recommended since it matches the sandbox runtime
  • google-genai SDK at version 2.0.0 or above (2.8.0 was current when this was written)
  • An API key, available on a free tier through Google AI Studio
  • Any operating system (macOS, Linux, Windows or WSL), because the code runs locally while the agent runs in Google's cloud

Set up a virtual environment and install the SDK.

python3 -m venv managed-agents-env
source managed-agents-env/bin/activate   # On Windows: managed-agents-env\Scripts\activate
# Install (or upgrade) the Google GenAI SDK
pip install -U google-genai
# Verify the version — must be 1.14.0 or later
python3 -c "import google.genai; print(google.genai.__version__)"
# Set your API key (get one at https://aistudio.google.com/apikey)
export GEMINI_API_KEY="your-api-key-here"

If you'd rather skip local setup, Google AI Studio has a "Managed Agents" template section that works as an interactive playground in the browser.

Running the examples

Every example here is a complete, self-contained Python script. Save it to a file, then run it.

# 1. Save the code to a file (an example name used here is hello_agent.py
vim hello_agent.py   # or use any editor

# 2. Run it
python3 hello_agent.py

Each interaction takes anywhere from half a minute to three minutes, depending on the task, since the agent starts a sandbox, writes and runs code, reads errors and iterates. Easy jobs wrap up within a minute, and complex multi-turn chains may take two to three minutes per turn.

Hello, Managed Agents

Compare the clumsy multi-step code from earlier with the Managed Agents equivalent.

from google import genai

client = genai.Client()

# One API call. One autonomous agent. One remote Linux sandbox.
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a Python script that generates 100 random exam scores between 0 and 100, "
          "calculates the mean, median, and standard deviation, prints a summary, "
          "and saves a grade distribution histogram as grade_report.png using matplotlib.",
    environment="remote"  # This provisions a secure Linux sandbox hosted by Google
)

print(interaction.output_text)

Run it.

python3 hello_agent.py

The first interaction produced the following output. The numbers vary from run to run because the data is random.

I have successfully written and executed a Python script that generates 100 random exam scores, computes their key statistics, and plots a grade distribution histogram.

### 1. Generated Python Script (`generate_report.py`)

Here is the Python script, which is saved in the environment as `generate_report.py`. It uses `numpy` for data generation, `statistics` conventions for calculation (such as sample standard deviation), and `matplotlib` to generate a high-quality visualization.

```python
import numpy as np
import matplotlib.pyplot as plt
import statistics

def generate_and_analyze_grades():
    # Set a random seed for reproducibility
    np.random.seed(42)

    # Generate 100 random exam scores between 0 and 100 (inclusive)
    scores = np.random.randint(0, 101, size=100)

    # Calculate statistics using Python's standard statistics module and NumPy
    # (Using ddof=1 for sample standard deviation, which is standard for student grade samples)
    mean_val = np.mean(scores)
    median_val = np.median(scores)
    std_val = np.std(scores, ddof=1)

    # Print summary to console
    print("=========================================")
    print("         EXAM GRADE REPORT SUMMARY       ")
    print("=========================================")
    print(f"Number of Students : {len(scores)}")
    print(f"Minimum Score      : {np.min(scores)}")
    print(f"Maximum Score      : {np.max(scores)}")
    print(f"Mean Score         : {mean_val:.2f}")
    print(f"Median Score       : {median_val:.2f}")
    print(f"Standard Deviation : {std_val:.2f}")
    print("=========================================")

    # Create the histogram plot
    plt.figure(figsize=(10, 6))

    # Customize the grid and style
    plt.grid(axis='y', linestyle='--', alpha=0.7, zorder=0)

    # Draw the histogram with bins of size 10 (0-10, 10-20, ..., 90-100)
    bins = range(0, 111, 10)
    plt.hist(scores, bins=bins, color='#4A90E2', edgecolor='black', rwidth=0.85, zorder=3)

    # Add labels and title
    plt.title('Distribution of Exam Scores', fontsize=16, fontweight='bold', pad=15)
    plt.xlabel('Exam Scores', fontsize=12, labelpad=10)
    plt.ylabel('Number of Students', fontsize=12, labelpad=10)

    # Mark Mean and Median with vertical lines
    plt.axvline(mean_val, color='#D0021B', linestyle='dashed', linewidth=2, zorder=4, label=f'Mean: {mean_val:.2f}')
    plt.axvline(median_val, color='#F5A623', linestyle='dotted', linewidth=2, zorder=4, label=f'Median: {median_val:.2f}')

    # Set x-ticks to align with bins
    plt.xticks(range(0, 101, 10))

    # Add a legend
    plt.legend(fontsize=11, loc='upper left')

    # Add details text box on the plot
    textstr = '\n'.join((
        f'Total Students: {len(scores)}',
        f'Mean: {mean_val:.2f}',
        f'Median: {median_val:.2f}',
        f'Std Dev: {std_val:.2f}'
    ))
    props = dict(boxstyle='round', facecolor='wheat', alpha=0.5)
    plt.gca().text(0.05, 0.75, textstr, transform=plt.gca().transAxes, fontsize=10,
            verticalalignment='top', bbox=props)

    # Adjust layout and save the figure
    plt.tight_layout()
    output_filename = 'grade_report.png'
    plt.savefig(output_filename, dpi=300)
    print(f"\nHistogram successfully saved to '{output_filename}'")

if __name__ == '__main__':
    generate_and_analyze_grades()
```

---

### 2. Output Statistics Summary

Upon running the script in the sandbox environment, it produced the following output:

```text
=========================================
         EXAM GRADE REPORT SUMMARY
=========================================
Number of Students : 100
Minimum Score      : 1
Maximum Score      : 100
Mean Score         : 51.31
Median Score       : 53.50
Standard Deviation : 29.70
=========================================

Histogram successfully saved to 'grade_report.png'
```

---

### 3. Generated Histogram Details (`grade_report.png`)

The script successfully outputted `grade_report.png` in high-resolution format (300 DPI) containing:
- **Clean Grid & Styling**: Standard light-gray horizontal grids to easily identify column heights.
- **Grade Bins**: Defined score ranges of size 10 (e.g., 0–10, 10–20, ..., 90–100) using custom spacing to give the columns a professional look.
- **Key Metrics Highlighted**:
  - A red dashed line representing the **Mean** (`51.31`).
  - A yellow dotted line representing the **Median** (`53.50`).
- **An Info Legend and Box**: In the top-left area summarizing all descriptive statistics for easy offline reference.

### How to Run it Yourself
If you want to run this script in another environment, ensure you have the required packages installed:
```bash
pip install matplotlib numpy
python generate_report.py
```

What comes back is a plain-English summary and not program output. It describes the agent's actions, namely the code it wrote, the packages it installed and what resulted, while the script and chart file themselves remain in the remote sandbox.

That's a few lines of understandable code. Behind the scenes, the agent:

  1. booted an Ubuntu Linux sandbox
  2. wrote a Python script to create random data and calculate statistics
  3. installed matplotlib on its own, without being told it was needed
  4. ran the script and rendered a histogram to grade_report.png
  5. returned a summary with the statistics and confirmation that the chart was saved

A more ambitious task needs several tools together.

from google import genai
client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="""
    Research the top 5 most popular Python web frameworks in 2026.
    For each framework:
    1. Find the latest version number and release date
    2. Count the GitHub stars
    3. Write a comparison table in Markdown
    """,
    environment="remote"
)

print(interaction.output_text)

In this run the agent searches Google through web browsing, shapes the data with code execution and stores the results through file management, entirely on its own inside one API call. Its output follows.

The landscape of Python web development in **2026** is marked by a fascinating split [1, 2]. On one side, classic **backend-first** and **API-focused** frameworks (Django, FastAPI, Flask) remain the dominant standards for enterprise applications and microservices [3, 5]. On the other side, **pure-Python UI and full-stack** frameworks (Streamlit, Reflex) have seen explosive growth—driven by the need to build interactive web apps, data dashboards, and AI/ML interfaces without writing JavaScript or TypeScript [1, 2].

Below is an in-depth research report on the **top 5 most popular Python web frameworks in 2026**, ranked by GitHub stars and overall developer adoption.

---

### Detailed Breakdown of the Top 5 Python Web Frameworks

#### 1. FastAPI (99,034 GitHub Stars)
*   **Latest Version:** `0.136.3` (Released: **May 23, 2026**)
*   **Architecture Type:** ASGI (Asynchronous Server Gateway Interface)
*   **Primary Focus:** High-Performance APIs and Microservices [4]
*   **Core Philosophy:** FastAPI is designed to build APIs quickly with standard Python type hints. It leverages **Pydantic v2** for extremely fast data validation and serialization, and **Starlette** for high-concurrency async handling [3, 4]. It natively auto-generates interactive Swagger UI and ReDoc documentation.
*   **Ideal Use Case:** AI/ML model deployment, backend APIs for single-page applications (React/Vue/Svelte), and low-latency microservices [5].

#### 2. Django (87,811 GitHub Stars)
*   **Latest Version:** `6.0.6` (Released: **June 3, 2026**)
*   **Architecture Type:** WSGI & ASGI (Fully async-supported)
*   **Primary Focus:** "Batteries-Included" Monolithic Web Applications [4]
*   **Core Philosophy:** As an 18-year industry standard, Django remains the premier full-featured web framework [2]. It handles everything—database routing (via its powerful ORM), administration panels, user authentication, form validation, and robust security defaults (SQLi, CSRF, XSS protection) [1]. In 2026, Django 6.x is highly optimized with full native asynchronous views and type hints [4].
*   **Ideal Use Case:** Large-scale enterprise applications, content management systems, e-commerce platforms, and fast SaaS MVP development where you need a complete, secure architecture out of the box [2, 5].

#### 3. Flask (71,638 GitHub Stars)
*   **Latest Version:** `3.1.3` (Released: **February 19, 2026**)
*   **Architecture Type:** WSGI
*   **Primary Focus:** Lightweight, Flexible Microframework [4]
*   **Core Philosophy:** Flask provides a minimalist core, leaving the choice of database ORM, form handling, and security components completely up to the developer [1, 2]. Paired with modern 2026 extensions (SQLAlchemy 2.x, Pydantic), it represents a simple, un-opinionated foundation that never gets in the developer's way [3].
*   **Ideal Use Case:** Small utility applications, lightweight APIs, microservices, and custom projects where developers want total control over their system design [1, 5].

#### 4. Streamlit (44,895 GitHub Stars)
*   **Latest Version:** `1.58.0` (Released: **May 28, 2026**)
*   **Architecture Type:** UI-First Scripting Paradigm
*   **Primary Focus:** Rapid Data and Machine Learning Applications [1]
*   **Core Philosophy:** Streamlit turns standard Python scripts into interactive, beautiful web apps in a matter of minutes. It handles the entire frontend and backend flow by re-running the script from top to bottom whenever a user interacts with a widget.
*   **Ideal Use Case:** Quick data dashboards, machine learning model prototypes, and internal analytical tools for teams without frontend resources [1, 2].

#### 5. Reflex (28,467 GitHub Stars)
*   **Latest Version:** `0.9.4` (Released: **June 4, 2026**)
*   **Architecture Type:** Full-Stack Async React-Compiled
*   **Primary Focus:** Interactive, Pure-Python Full-Stack Apps [2]
*   **Core Philosophy:** Formerly known as Pynecone, Reflex compiles Python code into a high-performance **React/Next.js frontend** and a **FastAPI backend**, using real-time WebSockets to synchronize states between them [1, 2]. It bypasses JavaScript entirely, offering 60+ pre-built Radix UI components with native Tailwind integration [1, 2].
*   **Ideal Use Case:** Complex, interactive web applications, real-time streaming dashboards (e.g., AI chat applications, financial trackers), and user-facing SaaS applications built entirely in Python [2].

---

### Other Honorable Mentions in 2026
While they didn't make the top 5 by GitHub stars, these frameworks are heavily utilized:
*   **Tornado** (22,182 stars, v6.5.7, Released June 8, 2026): A mature, asynchronous networking framework ideal for long-lived WebSocket connections [4].
*   **Sanic** (18,629 stars, v25.12.1, Released May 31, 2026): An ASGI web framework built for extreme speed and Flask-like simplicity, running on its own high-performance web server.
*   **Litestar** (8,269 stars, v2.23.0, Released May 29, 2026): A highly structured, strict, and enterprise-grade ASGI alternative to FastAPI [3, 4].

---

### 2026 Python Web Frameworks Comparison Table

| Framework | GitHub Stars | Latest Version | Release Date | Architecture | Best For | Key Strength | Learning Curve |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| **FastAPI** | ~99,034 | `0.136.3` | May 23, 2026 | ASGI (Async) | High-performance API development & AI model deployments [4, 5] | Autogenerated Swagger docs, native Pydantic v2 validation [4] | **Easy / Moderate** |
| **Django** | ~87,811 | `6.0.6` | Jun 03, 2026 | WSGI / ASGI | Enterprise apps, content-heavy websites, secure SQL backends [1, 2] | "Batteries-included" (built-in admin, ORM, security, auth) [1, 2] | **Moderate / Hard** |
| **Flask** | ~71,638 | `3.1.3` | Feb 19, 2026 | WSGI (Sync-first) | Microservices, custom MVPs, lightweight apps [1, 5] | Unrivaled design flexibility, minimal core overhead [1] | **Very Easy** |
| **Streamlit**| ~44,895 | `1.58.0` | May 28, 2026 | Scripted Reactive | Data visualization dashboards & ML interactive tools [1] | Zero frontend experience needed; fast prototyping [1] | **Very Easy** |
| **Reflex** | ~28,467 | `0.9.4` | Jun 04, 2026 | Async React-compiled | Interactive, real-time SaaS & full-stack apps in pure Python [2] | True multi-page routing, state management without JavaScript [2] | **Moderate** |

---

### Guidance: Which Framework Should You Choose in 2026?

1.  **Choose FastAPI** if you are building modern REST/GraphQL APIs, backend microservices, or deploying AI/ML models with high concurrency and automatic documentation [3, 5].
2.  **Choose Django** if you are building database-driven business platforms or SaaS architectures where user authentication, administrative interfaces, and built-in security are paramount [1, 2].
3.  **Choose Flask** if you need to build simple backend services or you want to hand-select every tool in your stack (e.g., combining custom database layers with external identity providers) [1].
4.  **Choose Streamlit** if your core team consists of data scientists or business analysts who need to quickly present internal analytics, charts, and interactive widgets without building a complex web architecture [1, 2].
5.  **Choose Reflex** if you want to build a fully interactive, production-ready full-stack application (with complex states, WebSocket interactions, and beautiful custom styles) but do not want to divide your team between Python and JavaScript [2].

---

### Sources & References
*   [1] [Best Python Web Frameworks 2026 Compared - Reflex](https://reflex.dev/blog/top-python-web-frameworks/)
*   [2] [Django vs Flask vs Reflex (April 2026) - Reflex](https://reflex.dev/blog/django-vs-flask-vs-reflex-comparison/)
*   [3] [12 Modern Python Frameworks to Try in 2026 - Medium](https://medium.com/the-pythonworld/12-modern-python-frameworks-to-try-in-2026-e7089305bb19)
*   [4] [5 top Python web frameworks of 2026 - Educative.io](https://www.educative.io/blog/top-python-web-frameworks)
*   [5] [The Python Backend Framework Decision Guide for 2026 - Rollbar](https://rollbar.com/blog/python-backend-frameworks/)

Multi-turn conversations with persistent state

By default, each interactions.create() call starts a brand-new, empty sandbox. To let the agent build on earlier work, pass two IDs back in.

from google import genai
client = genai.Client()

# Turn 1: Research and create a report
interaction_1 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Research the current state of carbon capture technology in 2026. "
          "Write a comprehensive 500-word report and save it as report.md",
    environment="remote"
)
print(f"Environment ID: {interaction_1.environment_id}")
print(f"Interaction ID: {interaction_1.id}")
print(interaction_1.output_text)

# Turn 2: Build on the previous work - same sandbox, same files
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction_1.environment_id,       # ← Re-attaches to same Ubuntu sandbox
    previous_interaction_id=interaction_1.id,       # ← Preserves conversation memory
    input="Convert that report.md file into a clean index.html webpage "
          "with modern inline CSS styling and responsive design."
          " Please output the contents of the index.html file"
)
print(interaction_2.output_text)

The first interaction produced a report.md file.

Environment ID: 5eb9b4b8-c02f-4a8f-b7a0-c90a796c01a6
Interaction ID: v1_ChdidXNuYXJLQkF1eWlqdU1QODRmUjJRZxIXYnVzbmFyS0JBdXlpanVNUDg0ZlIyUWc
I have researched the state of carbon capture, utilization, and storage (CCUS)
technology in 2026 and compiled a comprehensive 494-word report.
The report has been successfully saved to your environment as **`report.md`**.

Below is the full text of the report,
highlighting how the CCUS sector has transitioned from pilot-stage
demonstrations to industrial infrastructure in 2026.

***

# The State of Carbon Capture Technology in 2026: From Pilot to Infrastructure

## Executive Summary
....

## Point-Source Capture: The Current Backbone
...

## Scaling Direct Air Capture (DAC)
...

## Infrastructure, Transport, and Policy
...

## Key Challenges
...

***

### Sources Cited

* **[1] S&P Global:** [2026 CCUS: Navigating the tides of the great realignment](https://www.spglobal.com/energy/en/news-research/blog/energy-transition/041426-2026-ccus-navigating-the-tides-of-the-great-realignment) (April 2026)
* **[2] Carbon Herald:** [What's Next For Carbon Capture, Utilization & Storage (CCUS) In 2026](https://carbonherald.com/whats-next-for-carbon-capture-utilization-storage-ccus-in-2026/) (January 2026)
* **[3] Nature Tech Memos:** [Top 10 Carbon Capture Startups for Corporate Partnerships in 2026](https://www.naturetechmemos.com/p/top-10-carbon-capture-startups-for-corporate-partnerships-in-2026) (April 2026)
.....

The second interaction reused the earlier environment and interaction and asked for an HTML version of the report, index.html, with the instruction explicitly requesting the HTML contents in the reply.

I have successfully converted your `report.md` file into a clean, modern, and highly responsive **`index.html`** webpage!

### What was done:
1. **Designed a cohesive palette:** Implemented a modern climate-tech inspired aesthetic using Slate (`#1e293b`) and a range of deep and light teals (`#0f766e`, `#14b8a6`, `#115e59`).
2. **Added an Interactive Stat Dashboard:** Created a high-level statistical summary card grid displaying key 2026 data at a glance (e.g., global Mtpa capacity, Stratos targets, US Section 45Q tax credits).
3. **Structured visual highlights:** Embedded two distinct grid comparison cards for the **Climeworks Mammoth** and **1PointFive Stratos** facilities, as well as a custom callout block highlighting the trans-European **Northern Lights** shipping route.
4. **Professionalized the typography & chemistry:** Used system-ui fonts for excellent loading speeds and correctly formatted all chemical formulas to standard subscripts (e.g., **CO<sub>2</sub>**).
5. **Citations & Interactivity:** Mapped the original references into clickable, superscript citation numbers (e.g., `[1]`) that link smoothly down to a beautifully bulleted "Sources Cited" section with custom index bullet styling.

The full HTML contents of the newly created `index.html` are shown below:

```html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>The State of Carbon Capture Technology in 2026</title>
    <style>
        :root {
            --primary: #0f766e;
            --primary-light: #14b8a6;
            --primary-dark: #115e59;
            --bg: #f8fafc;
            --card-bg: #ffffff;
            --text-main: #1e293b;
            --text-muted: #475569;
            --accent: #0284c7;
            --border: #e2e8f0;
            --shadow: 0 4px 6px -1px rgba(15, 118, 110, 0.05), 0 2px 4px -2px rgba(15, 118, 110, 0.05);
            --shadow-md: 0 10px 15px -3px rgba(15, 118, 110, 0.1), 0 4px 6px -4px rgba(15, 118, 110, 0.1);
        }
        * {
            box-sizing: border-box;
        }
        body {
            font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
            background-color: var(--bg);
            color: var(--text-main);
            line-height: 1.8;
            margin: 0;
            padding: 0;
            -webkit-font-smoothing: antialiased;
        }

        <!-- LOTS MORE CSS STUFF :-) -->

        footer {
            text-align: center;
            color: var(--text-muted);
            font-size: 0.875rem;
            margin-top: 4rem;
            padding-top: 2rem;
            border-top: 1px solid var(--border);
        }
    </style>
</head>
<body>

    <header>
        <div class="header-content">
            <span class="meta">Special Intelligence Report</span>
            <h1>The State of Carbon Capture Technology in 2026</h1>
            <p>From Pilot to Infrastructure</p>
        </div>
    </header>

    <main>
        <!-- Key Metrics Dashboard -->
        <div class="stats-grid">
            <div class="stat-card">
                <div class="stat-num">~73 Mtpa</div>
                <div class="stat-label">Global Operational Capacity</div>
            </div>
            <div class="stat-card">
                <div class="stat-num">500k Tons</div>
                <div class="stat-label">Stratos DAC Annual Target</div>
            </div>
            <div class="stat-card">
                <div class="stat-num">Up to $180</div>
                <div class="stat-label">US 45Q Subsidy per Ton</div>
            </div>
            <div class="stat-card">
                <div class="stat-num">36,000 T</div>
                <div class="stat-label">Mammoth Iceland Capacity</div>
            </div>
        </div>

        <div class="content-wrapper">
            <!-- Executive Summary -->
            <section id="executive-summary">
                <h2>Executive Summary</h2>
                <p>
                    In 2026, the Carbon Capture, Utilization, and Storage (CCUS) industry is undergoing an "industrial hardening" phase, transitioning decisively from demonstration-stage pilots to commercial-scale infrastructure<sup><a href="#ref-1" class="citation-link">[1]</a></sup>. Global operational capture capacity has reached approximately 73 million metric tons per annum (Mtpa) as of mid-2026, up from 50 Mtpa in early 2025<sup><a href="#ref-1" class="citation-link">[1]</a></sup><sup><a href="#ref-2" class="citation-link">[2]</a></sup>. This momentum is propelled by robust climate policies, corporate carbon-removal commitments, and the commissioning of megaton-scale facilities.
                </p>
            </section>

            <!-- Point-Source Capture -->
            <section id="point-source">
                <h2>Point-Source Capture: The Current Backbone</h2>
                <p>
                    Point-source carbon capture remains the commercial backbone of CCUS<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. Technologies deployed at industrial and energy facilities—such as cement, steel, chemicals, and refining—now represent the vast majority of active capture capacity. Post-combustion chemical absorption using amine-based solvents is the most widely deployed technology<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. Companies like Carbon Upcycling Technologies are successfully integrating capture systems with utilization, converting captured carbon dioxide (CO<sub>2</sub>) into high-quality construction materials, turning emissions from cement manufacturers into a low-carbon concrete feedstock<sup><a href="#ref-3" class="citation-link">[3]</a></sup>.
                </p>
            </section>

            <!-- Scaling Direct Air Capture -->
            <section id="dac">
                <h2>Scaling Direct Air Capture (DAC)</h2>
                <p>
                    Direct Air Capture is experiencing a dramatic scale-up<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Climeworks' "Mammoth" facility in Iceland, operational since May 2024, captures up to 36,000 tons of CO<sub>2</sub> annually, storing it permanently underground via Carbfix mineralization<sup><a href="#ref-4" class="citation-link">[4]</a></sup><sup><a href="#ref-5" class="citation-link">[5]</a></sup>. Meanwhile, 1PointFive's (a subsidiary of Occidental Petroleum) "Stratos" facility in Ector County, Texas, is entering active operation in 2026<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Designed to capture up to 500,000 tons of atmospheric CO<sub>2</sub> annually using liquid solvent technology licensed from Carbon Engineering, Stratos is currently the world’s largest DAC plant<sup><a href="#ref-4" class="citation-link">[4]</a></sup><sup><a href="#ref-6" class="citation-link">[6]</a></sup>.
                </p>

                <div class="highlight-grid">
                    <div class="highlight-box">
                        <h4>Climeworks: Mammoth (Iceland)</h4>
                        <p>Nameplate capacity of 36,000 tons/year. Relies on solid-sorbent collectors powered by clean geothermal energy with deep Carbfix basaltic storage.</p>
                    </div>
                    <div class="highlight-box">
                        <h4>1PointFive: Stratos (Texas)</h4>
                        <p>World's largest facility with 500,000 tons/year target. Employs liquid-solvent infrastructure designed for rapid regional scalability.</p>
                    </div>
                </div>

                <p>
                    Major technology firms (including Microsoft, Google, Meta, and Amazon) have signed multi-year offtake agreements for high-quality, durable carbon credits, paying between $200 and $300 per ton, though current baseline DAC capture costs remain high, between $400 and $1,000 per ton<sup><a href="#ref-3" class="citation-link">[3]</a></sup><sup><a href="#ref-7" class="citation-link">[7]</a></sup>.
                </p>
            </section>

            <!-- Infrastructure, Transport, and Policy -->
            <section id="infrastructure">
                <h2>Infrastructure, Transport, and Policy</h2>
                <p>
                    The commercial viability of carbon capture relies heavily on dedicated transportation and storage networks<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. In Europe, 2026 marks the active operation of Norway’s "Northern Lights" project, the world's first open-source CO<sub>2</sub> transport and storage network<sup><a href="#ref-8" class="citation-link">[8]</a></sup>. For example, Yara's flagship Sluiskil ammonia plant in the Netherlands is liquefying up to 800,000 tons of CO<sub>2</sub> annually to be shipped by Northern Lights for permanent undersea storage<sup><a href="#ref-8" class="citation-link">[8]</a></sup>. Concurrently, Denmark’s "Greensand" offshore storage initiative is beginning operations<sup><a href="#ref-2" class="citation-link">[2]</a></sup>.
                </p>

                <div class="callout">
                    <div class="callout-title">The Trans-European Shipping Pathway</div>
                    <p>Northern Lights bridges emission-heavy inland industrial sites like Yara Sluiskil in the Netherlands directly with permanent injection storage wells beneath the North Sea seabed.</p>
                </div>

                <p>
                    On the policy front, the sector is heavily anchored by government subsidies. In the United States, the Inflation Reduction Act’s (IRA) modified Section 45Q tax credit provides up to $180 per metric ton for DAC and $85 per metric ton for point-source capture<sup><a href="#ref-9" class="citation-link">[9]</a></sup>. In the European Union, the Net Zero Industry Act has accelerated cross-border transport approvals, providing regulatory certainty.
                </p>
            </section>

            <!-- Key Challenges -->
            <section id="challenges">
                <h2>Key Challenges</h2>
                <p>
                    Despite rapid progress, critical bottlenecks persist. Chief among these is the high energy intensity of DAC, which requires 1.5 to 2.5 megawatt-hours (MWh) of zero-carbon energy per ton of captured CO<sub>2</sub><sup><a href="#ref-7" class="citation-link">[7]</a></sup>. Permitting delays for geologic injection wells—specifically the EPA’s rigorous Class VI permits in the United States—also restrict how fast captured carbon can be sequestered<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Overcoming these economic and infrastructure hurdles remains essential to achieving megaton targets by 2030.
                </p>
            </section>

            <!-- Sources Cited -->
            <div class="sources-section">
                <h3>Sources Cited</h3>
                <ul class="sources-list">
                    <li id="ref-1" data-index="1"><strong>S&P Global:</strong> <a href="https://www.spglobal.com/energy/en/news-research/blog/energy-transition/041426-2026-ccus-navigating-the-tides-of-the-great-realignment" target="_blank">2026 CCUS: Navigating the tides of the great realignment</a> (April 2026)</li>
                    <li id="ref-2" data-index="2"><strong>Carbon Herald:</strong> <a href="https://carbonherald.com/whats-next-for-carbon-capture-utilization-storage-ccus-in-2026/" target="_blank">What's Next For Carbon Capture, Utilization & Storage (CCUS) In 2026</a> (January 2026)</li>
                    <li id="ref-3" data-index="3"><strong>Nature Tech Memos:</strong> <a href="https://www.naturetechmemos.com/p/top-10-carbon-capture-startups-for-corporate-partnerships-in-2026" target="_blank">Top 10 Carbon Capture Startups for Corporate Partnerships in 2026</a> (April 2026)</li>
                    <li id="ref-4" data-index="4"><strong>Senken:</strong> <a href="https://www.senken.io/blog/top-direct-air-capture-carbon-removal-projects-buyers-guide" target="_blank">The Top 3 Direct Air Capture Carbon Removal Projects</a> (February 2026)</li>
                    <li id="ref-5" data-index="5"><strong>Climeworks:</strong> <a href="https://climeworks.com/plant-mammoth" target="_blank">Mammoth: our newest direct air capture and storage facility</a> (May 2024)</li>
                    <li id="ref-6" data-index="6"><strong>Carbon Credits:</strong> <a href="https://carboncredits.com/top-3-carbon-capture-leaders-to-drive-the-net-zero-race-in-2026/" target="_blank">Top 3 Carbon Capture Leaders to Drive the Net-Zero Race in 2026</a> (January 2026)</li>
                    <li id="ref-7" data-index="7"><strong>Energy Solutions Intelligence:</strong> <a href="https://energy-solutions.co/articles/sub/carbon-capture-direct-air-dac-cost-analysis" target="_blank">Direct Air Capture in 2026: Cost, Scale, and Path to $200/tCO2</a> (January 2026)</li>
                    <li id="ref-8" data-index="8"><strong>World Economic Forum:</strong> <a href="https://www.weforum.org/stories/2026/01/scale-carbon-capture-storage-climate-action/" target="_blank">How to scale carbon capture and storage for climate action</a> (January 2026)</li>
                    <li id="ref-9" data-index="9"><strong>International Energy Agency (IEA):</strong> <a href="https://www.iea.org/policies/16255-inflation-reduction-act-2022-sec-13104-extension-and-modification-of-credit-for-carbon-oxide-sequestration" target="_blank">Inflation Reduction Act 2022: Sec. 13104 Extension and Modification of Credit for Carbon Oxide Sequestration</a> (February 2026)</li>
                </ul>
            </div>

            <footer>
                <p style="text-align: center; color: var(--text-muted); font-size: 0.875rem; margin: 0;">&copy; 2026 Carbon Capture Intelligence. Compiled June 2026.</p>
            </footer>
        </div>
    </main>

</body>
</html>
```

The rendered report looks like this.

The two IDs

The two IDs do different jobs, as the table summarizes.

One tip: environment_id can be passed without previous_interaction_id. That reuses the files and installed packages but begins a fresh conversation, which suits forking the workspace for a new task.

Downloading files

Asking the agent to put file contents in its reply is one option, though usually not the preferred one. Often the file should come straight out of the sandbox. The listing below repeats the earlier multi-turn session that built a markdown report and an HTML version, and adds code at the end that downloads the whole environment snapshot as a tar file and extracts it into a local folder. That's what the Managed Agents environment currently supports.

import os
import requests
import tarfile
from google import genai
client = genai.Client()

# Turn 1: Research and create a report
interaction_1 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Research the current state of carbon capture technology in 2026. "
          "Write a comprehensive 500-word report and save it as report.md",
    environment="remote"
)
print(f"Environment ID: {interaction_1.environment_id}")
print(f"Interaction ID: {interaction_1.id}")
print(interaction_1.output_text)

# Turn 2: Build on the previous work - same sandbox, same files
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction_1.environment_id,       # ← Re-attaches to same Ubuntu sandbox
    previous_interaction_id=interaction_1.id,       # ← Preserves conversation memory
    input="Convert that report.md file into a clean index.html webpage "
          "with modern inline CSS styling and responsive design."
          " Please output the contents of the index.html file"
)
print(interaction_2.output_text)

env_id = interaction_2.environment_id
api_key = os.environ.get("GEMINI_API_KEY")

response = requests.get(
    f"https://generativelanguage.googleapis.com/v1beta/files/environment-{env_id}:download",
    params={"alt": "media"},
    headers={"x-goog-api-key": api_key},
    allow_redirects=True,
)

with open("snapshot_env.tar", "wb") as f:
    f.write(response.content)

os.makedirs("extracted_env_snapshot", exist_ok=True)
with tarfile.open("snapshot_env.tar") as tar:
    tar.extractall(path="extracted_env_snapshot")

At the time of writing there's no SDK method for this, so the snapshot comes from a direct REST call. After running the program, the extracted files appear in a local folder.

Customizing agents with skills and personas

In place of one huge prompt string, Antigravity uses a configuration system built on the filesystem. When the sandbox boots, it looks for a hidden .agents/ directory.

📁 Your-Project-Directory/
└── 📁 .agents/
    ├── 📄 AGENTS.md        ← Global system instructions (persona, rules, standards)
    └── 📁 skills/
        └── 📁 data-cleaner/
            └── 📄 SKILL.md ← Specific skill with step-by-step instructions

AGENTS.md as the persona

This file carries the base rules, behavioral limits and project background for the agent, much like a README it reads ahead of every task.

SKILL.md for modular expertise

Skills bundle domain expertise into reusable units, with YAML frontmatter for metadata and Markdown for the instructions.

---
name: data-cleaner
description: Use when the user needs to clean, normalize, or validate tabular data files.
---
# Data Cleaner
## When to Use
- User provides CSV, Excel, or JSON files that need cleaning
- Data has missing values, inconsistent formatting, or duplicate rows
## Steps
1. Load the data file using pandas
2. Profile the data: count nulls, duplicates, and type mismatches
3. Apply cleaning rules (fill nulls, normalize strings, deduplicate)
4. Save the cleaned output and generate a summary report

The central idea is progressive disclosure. The agent loads the full body of a SKILL.md only when it decides the skill matters for the current task. At startup it reads just the name and description from the frontmatter, which keeps the context window clean.

If a skill doesn't trigger when expected, the cause is almost always its frontmatter description. Make it more specific about when the skill should activate.

Creating a persistent agent

For production, a persistent agent configuration can be registered once so it doesn't have to be repeated. The Agents API creates a named agent, here with the data-cleaning skill from the previous section.

from google import genai

client = genai.Client()

# Register a reusable, named agent with the data-cleaner skill baked in
agent = client.agents.create(
    id="my-csv-cleaner",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a data quality engineer. Always use pandas for data manipulation. "
                       "Always generate a before/after summary showing what changed.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": (
                    "# Data Quality Agent\n\n"
                    "## Standards\n"
                    "- Never drop rows silently — log every removal with a reason\n"
                    "- Normalize all string columns to lowercase, stripped of whitespace\n"
                    "- Output cleaned files in UTF-8 CSV format\n"
                    "- Always print a summary table at the end\n"
                )
            },
            {
                "type": "inline",
                "target": ".agents/skills/data-cleaner/SKILL.md",
                "content": (
                    "---\n"
                    "name: data-cleaner\n"
                    "description: Use when the user needs to clean, normalize, or validate tabular data files.\n"
                    "---\n"
                    "# Data Cleaner\n\n"
                    "## When to Use\n"
                    "- User provides CSV, Excel, or JSON files that need cleaning\n"
                    "- Data has missing values, inconsistent formatting, or duplicate rows\n\n"
                    "## Steps\n"
                    "1. Load the data file using pandas\n"
                    "2. Profile the data: count nulls, duplicates, and type mismatches\n"
                    "3. Apply cleaning rules (fill nulls, normalize strings, deduplicate)\n"
                    "4. Save the cleaned output and generate a summary report\n"
                )
            }
        ]
    }
)

print(f"Agent created with ID: {agent.id}")

Saving that as create_csv_cleaner_agent.py and running it registers a persistent agent addressable by its ID, my-csv-cleaner.

To put it to work, first create a CSV file of deliberately messy customer records named messy_customers.csv.

name,email,phone,country
John Smith,john@example.com,+14155551234,US
jane doe, JANE@EXAMPLE.COM ,4155559999,
John Smith,john@example.com,+14155551234,US
Bob Wilson,bob@@invalid,+442071234567,
María García,maria@test.com,+34612345678,Spain
  alice brown ,alice@example.com,,US
Charlie Lee,charlie@test.com,+61412345678,AU
jane doe,jane@example.com,+14155559999,

Then the agent can be invoked by ID from anywhere in an app, using a script like run_csv_cleaner_agent.py.

from google import genai

client = genai.Client()

# Read your local CSV file
with open("messy_customers.csv", "r") as f:
    csv_content = f.read()

# Inject the file into the sandbox and tell the agent to clean it
interaction = client.interactions.create(
    agent="my-csv-cleaner",
    input="Clean the file at data/customers.csv. "
          "Remove duplicate rows by email (case-insensitive), "
          "standardize phone numbers to E.164 format, "
          "fill missing 'country' fields by looking up the phone country code, "
          "and flag any rows where the email format is invalid. "
          "Generate a before/after summary showing what changed.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": "data/customers.csv",   # ← Path inside the sandbox
                "content": csv_content             # ← Your local file contents
            }
        ]
    }
)

print(interaction.output_text)

The sources array in that script loads files into the sandbox ahead of the agent's start. To the agent, data/customers.csv is just a regular file on its Linux filesystem, and it has no idea the file was pushed from a local machine. Any type works, including CSV, JSON, XML, Python scripts and config files.

Notice that the prompt says nothing about pandas, UTF-8 or logging conventions. Those details already live in the AGENTS.md and SKILL.md that travel with the named agent, and the data-cleaner skill switches on automatically because the task text fits its description. A sample run is shown next.

I have successfully cleaned the customer dataset at `data/customers.csv` using Python and `pandas`.

Below is a detailed report and before/after summary of the transformations applied.

---

### Summary of Transformations

1. **whitespace Trimming:** Stripped all leading and trailing whitespace from both column names and text values (e.g., `  alice brown ` became `alice brown`).
2. **Email Normalization & Validation:**
   - Converted all email addresses to lowercase and trimmed whitespace.
   - Added a new column `email_invalid` (boolean) to flag emails with an invalid format.
   - Identified `bob@@invalid` as an invalid format (due to a duplicate `@` symbol and lack of a top-level domain).
3. **Phone Number Standardization:**
   - Standardized all valid phone numbers to the international **E.164** format using the `phonenumbers` library.
   - Converted `4155559999` (with a default US region fallback) to `+14155559999`.
   - Ignored the missing phone number for `alice brown` while leaving it empty.
4. **Country Code Lookup:**
   - Looked up and populated missing `country` values based on the telephone country code prefix.
   - Filled `jane doe`'s country as `US` (derived from prefix `+1`).
   - Filled `Bob Wilson`'s country as `GB` (derived from prefix `+44`).
   - Kept existing valid country entries (e.g., `Spain`, `US`, `AU`) intact.
5. **Deduplication:**
   - Removed duplicate rows by performing a case-insensitive match on the cleaned `email` column, keeping the first occurrence.
   - Safely removed the duplicate row for `john@example.com` (Row 3).
   - Safely removed the duplicate row for `jane@example.com` (Row 8).

---

### Before/After Summary

#### 1. Data Quality Metrics

| Metric | Before Clean | After Clean | Change Description |
| :--- | :---: | :---: | :--- |
| **Total Rows** | 8 | 6 | 2 duplicate rows were removed. |
| **Duplicates Removed** | 0 | 2 | Dropped rows 3 (`john@example.com`) and 8 (`jane@example.com`). |
| **Invalid Emails Flagged** | 0 | 1 | Flagged `bob@@invalid` as invalid (`email_invalid = True`). |
| **Standardized Phone Numbers** | 1 | 5 | All numbers formatted to E.164 (e.g., `4155559999` -> `+14155559999`). |
| **Filled Country Fields** | 5 | 6 | Filled 2 missing country values (`US` and `GB`) via phone prefix lookups. |

#### 2. Row-by-Row Comparison

Below is the row-by-row evolution from the raw file to the cleaned output:

| Row # | Name (Before) | Name (After) | Email (Before) | Email (After) | Phone (Before) | Phone (After) | Country (Before) | Country (After) | Email Invalid Flag | Action Taken / Status |
| :---: | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :---: | :--- |
| **1** | `John Smith` | `John Smith` | `john@example.com` | `john@example.com` | `+14155551234` | `+14155551234` | `US` | `US` | `False` | Retained as first unique instance. |
| **2** | `jane doe` | `jane doe` | ` JANE@EXAMPLE.COM ` | `jane@example.com` | `4155559999` | `+14155559999` | *Missing* | `US` | `False` | Email normalized; Phone formatted to E.164; Country populated from `+1` prefix. |
| **3** | `John Smith` | — | `john@example.com` | — | `+14155551234` | — | `US` | — | — | **Removed** (Duplicate email). |
| **4** | `Bob Wilson` | `Bob Wilson` | `bob@@invalid` | `bob@@invalid` | `+442071234567` | `+442071234567` | *Missing* | `GB` | `True` | Country populated from `+44` prefix; Email flagged as invalid. |
| **5** | `María García` | `María García` | `maria@test.com` | `maria@test.com` | `+34612345678` | `+34612345678` | `Spain` | `Spain` | `False` | Retained; Email valid; Preserved existing country. |
| **6** | `  alice brown ` | `alice brown` | `alice@example.com` | `alice@example.com` | *Missing* | *Missing* | `US` | `US` | `False` | Name whitespace stripped; Phone left empty; Preserved existing country. |
| **7** | `Charlie Lee` | `Charlie Lee` | `charlie@test.com` | `charlie@test.com` | `+61412345678` | `+61412345678` | `AU` | `AU` | `False` | Retained; Email valid. |
| **8** | `jane doe` | — | `jane@example.com` | — | `+14155559999` | — | *Missing* | — | — | **Removed** (Duplicate email). |

---

### Cleaned Dataset Output

The cleaned data has been written back to `data/customers.csv` and contains the following records:

```csv
name,email,phone,country,email_invalid
John Smith,john@example.com,+14155551234,US,False
jane doe,jane@example.com,+14155559999,US,False
Bob Wilson,bob@@invalid,+442071234567,GB,True
María García,maria@test.com,+34612345678,Spain,False
alice brown,alice@example.com,,US,False
Charlie Lee,charlie@test.com,+61412345678,AU,False
```

Real-world use cases

With the foundations in place, a few agents show how the pieces combine, and each introduces a new capability.

Use case one: refactoring code and fixing tests

Take a Python project with stale code and failing tests. An ordinary LLM returns snippets, leaving the developer to copy them, run the tests, debug and iterate manually. With Antigravity, the agent clones the code, runs the suite, reads terminal errors, patches the source and reruns the tests, looping until all of them pass.

A sample repository with deliberately buggy code serves as the target. It contains three root-cause bugs that together cause six test failures:

  1. calculate_total() in utils.py does arithmetic on a string tax_rate without converting it to a float.
  2. normalize_name() in utils.py crashes when given None, because there's no null check.
  3. Invoice.summary() in models.py refers to self.total, the method object, instead of calling self.total().

The agent that handles it is defined like this.

from google import genai
client = genai.Client()

system_instructions = """
You are an expert QA and Refactoring Engineer. Your workflow is:
1. Clone the target repository into the workspace
2. Install all dependencies from requirements.txt
3. Run the full pytest suite and capture all output
4. For each failing test:
   a. Read the error traceback carefully
   b. Open the source file causing the failure
   c. Diagnose the root cause
   d. Apply the minimal fix
5. Re-run pytest after each fix to confirm resolution
6. Continue until ALL tests pass (0 failures)
7. Generate a summary of every change you made
IMPORTANT: Make the minimal possible change to fix each test.
Do not refactor working code unnecessarily.
"""
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    system_instruction=system_instructions,
    input="""
    Clone this repository: https://github.com/rominirani/uc1-legacy-app
    Run the pytest suite to check for environment or code failures.
    Isolate the bugs causing test failures and fix them one by one.
    Keep running the tests until you achieve a 100% pass rate.
    When done, provide:
    1. A list of all files modified with a diff summary
    2. The final pytest output showing all tests passing
    3. Any dependency changes you had to make
    """,
    environment="remote"
)
print(interaction.output_text)

Save it as uc1_refactor.py and run it.

python3 uc1_refactor.py

The expected output follows.

I have successfully diagnosed and resolved all the issues causing test failures in the `uc1-legacy-app` repository. Below is a detailed summary of the findings, modifications, and the final test execution output.

---

### 1. Modified Files & Diff Summary

#### File: `src/models.py`
- **Issue**: In the `Invoice.summary()` method, the `self.total` method itself was passed to `format_currency()` as an object, instead of being invoked (`self.total()`). This led to a `TypeError` during format evaluation.
- **Fix**: Changed `self.total` to `self.total()`.
- **Diff Summary**:
```diff
@@ -23,7 +23,7 @@ class Invoice:
"""Return a one-line summary of the invoice."""
from src.utils import format_currency, normalize_name
name = normalize_name(self.customer_name)
-        return f"Invoice {self.invoice_id}: {name} - {format_currency(self.total)}"
+        return f"Invoice {self.invoice_id}: {name} - {format_currency(self.total())}"
```

#### File: `src/utils.py`
- **Issues**:
1. **`calculate_total()`**: When `tax_rate` is received as a string, Python fails to perform multiplication of float/string (`TypeError: can't multiply sequence by non-int of type 'float'`).
2. **`normalize_name()`**: When passed a `None` value (common in CSV imports), the code raised `AttributeError: 'NoneType' object has no attribute 'strip'`.
- **Fixes**:
1. Explicitly cast `subtotal` and `tax_rate` to `float` prior to calculating the tax.
2. Add a safeguard to return an empty string (`""`) when `name` is `None`.
- **Diff Summary**:
```diff
@@ -11,8 +11,10 @@ def calculate_total(subtotal, tax_rate):
Returns:
The total as a float rounded to 2 decimal places.
"""
-    tax = subtotal * tax_rate / 100
-    return round(subtotal + tax, 2)
+    subtotal_val = float(subtotal)
+    tax_rate_val = float(tax_rate)
+    tax = subtotal_val * tax_rate_val / 100
+    return round(subtotal_val + tax, 2)

def format_currency(amount):
@@ -36,6 +38,8 @@ def normalize_name(name):
Returns:
Cleaned, title-cased name.
"""
+    if name is None:
+        return ""
return name.strip().title()
```

---

### 2. Dependency Changes
No additional packages or dependency changes were made. All required libraries from `requirements.txt` (consisting of `pytest>=7.0.0`) were successfully installed and utilized without modification.

---

### 3. Final Pytest Output
Running the full suite confirms that all 10 tests now pass:

```
============================= test session starts ==============================
platform linux -- Python 3.12.3, pytest-9.0.3, pluggy-1.6.0
rootdir: /uc1-legacy-app
plugins: anyio-4.13.0
collected 10 items

tests/test_models.py ....                                                [ 40% ]
tests/test_utils.py ......                                               [100% ]

============================== 10 passed in 0.02s ==============================
```

Without any hand-holding, the agent:

  1. runs git clone in the sandbox terminal
  2. runs pip install -r requirements.txt into the sandbox's Python
  3. runs pytest -v and reads the whole output, tracebacks included
  4. opens the failing source files and locates the faulty logic
  5. writes patches, saves the files and runs pytest again
  6. repeats until the output shows zero failures

This is the plan, act, observe loop at work. The agent doesn't merely generate code. It executes it, reads real terminal output and corrects itself.

Use case two: competitive analysis

Say a team needs a thorough competitive analysis of rival products. Scraping by hand is tedious, and fixed scrapers break all the time. Here the agent searches Google with its browsing tools, crawls competitor sites, copes with differing page layouts, writes its own pandas script to organize the data and exports a finished spreadsheet.

from google import genai
client = genai.Client()

system_instructions = """
You are a precise Business Intelligence Analyst. Your workflow:
1. Use web search to find current, real-time information
2. Navigate to official product/pricing pages for each competitor
3. Extract: pricing tiers, key features, target audience, notable limitations
4. Structure ALL findings into a pandas DataFrame
5. Export to both CSV and a formatted Markdown comparison table
6. Include the date/time of research and source URLs for every data point
Rules:
- Only report data you can verify from official sources
- If pricing isn't publicly available, note "Contact Sales" - don't guess
- Use USD for all pricing normalization
"""
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    system_instruction=system_instructions,
    input="""
    Research the pricing models and core feature matrices of the top 3 alternative
    platforms to Vercel for frontend deployment:
    1. Netlify
    2. Cloudflare Pages
    3. Cloud Run
    For each, extract:
    - Free tier limits (bandwidth, builds, sites)
    - Pro/paid tier pricing and what it unlocks
    - Key differentiating features
    - Notable limitations or complaints from developer communities
    Create:
    1. A competitive_matrix.csv spreadsheet with all data
    2. A competitive_analysis.md report with a formatted comparison table
       and a "Recommendation" section at the bottom
    """,
    environment="remote"
)
print(interaction.output_text)

It produces this report.

As a Business Intelligence Analyst, I have conducted a precise competitive analysis of the top three frontend deployment alternatives to Vercel: **Netlify**, **Cloudflare Pages**, and **Google Cloud Run**.

All findings have been structured using `pandas` and exported to `/` (the current working directory) as:
1. `competitive_matrix.csv` — The raw, structured dataset.
2. `competitive_analysis.md` — A comprehensive, reader-ready report including a detailed markdown comparison matrix, architectural breakdowns, limitation analyses, and a tailored recommendation framework.

All data has been verified against official vendor pricing, product, and developer documentation as of **June 9, 2026**. All currency values are normalized in **USD**.

---

### Core Finding Highlights

#### 1. Netlify
* **The Architectural Shift (April 2026):** Netlify made a massive strategic update to its Pro plans, moving from a seat-based model ($19/member/month) to a **flat $20/month per organization** [10]. This includes unlimited team members (Owners, Developers, Reviewers, and Git Contributors) [10], which is highly disruptive compared to Vercel's strict per-seat billing.
* **The Credits Trap:** Usage is now managed entirely via a unified credit-based model (300 credits/mo free, 3,000 on Pro) [2, 10]. However, credits are consumed fast: bandwidth costs 20 credits per GB [2, 10] (meaning Free tier is only **~15 GB max** and Pro is only **~150 GB max** if solely used for traffic). If Free tier credits run out, **all site traffic pauses immediately** (no auto-recharge is supported on Free) [2, 11].
* **Capabilities:** Highly integrated features like Netlify Database (managed Postgres via Neon) [4], Blob storage, Forms, and Auth [10]. Serverless timeout is 10s on Free/Personal [2] and 26s on Pro [2].

#### 2. Cloudflare Pages
* **Unmetered Freedom:** Genuinely **unlimited and unmetered static bandwidth and requests** across all tiers (including the $0 Free tier) [24, 25, 27].
* **The Pro Tier ($20/mo billed annually / $25/mo monthly):** Tied directly to Cloudflare's Workers Paid plan [25, 27]. It increases build limits from 500/mo to 5,000/mo, concurrent builds from 1 to 5, and the file-count ceiling per project from 20,000 to 100,000 assets [31] (unlocked via the `PAGES_WRANGLER_MAJOR_VERSION=4` env variable) [31].
* **Edge Isolates Constraints:** While running serverless code on Cloudflare's global network of 310+ cities is blazingly fast with zero cold starts [24, 33], it uses a **strict V8 edge runtime** [24]. Standard Node.js library modules (`fs`, `path`, native `crypto`) do not run natively [24], forcing developers to compile meta-frameworks like Next.js via edge adapters (e.g., `@cloudflare/next-on-pages` or OpenNext) [24] which restricts certain features like Incremental Static Regeneration (ISR).

#### 3. Google Cloud Run
* **Pure Container Portability:** Cloud Run runs any application, language, or compiled binary (Node.js, Python, Go, Rust) packaged in a standard Docker container [37, 39]. It runs full Node.js natively [39], ensuring 100% Next.js feature parity (ISR, Server Actions, dynamic image optimization) with zero edge-runtime workarounds [39].
* **No Monthly Base Fee:** Operates on a pure pay-as-you-go serverless model (billed in granular vCPU-seconds and GiB-seconds) [41], backed by a generous Always Free tier (2 million requests/mo, 180,000 vCPU-seconds, 360,000 GiB-seconds, and 120 daily Cloud Build minutes free) [37, 38, 41].
* **The Infrastructure Overhead:** Not a standard "push-to-deploy" platform. Developers must write Dockerfiles, configure Artifact Registry, and manage IAM and networking [37, 39]. It is regionally hosted; to get a global CDN with SSL mapping, you must set up Cloud CDN and a Global HTTP Load Balancer [37] (~$20-$30/mo base fee) and navigate container cold starts (2 to 10+ seconds) [37] and expensive internet egress rates ($0.085 - $0.12 per GB) [37].

---

### Structure of Generated Files

#### 1. `competitive_matrix.csv`
A raw, tabular CSV structured for business intelligence pipelines, featuring the following schema:
- `Platform Name`
- `Free Tier Pricing (USD)`
- `Free Tier Bandwidth Limit`
- `Free Tier Build Limit`
- `Free Tier Sites/Projects Limit`
- `Free Tier Key Specs & Features`
- `Paid/Pro Tier Price (USD)`
- `Paid/Pro Tier Features Unlocked`
- `Key Differentiating Features`
- `Notable Limitations & Developer Complaints`
- `Date of Research`
- `Source URLs`

#### 2. `competitive_analysis.md`
A professionally formatted report including:
* **Executive Summary:** Contextualizing why frontend teams are exploring alternatives to Vercel in 2026.
* **Structured Comparison Table:** Transposed for high-density reading and side-by-side comparison.
* **Deep-Dive Section:** Dedicated analyses of the Free limits, paid features, unique differentiators, and community complaints for Netlify, Cloudflare Pages, and Google Cloud Run.
* **Architectural Recommendation Flowchart & Matrix:** Tailored decision pathways based on project profile:
  * *Static / JAMstack / Zero-Budget* $\rightarrow$ **Cloudflare Pages**
  * *Collaborative Teams / Rapid Prototyping / Seat-Free DX* $\rightarrow$ **Netlify**
  * *Complex Server-Side Rendering / Backend Pipelines / Custom Docker* $\rightarrow$ **Google Cloud Run**

---

### Source Verification & Citations

1. **Netlify:**
   - [Official Pricing & Plans](https://www.netlify.com/pricing/)
   - [Introducing Seat-Free Collaborative Billing (April 14, 2026)](https://www.netlify.com/blog/pricing-netlify-for-3-billion-builders/)
   - [Credit-Based Pricing Documentation](https://docs.netlify.com/manage/accounts-and-billing/billing/billing-for-credit-based-plans/credit-based-pricing-plans/)
   - [Netlify Free Tier Credit Analysis (Temps)](https://temps.sh/compare/vs-netlify)

2. **Cloudflare Pages:**
   - [Workers & Pages Pricing Matrix](https://www.cloudflare.com/plans/developer-platform/)
   - [Official Pages Limits Documentation](https://developers.cloudflare.com/pages/platform/limits/)
   - [Cloudflare Pages Platform Features](https://pages.cloudflare.com/)
   - [Cloudflare Pages Edge Limitations (Temps)](https://temps.sh/compare/vs-cloudflare-pages)

3. **Google Cloud Run:**
   - [Official Cloud Run Pricing Breakdown](https://cloud.google.com/run/pricing)
   - [Google Cloud Free Tier Inclusions](https://cloud.google.com/free)
   - [Cloud Run Quotas & Limits](https://docs.cloud.google.com/run/quotas)
   - [Cloud Run Cost Optimization & Egress Guide (Cloudchipr)](https://cloudchipr.com/blog/cloud-run-pricing)

The generated files are saved directly in your working directory and are immediately available for download or integration into your reporting pipelines. Let me know if you would like me to modify the analysis parameters or explore a specific platform further!

A follow-up can reuse the previous environment and interaction, taking the generated competitive_matrix.csv and turning it into a visualization. The code below retrieves only the text reply, but the download technique shown earlier can extract the generated files from the sandbox.

# Follow-up: generate a visual chart from the data we just collected
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction.environment_id,
    previous_interaction_id=interaction.id,
    input="""
    Using the competitive_matrix.csv you just created:
    1. Create a grouped bar chart comparing the free tier limits across all 3 platforms
    2. Create a pricing comparison chart for the paid tiers
    3. Save both charts as PNG files with clear labels and a professional color scheme
    4. Add the charts as embedded images in the competitive_analysis.md report
    """
)
print(interaction_2.output_text)

The concept here is web browsing combined with code execution in a single task. The agent searches the live internet, then writes Python to structure and visualize what it found, all in one flow.

Patterns that hold up in production

Expect to rebuild. Model performance improves quickly, so design agents on the assumption that they'll be rebuilt on newer models soon. Keep configuration modular, since AGENTS.md and SKILL.md files are easy to swap, and don't over-engineer the orchestration layer.

Split big agents up. Avoid one massive agent with a 2,000-word system prompt. Break complex problems into specialized sub-agents.

Treat errors as inputs, not crashes. In sound agentic designs, errors are data the agent uses to reflect and correct. It reads a TypeError, reasons about the cause and fixes it. Skip the blanket try/except blocks that swallow failures and let the agent see them.

Use evals instead of unit tests. Agent behavior isn't deterministic, so testing should focus on evaluation metrics and not on exact output matching.

# ❌ Don't: Assert exact output
assert agent_output == "The answer is 42"

# ✅ Do: Evaluate behavioral success rate
results = [run_agent(task) for _ in range(20)]
success_rate = sum(1 for r in results if r.meets_criteria) / len(results)
assert success_rate >= 0.85  # Agent succeeds at least 85% of the time

Watch token cost. Because the agent runs an autonomous reasoning loop, one prompt can trigger many internal operations, so the cost per task varies a good deal. This table gives a rough idea.

Use strict timeouts and monitor trace lengths during development, and use system_instruction to ask the agent to be concise when verbose reasoning isn't needed.

Plan for failure. Error-handling patterns for common failure cases are summarized here.

How it works under the hood

Several mechanics explain the behavior seen above:

  • One API call, interactions.create(), starts a server-side orchestration loop. A Gemini Flash model keeps reasoning, choosing tools, running code and reviewing results until the task is done.
  • Every interaction gets its own isolated Ubuntu container, configured with 4 vCPUs and 16 GB of RAM, where the model can install packages, run scripts and manage files.
  • Passing a returned environment_id into later calls preserves files and state across turns, which avoids creating a fresh sandbox each time.
  • When an agent configuration is stable, including its system instructions and file-based skills, it can be saved permanently with client.agents.create() and invoked anywhere by ID.

Ideas for the next agent

  • A CI/CD agent that watches a GitHub repository, runs tests on every push and opens fix PRs for failures
  • A documentation generator that reads a codebase and writes complete API docs
  • A data pipeline orchestrator that connects to a warehouse, runs transformations and validates output
  • A support triage agent that reads tickets, rates severity, drafts replies and escalates critical issues
  • A research assistant that takes a topic, searches papers and articles, and writes a literature review with citations

What changes

Managed Agents change how AI gets built. Developers stop assembling the infrastructure around the model and just give it a goal and a sandbox to work in. The sandbox is the abstraction, the agentic loop drives it, and the Interactions API is the one entry point. A sensible way to begin is small, with firm limits on what the agent may do unattended, then scale up.

← All articlesSend the brief