### Python SDK - PyGEAI Getting Started

Source: https://docs.globant.ai/en/wiki?1980%2CHow+to+expose+a+Flow+through+WhatsApp+Client+%282025-04+or+prior%29=

This section guides users on how to get started with the PyGEAI Python SDK. It typically involves installation and basic setup to interact with Globant Enterprise AI services.

```python
pip install pygeai

from pygeai import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Example usage: List available agents
agents = client.agents.list()
print(agents)
```

--------------------------------

### Install and Configure QE Test Case Analyzer

Source: https://docs.globant.ai/en/wiki?3607%2CTest+Case+Analyzer+Quickstart%2CViews=

Instructions for deploying the agent file to the local CODA CLI directory and verifying its availability.

```bash
cp qe-test-case-analyzer.md ~/.coda/agents/qe-test-case-analyzer.md
coda
/agents
```

--------------------------------

### Promote Development to Production (New Project)

Source: https://docs.globant.ai/en/wiki?3605%2Cgeai+migrate+clone-project+command+samples%2CHistory=

Promotes a development project to production by creating a new production project. Requires development and production API keys, organization keys, project IDs, instance URLs, a new production project name, and admin email. Migrates all resources.

```bash
geai migrate clone-project \
  --from-api-key "dev_project_api_key" \
  --from-org-key "dev_org_api_key" \
  --from-project-id "dev-project-id" \
  --from-instance "https://api.dev.example.ai" \
  --to-api-key "prod_project_api_key" \
  --to-org-key "prod_org_api_key" \
  --to-project-name "Production Release v1.0" \
  --to-instance "https://api.prod.example.ai" \
  --admin-email "prod-admin@example.com" \
  --all

```

--------------------------------

### Python SDK (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?1033%2CAgents+Dashboard%2CForwardlinks=

This snippet provides a basic example of how to get started with the PyGEAI Python SDK. It demonstrates initial setup and potential usage patterns. Ensure you have the PyGEAI library installed.

```python
from pygeai import GeaiClient

# Initialize the client with your API key and endpoint
client = GeaiClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Example usage: List available agents
agents = client.agents.list()
print(agents)
```

--------------------------------

### Create Project - cURL Example

Source: https://docs.globant.ai/en/wiki?22%2COrganization+API%2C=

Demonstrates how to create a new AI project using a cURL command. It includes the necessary headers and a JSON payload for the request.

```shell
curl -X POST "$BASE_URL/v1/organization/project" \
 -H "Authorization: Bearer $GEAI_APITOKEN" \
 -H "accept: application/json" \
 -d '{ \
      "name": "my Project", \
      "description": "My awesome Project", \
      "administratorUserEmail": "myemail@globant.com" \
 }'
```

--------------------------------

### Python SDK for Globant Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?1167%2CPrompt+composition+for+Agents+and+Tasks+within+Agentic+Processes%2CBacklinks=

This section guides users on how to get started with the PyGEAI Python SDK. It covers installation and initial setup for interacting with Globant Enterprise AI services.

```python
pip install pygeai

from pygeai import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

print("PyGEAI client initialized successfully.")
```

--------------------------------

### Create Test Plan (Quick Reference)

Source: https://docs.globant.ai/en/wiki?3754%2CPrincipal+Performance+Architect+Agent%2CArticle=

This entry offers a quick reference prompt for creating a test plan. The user should specify the application type when making the request.

```text
Create test plan | "Help me create a performance test plan for \application type\"
```

--------------------------------

### Python SDK - PyGEAI Getting Started

Source: https://docs.globant.ai/en/wiki?408%2CStart+Page=

This section guides users on getting started with the PyGEAI Python SDK. It typically covers installation, basic setup, and initial usage patterns for interacting with Globant Enterprise AI services.

```python
from pygeai import GEAI

# Initialize the GEAI client
geai = GEAI(api_key="YOUR_API_KEY")

# Example: List available agents
agents = geai.agents.list()
print(agents)
```

--------------------------------

### Promote project from development to production

Source: https://docs.globant.ai/en/wiki?3605%2Cgeai+migrate+clone-project+command+samples%2C=

Automates the promotion of a project to a production environment by creating a new project instance. Requires both development and production API keys and organization keys.

```bash
geai migrate clone-project \
  --from-api-key "dev_project_api_key" \
  --from-org-key "dev_org_api_key" \
  --from-project-id "dev-project-id" \
  --from-instance "https://api.dev.example.ai" \
  --to-api-key "prod_project_api_key" \
  --to-org-key "prod_org_api_key" \
  --to-project-name "Production Release v1.0" \
  --to-instance "https://api.prod.example.ai" \
  --admin-email "prod-admin@example.com" \
  --all
```

--------------------------------

### Python SDK: Get Started with PyGEAI

Source: https://docs.globant.ai/en/wiki?1949%2CTools%2CViews=

Provides a basic example of how to get started with the PyGEAI Python SDK. This includes installation and a simple usage pattern, likely involving authentication and a basic API call. Assumes the SDK is installed.

```python
# First, ensure you have the SDK installed:
# pip install globant-enterprise-ai

from globant_enterprise_ai.client import GEAIClient

# Initialize the client with your API key or other credentials
# Replace 'YOUR_API_KEY' with your actual API key
# client = GEAIClient(api_key="YOUR_API_KEY")

# Placeholder for client initialization
class MockGEAIClient:
    def __init__(self, api_key):
        print(f"GEAIClient initialized with API key: {api_key[:4]}... (hidden)")
    def get_status(self):
        return {"status": "connected", "version": "1.0.0"}

client = MockGEAIClient(api_key="YOUR_API_KEY")

# Example: Get the client status
status = client.get_status()
print(f"API Status: {status['status']}, Version: {status['version']}")

```

--------------------------------

### Getting Started with PyGEAI Python SDK

Source: https://docs.globant.ai/en/wiki?170%2CHow+to+create+a+Chat+with+Data+Assistant%2C=

This snippet provides guidance on getting started with the PyGEAI Python SDK. It covers initial setup, installation, and basic usage for developers.

```python
Getting started with PyGEAI
```

--------------------------------

### Clarifying Rules with Examples in AGENTS.md (Markdown Example)

Source: https://docs.globant.ai/en/wiki?3887%2CCA+AGENTS.md%2CArticle=

Illustrates the importance of providing clear examples within AGENTS.md to avoid ambiguity. It contrasts a vague instruction with a specific, actionable example for component naming conventions.

```markdown
- Component naming:
  Bad: Comp1.tsx, Util.tsx
  Good: UserProfileCard.tsx, DateFormatter.tsx
```

--------------------------------

### Getting Started with PyGEAI (Python)

Source: https://docs.globant.ai/en/wiki?1165%2C%2C=

This Python code snippet provides a basic example of getting started with the PyGEAI SDK. It demonstrates initial setup and a simple API call.

```python
from pygeai import GEAIClient

# Initialize the client with your API key
# client = GEAIClient(api_key="YOUR_API_KEY")

# Example: Making a simple API call (e.g., listing agents)
# try:
#     agents = client.list_agents()
#     print("Successfully retrieved agents:", agents)
# except Exception as e:
#     print(f"An error occurred: {e}")

print("PyGEAI getting started example. Replace placeholders with actual credentials and calls.")
```

--------------------------------

### Performance Best Practices: Small AGENTS.md Files (Text Example)

Source: https://docs.globant.ai/en/wiki?3887%2CCA+AGENTS.md%2CArticle=

Recommends using smaller, focused `AGENTS.md` files in different directories for better performance. It provides an example structure with line count suggestions for general, frontend, and backend rules.

```text
project/AGENTS.md (20-30 lines)
  → General rules, stack, basic commands

project/frontend/AGENTS.md (50-100 lines)
  → Detailed React rules, components, styles

project/backend/AGENTS.md (50-100 lines)
  → Detailed API rules, validations, DB
```

--------------------------------

### Install and Setup PyGEAI Environment

Source: https://docs.globant.ai/en/wiki?1149%2CGetting+started+with+PyGEAI=

Commands to create a Python virtual environment and install the PyGEAI SDK package via pip.

```bash
python3 -m venv venv
source venv/bin/activate
pip install pygeai
```

--------------------------------

### Execute CODA Batch Commands

Source: https://docs.globant.ai/en/wiki?3471%2CGetting+Started+with+CODA+Batch%2CArticle=

Demonstrates basic usage of the coda-batch CLI to perform tasks such as analyzing source code files, generating project documentation, and processing piped input strings.

```bash
coda-batch -p "Analyze the main.py file and suggest improvements"
coda-batch -p "Create a README for this project"
echo "hi there!" | coda-batch
```

--------------------------------

### Create Performance Test Plan (Example Interaction)

Source: https://docs.globant.ai/en/wiki?3754%2CPrincipal+Performance+Architect+Agent%2CArticle=

This interaction shows the AI's capability to help users create a performance test plan for a new microservices architecture. It initiates the process by asking clarifying questions about performance objectives, user load, SLAs, and architecture setup.

```text
User: "I need a performance test plan for a new microservices architecture" 

Agent: "I'll help you create a comprehensive test plan. Let's start with some key questions: 1. What are your primary performance objectives? 2. What's the expected user load and usage patterns? 3. Do you have specific SLA requirements? 4. What's your current architecture setup? ..."
```

--------------------------------

### Python SDK for Globant Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?1521%2CDifferences+between+Agentic+Processes+and+Flows%2CArticle=

This snippet demonstrates how to get started with the PyGEAI Python SDK. It covers basic setup and initialization for interacting with Globant Enterprise AI services. Ensure you have the PyGEAI library installed (`pip install pygeai`).

```python
from pygeai import GEAIClient

# Initialize the client with your API key and base URL
client = GEAIClient(api_key="YOUR_API_KEY", base_url="YOUR_BASE_URL")

print("GEAIClient initialized successfully.")
```

--------------------------------

### Execute QE Test Case Analyzer

Source: https://docs.globant.ai/en/wiki?3607%2CTest+Case+Analyzer+Quickstart%2CViews=

Commands and input formats required to invoke the agent and provide the necessary user story and existing test case data.

```text
@qe-test-case-analyzer

As a user role, I want to goal so that benefit

1. Test case title - Brief description
2. Test case title - Brief description
```

--------------------------------

### Python SDK - PyGEAI: Getting Started

Source: https://docs.globant.ai/en/wiki?3606%2Cgeai+migrate+clone-project+command+troubleshooting=

This section guides users on how to get started with the PyGEAI Python SDK. It covers initial setup and basic usage for interacting with Globant Enterprise AI services.

```python
from geai import GEAI

# Initialize the GEAI client
geai_client = GEAI(api_key="YOUR_API_KEY")

# Example: List available agents
agents = geai_client.agents.list()
print(agents)
```

--------------------------------

### Python SDK - PyGEAI Getting Started

Source: https://docs.globant.ai/en/wiki?1040%2CJSON+Tab+of+an+Agent%2CBacklinks=

This section provides instructions on how to get started with the PyGEAI Python SDK. It covers installation and initial setup for using Globant Enterprise AI functionalities through Python.

```python
pip install pygeai

from pygeai import GEAIClient

client = GEAIClient(api_key="YOUR_API_KEY")
print("GEAIClient initialized successfully.")
```

--------------------------------

### Initialize AGENTS.md with a template

Source: https://docs.globant.ai/en/wiki?3887%2CCA+AGENTS.md%2CTalk=

A standard template for structuring agent instructions, including tech stack, code rules, commands, and restrictions.

```markdown
# Agent Instructions

## Tech Stack

- Your stack: React, Node, Python, etc.

## Code Rules

- Naming conventions
- Complexity limits
- Preferred patterns

## Main Commands

- Build: command
- Test: command
- Lint: command

## Restrictions
- What it should NOT do
```

--------------------------------

### Agent Setup and Guidelines

Source: https://docs.globant.ai/en/wiki?3075%2CHow+to+create+the+Web+Search+Agent+manually%2CTalk=

Details the agent's role, background knowledge, and general guidelines for its operation.

```APIDOC
## Agent Setup

### Background Knowledge

You are an expert in web search, skilled at finding and summarizing information from the internet.

### Guidelines

- You are a helpful search assistant. Your goal is to write an accurate, detailed, and comprehensive answer to the Query, drawing from the given search results.
- You will be provided sources from the internet to help you answer the Query. Your answer should be informed by the provided "Search results".
- Another system has done the work of planning out the strategy for answering the Query, issuing search queries, math queries, and URL navigations to answer the Query, all while explaining their thought process.
- The user has not seen the other system's work, so your job is to use their findings and write an answer to the Query.
- Although you may consider the other system's when answering the Query, your answer must be self-contained and respond fully to the Query.
- Your answer must be correct, high-quality, well-formatted, and written by an expert using an unbiased and journalistic tone.

### Tools

- **get_search_api_v1_web_search__get_get**: Performs a web search, it returns a list of URLs
- **tool_web_scraper_httpx_post**: Fetch content from web pages, it must be used to scrape the list of URLs got by get_search_api_v1_web_search__get_get

### Instructions

- According to each query and in order to get updated data
- You must use the tools get_search_api_v1_web_search__get_get to get a list of URLs
- Then use the tool tool_web_scraper_httpx_post to scrape each web page, you must scrape at least three web pages. Do not scrape PDFs, If the URL has a .pdf at the end, avoid scraping this web page.
- Then summarize your results.

### Format Rules

Write a well-formatted answer that is clear, structured, and optimized for readability using Markdown headers, lists, and text. Below are detailed instructions on what makes an answer well-formatted.

**Answer Start**:

- Begin your answer with a few sentences that provide a summary of the overall answer.
- NEVER start the answer with a header.
- NEVER start by explaining to the user what you are doing.

**Headings and sections**:

- Use Level 2 headers (##) for sections. (format as "## Text")
- If necessary, use bolded text (**) for subsections within these sections. (format as "Text")
- Use single new lines for list items and double new lines for paragraphs.

**Paragraph text**: Regular size, no bold

- NEVER start the answer with a Level 2 header or bolded text

**List Formatting**:

- Use only flat lists for simplicity.
- Avoid nesting lists, instead create a markdown table.
- Prefer unordered lists. Only use ordered lists (numbered) when presenting ranks or if it otherwise make sense to do so.
- NEVER mix ordered and unordered lists and do NOT nest them together. Pick only one, generally preferring unordered lists.
- NEVER have a list with only one single solitary bullet

**Tables for Comparisons**:

- When comparing things (vs), format the comparison as a Markdown table instead of a list. It is much more readable when comparing items or features.
- Ensure that table headers are properly defined for clarity.
- Tables are preferred over long lists.

**Emphasis and Highlights**:

- Use bolding to emphasize specific words or phrases where appropriate (e.g. list items).
- Bold text sparingly, primarily for emphasis within paragraphs.
- Use italics for terms or phrases that need highlighting without strong emphasis.

**Code Snippets**:

- Include code snippets using Markdown code blocks.
- Use the appropriate language identifier for syntax highlighting.

**Mathematical Expressions**:

- Wrap all math expressions in LaTeX using `$` for inline and `$$` for block formulas. For example: $x^4 = x - 3$
- To cite a formula add citations to the end, for example $\sin(x)^{12}$ or $x^2 - 2^{4}$.
- Never use $ or $$ to render LaTeX, even if it is present in the Query.
- Never use unicode to render math expressions, ALWAYS use LaTeX.
- Never use the `\label` instruction for LaTeX.

**Quotations**:

- Use Markdown blockquotes to include any relevant quotes that support or supplement your answer.

**Citations**:

- You MUST cite search results used directly after each sentence it is used in.
- The citation must be an hyperlink following this format: (index reference)(URL). The index must be between parentheses.
- Each index should be enclosed in its own brackets and never include multiple indices in a single bracket group.
- Do not leave a space between the last word and the citation.
- Cite up to three relevant sources per sentence, choosing the most pertinent search results.
- You MUST NOT include a References section, Sources list, or long list of citations at the end of your answer.
- Please answer the Query using the provided search results, but do not produce copyrighted material verbatim.
- If the search results are empty or unhelpful, answer the Query as well as you can with existing knowledge.

**Answer End**:

```

--------------------------------

### Python SDK for Globant Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?145%2CRAG+Index+Configuration%2CArticle=

This snippet provides a basic example of how to get started with the PyGEAI Python SDK. It demonstrates initial setup and common usage patterns for interacting with Globant Enterprise AI services.

```python
from geai_sdk import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Example: Interact with an AI model
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### Create a project backup

Source: https://docs.globant.ai/en/wiki?3605%2Cgeai+migrate+clone-project+command+samples%2C=

Creates a full backup of an existing project by cloning it into a new project with a timestamped name. Uses the current date to ensure unique naming.

```bash
geai migrate clone-project \
  --from-api-key "project_api_key" \
  --from-org-key "org_api_key" \
  --from-project-id "main-project-id" \
  --from-instance "https://api.example.ai" \
  --to-org-key "org_api_key" \
  --to-project-name "Main Project Backup $(date +%Y-%m-%d)" \
  --admin-email "admin@example.com" \
  --all
```

--------------------------------

### Python SDK for Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?984%2CHow+to+create+a+Private+Integration=

This snippet demonstrates the initial steps for getting started with the PyGEAI Python SDK. It covers basic setup and authentication, which are crucial for interacting with Enterprise AI services. Ensure you have the SDK installed and your API credentials configured.

```python
from geai.sdk import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Example: List available agents
agents = client.agents.list()
print(agents)
```

--------------------------------

### Extend Existing UI Automation Framework

Source: https://docs.globant.ai/en/wiki?3596%2CTest+Automation=

This example shows how to use the '@qe-ui-automation-code-creation' agent to add new feature automation to an existing Selenium/TestNG framework. It emphasizes following existing patterns and reusing components.

```shell
> @qe-ui-automation-code-creation I have an existing Selenium/TestNG framework.
  Add automation for the new user profile feature:

  - User can view profile
  - User can edit name and email
  - User can change password
  - User can upload avatar image

  Follow the existing patterns and reuse the BasePage and utilities.


```

--------------------------------

### Python SDK for Globant Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?972%2CAgents%2CTalk=

This snippet demonstrates how to get started with the PyGEAI SDK for Globant Enterprise AI. It covers basic setup and initialization, which is essential for interacting with the platform's features programmatically. Ensure you have the PyGEAI library installed.

```python
from geai.sdk import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Now you can use the client to interact with Globant Enterprise AI services
print("GEAI Client initialized successfully.")
```

--------------------------------

### Create Project - Basic

Source: https://docs.globant.ai/en/wiki?22%2COrganization+API%2C=

Creates a new AI project with a name, description, and administrator email. This is a fundamental operation for setting up a new project environment.

```json
{
  "name": "my Project",
  "description": "My awesome Project",
  "administratorUserEmail": "myemail@globant.com"
}
```

--------------------------------

### Python SDK for Globant Enterprise AI (PyGEAI) - Getting Started

Source: https://docs.globant.ai/en/wiki?1168%2CLLMs+with+Reasoning+Capabilities=

This snippet demonstrates the initial steps to get started with the PyGEAI Python SDK. It covers basic setup and authentication, which are crucial for interacting with Globant Enterprise AI services. Ensure you have the SDK installed and your API credentials configured.

```python
from geai.client import GEAIClient

# Initialize the client with your API key and endpoint
client = GEAIClient(api_key="YOUR_API_KEY", endpoint="YOUR_ENDPOINT")

# Now you can use the client to interact with various GEAI services
print("GEAI Client initialized successfully.")
```

--------------------------------

### Python SDK - PyGEAI - Getting Started

Source: https://docs.globant.ai/en/wiki?1974%2C%2C=

Getting started guide for the PyGEAI Python SDK.

```APIDOC
## Python SDK - PyGEAI - Getting Started

### Description
Getting started guide for the PyGEAI Python SDK.

### Method
GET

### Endpoint
/developers/sdks/pygeai/gettingstarted
```

--------------------------------

### Configure MCP Servers for CODA CLI

Source: https://docs.globant.ai/en/wiki?3597%2CUI+Flaky+Test+Fixer+Quickstart%2CViews=

Configuration schema for integrating Playwright and Web Inspector MCP servers into the CODA CLI environment to enable browser automation and DOM analysis.

```json
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "autoApprove": [
        "browser_navigate",
        "browser_snapshot",
        "browser_take_screenshot",
        "browser_handle_dialog",
        "browser_type",
        "browser_click"
      ]
    },
    "mcp-web-inspector": {
      "command": "npx",
      "args": ["-y", "mcp-web-inspector"]
    }
  }
}
```