MODSetter/SurfSense: A Software Engineer's Guide to Workflow Automation

MODSetter/SurfSense

This tool acts as a powerful, open-source knowledge assistant that integrates directly into your workflow. Instead of switching between multiple tabs and applications to gather information, you can bring all that data to you. Think of it as having an AI-powered brain that can access all your key professional and project sources—like Slack, Jira, GitHub, and even the web—in one place.

<br>

MODSetter/SurfSense is incredibly useful for a software engineer because it helps streamline your daily tasks and decision-making processes. Here are some key benefits

Faster Problem Solving
When you encounter a bug, you often need to check a bug ticket in Jira, a related conversation in Slack, and code changes in GitHub. With this tool, you can get a summary of all this information without leaving your current page. It's like having a single search bar for your entire project ecosystem.

Onboarding New Team Members
A new engineer can quickly get up to speed on a project by asking the tool questions like, "What's the status of the login-flow feature?" or "Show me the recent discussions about the database-migration." This drastically reduces the time and effort required to navigate existing documentation and communication logs.

Enhanced Code Reviews
As you're reviewing a pull request, you can use the tool to instantly pull up related discussions or bug reports. This provides crucial context, allowing you to make more informed decisions and provide better feedback.

Centralized Knowledge
Instead of losing important information scattered across various platforms, MODSetter/SurfSense helps you create a unified knowledge base. This reduces information silos and makes it easier for the entire team to access key insights.

<br>

Getting MODSetter/SurfSense up and running involves a few simple steps. The process generally consists of installing the Chrome extension and then setting up the Python backend to connect to your various data sources.

Install the Chrome Extension
This is the frontend of the tool. You'll install it from the Chrome Web Store (or by loading it as an unpacked extension from the project's GitHub repository). This extension will be your main interface for querying and interacting with your data.

Clone the Python Backend
The core logic, including all the integrations with services like Slack, Jira, and GitHub, is managed by a Python backend. You'll need to clone the project's repository from GitHub.

Configure Your Integrations
This is the most important step. You'll need to create configuration files or set environment variables with your API keys and tokens for the services you want to connect. For example, you'll need a Slack API token to pull in conversation history or a Jira API token to access tickets. The project's documentation will guide you on how to do this for each service.

Run the Backend
Once configured, you'll start the Python server. This server will handle your requests, fetch data from the connected sources, and process it before sending it back to your Chrome extension.

<br>

Here's a simplified look at how the backend might be structured and what a query-response cycle looks like from a code perspective.

Let's imagine you've set up the Slack and Jira integrations. The user in the Chrome extension asks, "What's the status of the API-123 Jira ticket and the recent discussion about it in Slack?"

from modsetter.integrations import Jira, Slack

# Initialize our integrations with credentials
jira_client = Jira(api_key='YOUR_JIRA_KEY')
slack_client = Slack(token='YOUR_SLACK_TOKEN')

def handle_user_query(query):
    # This is a simplified logic to demonstrate the flow
    if 'API-123' in query:
        # Fetch ticket details from Jira
        jira_ticket = jira_client.get_ticket('API-123')
        
        # Search for related discussions in Slack
        slack_messages = slack_client.search_messages('API-123')
        
        # Combine the data into a single response
        response = {
            'jira_status': jira_ticket['status'],
            'summary': jira_ticket['summary'],
            'slack_discussions': slack_messages
        }
        return response
    
    return {'message': 'Query not understood or not relevant to configured sources.'}

# Example usage
query_from_extension = "What's the status of the API-123 ticket and recent discussions?"
result = handle_user_query(query_from_extension)

print(result)

In this example, the handle_user_query function acts as the central point. It receives a query, identifies relevant keywords (API-123), and then calls the appropriate methods from the integrated clients (like jira_client.get_ticket). The final result is a consolidated, relevant piece of information, which is then sent back to the user's browser via the extension.

<br>