This content originally appeared on DEV Community and was authored by Nikunj Rohit
This is a submission for the Runner H “AI Agent Prompting” Challenge
What I Built
I built two distinct AI agent workflows using Runner H, showcasing its versatility in addressing different real-world problems:
1. SDE2 Preparation Resource Aggregator: This agent is designed to assist aspiring Software Development Engineers (SDE2s) by curating relevant preparation resources. The goal is to streamline the often overwhelming process of finding study materials for Data Structures and Algorithms (DSA), System Design (High-Level Design and Low-Level Design), and behavioral interview preparation. It aims to save users significant time and effort in gathering scattered information.
2. Local Farmer Advisory System: This agent focuses on providing targeted and timely advice to local farmers. It addresses the need for accessible agricultural information, potentially offering guidance on topics like crop planning, pest control, weather monitoring, and market prices. This system aims to empower farmers with data-driven insights to improve their practices and yields.
Demo
For the SDE2 preparation resource, you can show the agent being prompted, then demonstrating how it navigates various websites (e.g., LeetCode, GeeksforGeeks, System Design interview resources) to extract and organize information relevant to SDE2 interview topics.
For the local farmer advisory system, you can demonstrate the agent receiving a query (e.g., “What’s the best fertilizer for cotton in this region given current weather?”) and then showing how it accesses agricultural databases, weather forecasts, and potentially local farming guidelines to generate a tailored response.
Here are the share links you provided, which can be linked in your demo section:
- .
- .
How I Used Runner H
Runner H’s autonomous agent capabilities were instrumental in building these workflows. For the SDE2 Preparation Resource Aggregator, I leveraged Runner H’s ability to:
Navigate diverse web pages: The agent was prompted to visit and extract information from multiple technical interview preparation websites (e.g., those specializing in DSA, System Design, and behavioral questions).
Identify and categorize information: I designed prompts that guided Runner H to understand the different sections of SDE2 preparation (e.g., Data Structures, Algorithms, High-Level Design, Low-Level Design, Behavioral) and to extract relevant links, topics, and study tips.
Consolidate data: The agent was configured to pull information from various sources and present it in a structured and easy-to-digest format, effectively creating a personalized study guide.
For the Local Farmer Advisory System, Runner H’s power was utilized to:
Access real-time data: The agent was set up to query agricultural databases, government advisory services (like eNAM or IMD’s Agromet Advisory Services in India), and potentially local weather APIs.
Process natural language queries: Farmers can ask questions in a natural, conversational style, and Runner H interprets these queries to fetch the most relevant information.
Generate tailored advice: Based on the farmer’s specific query and the gathered data, Runner H synthesizes actionable advice, potentially including optimal planting times, pest management strategies, or market price trends.
Handle varying information formats: The agent can parse information from different sources, including structured data, text, and potentially reports or advisories.
The “no coding skills” aspect of the challenge was fully embraced, as the development of these agents relied purely on creative and effective prompting of Runner H.
Use Case & Impact
The SDE2 Preparation Resource Aggregator has a significant impact on individuals preparing for technical interviews. It:
Reduces information overload: Instead of manually searching through countless websites and forums, candidates can get a consolidated, relevant list of resources.
Saves time: By automating the resource gathering, it frees up valuable time for actual studying and practice.
Provides a structured approach: It helps candidates follow a more organized preparation roadmap, covering all essential areas for an SDE2 role.This would benefit anyone aiming for software engineering roles, particularly those targeting product-based companies with rigorous interview processes.
The Local Farmer Advisory System revolutionizes agricultural practices, especially in regions like India where access to timely and accurate information can be crucial. Its impact includes:
Improved decision-making: Farmers can make more informed choices regarding crop cycles, resource allocation, and pest/disease management, leading to better yields.
Increased efficiency: Timely advisories can help prevent losses due to adverse weather or pest outbreaks.
Empowerment of farmers: By providing easy access to expert knowledge, it bridges the information gap and supports sustainable farming practices.This system would greatly benefit small and medium-scale farmers, agricultural cooperatives, and even agricultural extension workers.
Social Love
My Twitter account for social sharing is: nikunj_rohit10
This content originally appeared on DEV Community and was authored by Nikunj Rohit