Search for a command to run...
I am a Journalist-turned-Software Engineer. I love coding and the associated grind of learning every day. A firm believer in social learning, I owe my dev career to all the tech content creators I have learned from. This is my contribution back to the community.
No comments yet. Be the first to comment.
Video https://www.youtube.com/watch?v=FgRGwnpd2HY Google's recent white paper on "Agents" has created quite a buzz. The paper explores the concept of AI agents and delves into their architecture and potential. Let's break down what this white paper...
📖 Introduction In modern AI applications, communication between clients and tools isn’t always as simple as calling an API. The Model Context Protocol (MCP) provides a standardized way for clients to exchange information, invoke tools, and maintain ...
If you’re curious about how to build an intelligent agent using Model Context Protocol (MCP), you’re in the right place. In this post, I’ll walk you through how to: Create an MCP Server using FastMCP Expose a tool that calculates BMI Build a Clien...
In our previous tutorial, we built a restaurant customer support chatbot using OpenAI's Agents SDK. In this follow-up, we’ll explore guardrails—a critical feature that enhances AI chatbot safety and reliability. What Are Guardrails in AI Agents? Guar...
Video https://www.youtube.com/watch?v=FgRGwnpd2HY Google's recent white paper on "Agents" has created quite a buzz. The paper explores the concept of AI agents and delves into their architecture and potential. Let's break down what this white paper...
I am Zahiruddin Tavargere (Zahere). A social-learner, here to learn, share and grow with the tech community.
74 posts
I am Zahiruddin Tavargere (Zahere). A firm believer in social learning, I owe my dev career to all the tech content creators I have learned from - this is my contribution back to the community.
Uber's data platform processes approximately 1.2 million interactive queries monthly, with 36% of these coming from the operations organization. This group—comprising engineers, data scientists, and operations professionals—analyzes data from hundreds of thousands of tables across various domains to derive actionable insights.
However, the process of composing and executing queries was a bottleneck:
10 minutes per query: Each actor spent an average of 10 minutes composing a query.
Inefficiency Loop: Users would sift through datasets, run queries, and validate results in a repetitive cycle.
Wasted Time: The cumulative effect of this inefficiency led to significant lost productivity.
This challenge is not unique to Uber. It resonates across industries, from e-commerce to customer support, where operations teams grapple with similar inefficiencies.
In 2023, a team at Uber's hackathon introduced QueryGPT, a prototype designed to streamline the query-generation process. Here's how it worked:
Metadata-Driven Query Generation:
Stored 20 SQL queries with metadata (table and schema information).
Mapped natural language prompts to these queries.
Few-Shot Prompting:
Used a Retrieval-Augmented Generation (RAG) technique to fetch relevant queries.
Generated SQL queries in response to user prompts.
Initial Results:
Reduced query composition time from 10 minutes to 3 minutes.
Achieved an 18% productivity gain.
While this was a promising start, the prototype faced scalability and technical challenges, necessitating further iterations.
Prompt-to-Schema Mismatch:
Token Limitations:
The refined system, powered by Azure OpenAI and GPT-4, demonstrated remarkable efficiency:
Context Optimization: Leveraged a context window of 128k tokens to handle large schemas.
Human Validation: Ensured precision through user acknowledgment of suggested tables.
Scalable Design: Addressed the challenge of querying across hundreds of thousands of datasets.
Uber's engineering team implemented a robust architecture combining SQL, RAG, agents, and custom configurations. Here's a breakdown:
Domain-Specific Curation:
Decomposed datasets into business domains/workflows (e.g., mobility, trips, support).
Allowed the system to focus on smaller, relevant subsets of data.
Intent Agent:
Classified user prompts to map them to the appropriate domain or workspace.
Likely employed a vector-store-based intent classifier for high accuracy.
Table Agent:
Retrieved domain-specific tables and displayed them in a user-friendly interface.
Enabled human-in-the-loop validation to ensure table relevance.
Enhanced RAG Pipeline:
Generated few-shot prompts tailored to the specific domain.
Sent refined prompts to GPT-4 for SQL query generation.
By the 20th iteration, Uber's Query GPT achieved a staggering 140,000 hours saved monthly across its operations organization. This success underscores the value of combining AI, domain-specific curation, and user-centric design.
Uber's solution offers valuable insights for tackling similar challenges in other industries:
Break Down Data Silos:
Implement Intent Detection:
Leverage Human-in-the-Loop Systems:
Iterate for Scalability:
Uber's journey with QueryGPT exemplifies the transformative potential of generative AI in operational analytics. By reducing manual effort and empowering teams with intelligent tools, businesses can unlock unprecedented productivity gains.
Whether you're in e-commerce, customer support, or any data-intensive field, the principles behind Uber's success can guide your own AI-driven innovations.
Want to delve deeper into the technical details? Check out Uber's engineering blog here for the full story.