[Music] I'm Paul Rasgitis and I'm the tech lead for AI products at Modern Treasury. Modern Treasury is the payment operations platform built for the instant economy. At Modern Treasury, our goal is to transform how teams track and move money.Recently, we launched Modern Treasury AI, a horizontal platform that includes chat, task management, monitoring, and an AI agent designed specifically for financial operations. The agent is just one part of this broader experience, but it plays a key role in how users i ...

Agentic Platform Engineering Implementation - Outshift by Cisco is redefining platform engineering with agentic platform engineering, aiming to automate workflows and allow platform engineers to focus on high-value work [1][2] - The company built Jarvis, a genai-powered multi-agentic system, to automate tasks and improve efficiency [2] - Langraph, combined with Langsmith's observability tools, enables debugging agentic applications and improving reasoning capabilities at scale [6] Efficiency Improvement - Implementing Jarvis allows developers to self-service through genai-powered automation, eliminating manual toil [4] - CI/CD pipeline setup time reduced from a week to less than an hour [7] - Resource provisioning time (e.g., S3 buckets, EC2 instances, access keys) reduced from half a day to nearly instantaneous [7] - The company has eliminated unnecessary back and forth between developers and SREs [7] Workflow Transformation - The company shifted from traditional automation to agentic reasoning-based workflows by adopting Langraph [5] - Developers interact with Jarvis for platform-related questions and configurations, retrieving information autonomously [8] - The new system allows the company to handle a higher volume of requests with the same team while reducing burnout [8] Technology Evaluation - Langraph's tight integration with Langsmith, especially for debugging and evaluations, is a significant advantage [9] - The company found Langraph to be superior compared to other agentic solutions or custom-built alternatives [9]

Company Overview - Box is a B2B company operating as an unstructured data platform, serving large enterprises including Fortune 500 companies [1][2] - Box has over 115,000 companies as customers, tens of millions of users, and manages over 1 exabyte of data [2] - Box is often the first AI deployed within large enterprises due to existing trust relationships [3] Data Extraction Evolution - Box initially used a straightforward architecture for data extraction involving pre-processing, OCR, and large language models [8] - The initial AI deployment processed 10 million pages, but encountered challenges with complex documents, OCR accuracy, language variations, and the need for confidence scores [9][10][11] - The company experienced a "trough of disillusionment" as the initial AI solution proved insufficient for diverse customer needs [12] Agentic Approach Implementation - Box re-architected its data extraction process using a multi-agent approach, separating problems into sub-agents [12] - The agentic system intelligently groups related fields, dynamically determines data extraction methods, and incorporates a quality feedback loop for continuous improvement [13] - This approach allows for easier updates and specialization, enabling the company to quickly adapt to new document types and customer requirements [13] Engineering and Customer Impact - Building agentic systems helps engineers think about AI and agentic workflows, leading to better understanding of customer needs [13] - This approach facilitates the development of tools that integrate with customer-built agents, enhancing the overall ecosystem [13] - The company advises building agentic systems early when developing intelligent features [14]

AI Developer Tool Strategy at Uber - Uber's AI developer tool strategy focuses on products that directly improve developer workflow, such as writing tests and reviewing code [6] - The strategy emphasizes building crosscutting primitives, foundational AI technologies applicable across multiple solutions [7] - Intentional tech transfer is a cornerstone, identifying and spinning out reusable components to reduce barriers for future problem-solving [8][9] Key Products and Their Impact - Validator, an IDE experience, flags best practices violations and security issues, resulting in thousands of fixed interactions daily [11][16] - Autocover, a test generation tool, leverages domain expert agents and has increased developer platform coverage by approximately 10%, saving an estimated 21,000 developer hours [17][27][28] - Uber has built an internal custom GPT store where you can build chatbots that are steeped in Uber knowledge [29] Technical Learnings - Building super capable domain expert agents yields outsized results due to better context utilization and reduced hallucination [34] - Composing agents with deterministic sub-agents, like the lint agent in Validator, ensures reliable output [36] - Scaling development efforts is achieved by creating and reusing agents across multiple applications, such as the build system agent [37] Strategic Learnings - Encapsulation through well-defined abstractions like Langraph boosts collaboration and allows for horizontal scaling of development [39] - Graphs model interactions effectively, mirroring developer workflows and improving both AI and non-AI experiences [41]