Engineering posts about Generative AI
Curated summaries and key learnings for engineers working with Generative AI.
Accelerating LLM Inference with Prompt Caching for Open‑Source Models on Databricks
The article outlines the significance of prompt caching in accelerating inference for large language models (LLMs) on Databricks. It explains how repeated prompts can lead to inefficiencies in...
Introducing Nova, our internal platform for coding agents
The article introduces Nova, an internal platform developed by Dropbox to enhance the efficiency of coding agents in software development. It outlines how Nova integrates AI to assist engineers in...
How We Built DigitalOcean Inference Router
This article details the development and functionality of DigitalOcean's Inference Router, a system designed to optimize AI model selection based on specific task requirements. It highlights the...
How to safeguard AI workloads with Unity AI Gateway Guardrails
The article outlines the importance of implementing guardrails in AI applications to protect sensitive information and ensure compliance with security standards. It details how Unity AI Gateway...
How Databricks Genie improves supply chain visibility with real-time AI analytics
The article outlines how Databricks Genie addresses the challenges of supply chain visibility by leveraging real-time AI analytics to synthesize data from various sources. Traditional supply chain...
Blazing fast on-device GenAI with LiteRT-LM
The article provides an in-depth exploration of LiteRT-LM, an advanced framework for deploying the Gemma 4 model across various platforms, including Android, iOS, and web environments. It highlights...
One Year of Innovation: Celebrating 100k Members in the Google Cloud x NVIDIA Developer Community
The article celebrates the one-year anniversary of the Google Cloud and NVIDIA developer community, highlighting its growth to 100,000 members. It emphasizes the importance of bridging AI...
Google Tensor SDK Beta with LiteRT
The Google Tensor ML SDK has transitioned from an Experimental Access Program to Beta, enabling developers to leverage the capabilities of the Google Tensor System-on-Chip (SoC) and its dedicated...
The JavaScript AI Build-a-thon Season 2 starts today!
The JavaScript AI Build-a-thon is a comprehensive program aimed at bridging the gap in AI development for JavaScript and TypeScript developers. Spanning four weeks, the event includes self-paced...
Securing MCP: A Control Plane for Agent Tool Execution
The Model Context Protocol (MCP) is emerging as a standard for AI agents to access tools, but it lacks governance mechanisms to ensure secure execution. This article outlines the risks associated...
LangChain.js for Beginners: A Free Course to Build Agentic AI Apps with JavaScript
The article introduces 'LangChain.js for Beginners', a free course designed to help JavaScript developers build AI agents that can reason, call tools, and utilize knowledge bases. The course consists...
Amazon Bedrock introduces new advanced prompt optimization and migration tool
Amazon Bedrock has introduced an advanced prompt optimization tool that allows users to enhance their prompts for various models simultaneously. This tool facilitates migration to new models or...
The Rosetta stone of CPS: Claroty’s AI-powered library
The article presents Claroty's AI-Powered CPS Library, a groundbreaking solution designed to address the identity crisis in Cyber-Physical Systems (CPS). It highlights the challenges faced by...
What the design-to-code loop unlocks
The article explores the evolving relationship between design and code facilitated by AI technologies, particularly within the Figma platform. It emphasizes how AI is transforming traditional...
Build Long-running AI agents that pause, resume, and never lose context with ADK
This article presents a comprehensive guide to building long-running AI agents that can pause, resume, and maintain context using the Agent Development Kit (ADK). It highlights the limitations of...
Pushing the Frontier for Data Agents with Genie
The article presents Genie, a sophisticated data agent developed by Databricks, designed to enhance the analysis of both structured and unstructured enterprise data. It highlights the challenges...
MCP Marketplace Brings Real-Time Intelligence to Agentic Applications
The MCP Marketplace serves as a pivotal platform for integrating real-time intelligence into agentic applications, allowing them to leverage external data sources to enhance decision-making...
Using MemAlign to Improve Evaluation of Traditional Machine Learning in Genie Code
The article explores the implementation of MemAlign, an open-source alignment framework within MLflow, designed to enhance the evaluation of traditional machine learning (ML) notebooks generated by...
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
The article introduces Text-Conditional JEPA (TC-JEPA), a new framework for learning semantically rich visual representations by leveraging image captions to modulate predicted features. This...
What Matters in Practical Learned Image Compression
The article presents a comprehensive study on learned image compression codecs, emphasizing their optimization for the human visual system. It highlights the development of a new codec that...