engblogs

Explores how to architect, evaluate, and govern production-grade AI agents on Databricks MLflow (with LangGraph) to ensure responsible, calibrated performance in telecom use cases through guardrails, monitoring, and guideline-driven evaluation.

An end-to-end guide to building, testing, and deploying a Gemini 3 app on Google Cloud Run using Google AI Studio's Build mode, turning ideas into a shareable URL with API access.

A concise exploration of scaling PostgreSQL to support 800 million ChatGPT users, focusing on performance, reliability, and operational scalability.

How Agentforce 360 unifies Salesforce’s data, agent, and applications into a single real-time, AI-driven platform powering enterprise experiences across service, sales, and marketing.

Gemini CLI and Gemini 3 empower Google SREs to orchestrate AI-assisted, human-in-the-loop outage response—from paging to postmortem—dramatically shortening Mean Time to Mitigation.

Scaling WideEP MoE inference on Google Cloud's A4X (GB200 NVL72) with NVIDIA Dynamo to deliver rack-scale, disaggregated MoE serving that balances throughput and latency via GPUDirect RDMA, KV caching, and GKE orchestration.

Fastweb + Vodafone reimagined data workflows by deploying a connected Google Cloud stack with Spanner, BigQuery and Gemini to deliver real-time customer insights, enhanced governance, and AI-assisted engineering workflows across a unified Customer 360 platform.

Explores AlloyDB's integrated managed connection pooling, how it works, its Transaction and Session modes, and the resulting gains in scalability, latency, reliability, and operational simplicity for PostgreSQL workloads.

CLICKFORCE leverages Amazon Bedrock Agents, SageMaker AI, OpenSearch, and AWS Glue to power Lumos—an AI-driven, data-grounded advertising analysis platform that transforms weeks of manual work into an automated, hour-long workflow.

A serverless, AWS-based Retrieval Augmented Generation (RAG) platform that ingests diverse data sources, creates vector embeddings, and delivers secure, enterprise AI knowledge answers.

Recap of Google's Agent Factory exploring Antigravity and Nano Banana Pro to build AI agents that orchestrate ADK tools via a Model Context Protocol (MCP) server, using Always Review mode for planning, testing, and generating high-fidelity media.

A technical overview of Spotify's 2025 FOSS Fund recipients—FFmpeg, Mock Service Worker (MSW), and Xiph.org—highlighting how open-source streaming infrastructure benefits from volunteer-led development and targeted funding to sustain multimedia technologies.