engblogs

MIT's Stone Center on Inequality and Shaping the Future of Work launches to explore how technology, economics, and democratic governance intersect to reduce labor-market and wealth inequality while advancing pro-worker AI through policy design and innovative governance models.

Technical overview of ChatGPT Health, covering architecture, integration patterns, and privacy- and security-focused considerations for healthcare applications.

A technical exploration of how Tolan builds a voice-first AI with GPT-5.1.

A practical, hands-on guide to building AI-powered data analytics agents faster by using Google BigQuery’s fully managed, remote MCP server, with ADK integration, OAuth-based setup, and Gemini tooling for secure access to enterprise data.

Explores why Spotify separates personalization ML and experimentation tooling to build scalable, low-latency recommendations using contextual bandits and RL-powered models across teams.

Zero-downtime migration of Marketing Cloud caching from Memcached to Redis Cluster at 1.5M RPS across 50+ applications, preserving millisecond latency and enabling proactive hot-key management.

Gemini CLI now ships with pre-configured Google Cloud Monitoring dashboards and OpenTelemetry-powered telemetry, delivering out-of-the-box visibility into usage, performance, and logs with minimal setup.

Scaling from a single Engagement Agent MVP to a dispatcher-driven, enterprise-scale multi-agent platform that delivers high-throughput, fair, and observable AI-powered outreach at scale.

Comprehensive analysis of a Venezuela BGP route-leak involving AS8048 (CANTV), examining probable routing-policy misconfigurations and highlighting ASPA and RFC9234 as paths toward a safer, more verifiable BGP ecosystem.

NarrativeTrack introduces a benchmark for evaluating temporally grounded narrative understanding in multimodal language models, using entity-centric reasoning and a Compositional Reasoning Progression framework that scales from entity existence to changes and ambiguity.

A designer-aligned pipeline for improving UI generation models that leverages feedback via commenting, sketching, and direct manipulation to finetune LLMs with multimodal data and human evaluations, outperforming traditional RLHF baselines.

Introducing the Instructed Retriever, a system-aware retrieval architecture that propagates system specifications (user instructions, labeled examples, and index schema) through query generation and retrieval to enable robust instruction-following, low-latency enterprise agent search.