Richard Seroter

Richard Seroter

Creator
0 followers

Chief Evangelist, Google Cloud; platform engineering, integration, app modernization

Build Memory-Enabled Agents with Vertex AI and AlloyDB
SocialFeb 26, 2026

Build Memory-Enabled Agents with Vertex AI and AlloyDB

Agents with memory. It's a thing. An important thing. @AbiS_Google has a good post that shows how to build an ADK agent that uses @googlecloud Vertex AI Memory Bank and AlloyDB. https://t.co/eyYWcvNhXd https://t.co/COQKoOqVHp

By Richard Seroter
Confluent Adds MCP and A2A Support to Its Platform
SocialFeb 26, 2026

Confluent Adds MCP and A2A Support to Its Platform

Agent standards like MCP and A2A are starting to show up in more types of packaged software. @confluentinc just shipped updates to their data products, including their "intelligence" platform that now supports A2A and MCP integrations. https://t.co/n8teMonFMW https://t.co/1f7afnSw8K

By Richard Seroter
Databases Lose Standalone Status, Remain Core Infrastructure
SocialFeb 25, 2026

Databases Lose Standalone Status, Remain Core Infrastructure

"Databases are architecturally being subsumed. They’re being disintermediated as standalone products, even as they remain essential as components." https://t.co/VMnocvGVjl < some smart analysis from @rstephensme of @redmonk. Databases matter a ton, but the space is changing.

By Richard Seroter
Choose: AI-Driven Pipelines or Human-Controlled CI/CD
SocialFeb 25, 2026

Choose: AI-Driven Pipelines or Human-Controlled CI/CD

AI forces us to rethink CI/CD. This post outlines the situation, and says you should either be all-in on agentic workflows (and accept weird edge cases), or stick with human-centered determinism (and accept the slowness). But don't live in the middle. https://t.co/k7UkeG9CSD

By Richard Seroter
Strong CI Fundamentals, Not Special AI Pipelines, Ensure Quality
SocialFeb 24, 2026

Strong CI Fundamentals, Not Special AI Pipelines, Ensure Quality

How Do I Enforce Quality Checks on AI-Generated Code in CI/CD? https://t.co/IyaTDNp0Ql < money quote: "The good news: you don’t need a special AI pipeline. You need strong CI fundamentals."

By Richard Seroter
One-Line Code Swap Moves Cassandra to Spanner, Auto-Embeds in BigQuery
SocialFeb 24, 2026

One-Line Code Swap Moves Cassandra to Spanner, Auto-Embeds in BigQuery

Simple is good. One-line code change to switch from Apache Cassandra to a @googlecloud Spanner database. https://t.co/2n6AJutoNM Generate embeddings automatically for @googlecloud BigQuery table. https://t.co/SqIQzawOvt https://t.co/zWknasRT6r

By Richard Seroter
Scaling Config Security, Mapping AI, Token‑Efficient Frameworks
SocialFeb 24, 2026

Scaling Config Security, Mapping AI, Token‑Efficient Frameworks

Seroter Daily Reading List – February 23, 2026 (#727): Today’s links look at how to safeguard dynamic config changes at scale, how to teach AI to read a map, and which web frameworks are the most token-efficient for AI agents. https://t.co/qg47lXCkK1

By Richard Seroter
WebMCP Offers Reliable Function Calls Over Screen‑Scraping
SocialFeb 23, 2026

WebMCP Offers Reliable Function Calls Over Screen‑Scraping

"Web Model Context Protocol (WebMCP) replaces the fragile screen-scraping and simulated clicks, with reliable function calls." https://t.co/MExI9Y9Fng < I suspect that this new @googlechrome feature is going to be a BIG deal this year and a less-brittle option than Computer...

By Richard Seroter
Airbnb's Scalable Dynamic Config Prevents Outage Chaos
SocialFeb 23, 2026

Airbnb's Scalable Dynamic Config Prevents Outage Chaos

Config changes SHOULD be super boring, but we all see those public outages caused by misconfiguration. Here's a look at how Airbnb does dynamic config changes at scale ... https://t.co/S6jjDs54uv https://t.co/Xzvix5lw5G

By Richard Seroter
14 Google Lessons, Delivery Trends, and Component Shrinkage
SocialFeb 20, 2026

14 Google Lessons, Delivery Trends, and Component Shrinkage

Seroter Daily Reading List – February 20, 2026 (#726): Today’s links look at 14 lessons from 14 years at Google, takeaways from a new “state of software delivery” report, and how one company reduced the size of their software component. https://t.co/BG7Xbu8k54

By Richard Seroter
Trim the Fat: Removing Legacy Code Shrinks Software
SocialFeb 20, 2026

Trim the Fat: Removing Legacy Code Shrinks Software

It's not hard for software to get bloated over time. @datadoghq has a nice post about how they made an intentional effort to strip out old dependencies, dead code, and other things that made their agent too hefty. https://t.co/5OMhL4t5lr https://t.co/yXpAj3OH8w

By Richard Seroter
Expose All Product Surfaces to Empower Agentic Users
SocialFeb 19, 2026

Expose All Product Surfaces to Empower Agentic Users

How well are you surfacing your product experiences to agents? Enjoying this Bengaluru Builder Day talk from @Swiggy's CTO that's looking at making all their surfaces available to agentic users. https://t.co/o6lDaMS5wd

By Richard Seroter
Analyze Global Data with One BigQuery Query
SocialFeb 18, 2026

Analyze Global Data with One BigQuery Query

You've got data spread across geographies. What happens when you want to bring that data together? Usually ETL jobs or other mechanisms. We just launched @googlecloud BigQuery global queries. Do multi-location analysis with a single query: https://t.co/F3p2mn5SjZ

By Richard Seroter
AI Agent Automates VM Management with Guardrails
SocialFeb 16, 2026

AI Agent Automates VM Management with Guardrails

An AI agent that can proactively stop, resize, and restart your virtual machines? You'd want guardrails in place, but the use case matters. This post shows off a complete @GoogleCloudTech reference architecture ... https://t.co/gy9WePAHSO https://t.co/FKqdPutzUc

By Richard Seroter