Manveer Chawla

Anthropic’s new Claude Tag is impressive, but the gap between Claude tag coding and agents actually doing work in your business systems is the action layer. We’re here to help, so we wrote up how to build your own Claude Tag-style agent with Arcade. arcade.dev/blog/claude-ta…

Build Compliant AI Agents With Stateful Stream Processing via @confluentinc, by @manveerc confluent.io/blog/compliant…

@TryArcade just raised $60 million. Getting agents into production requires solving authorization, governance, and reliability all at once. We built the action runtime and today @WSJ covered why this is a big deal. wsj.com/cio-journal/ar…

Two years ago we made a bet that the action layer was going to be the hardest problem in enterprise AI. Today, the @WSJ covered why that bet paid off. Check out the full feature on our Series A announcement: wsj.com/cio-journal/ar…

Integrating AI Into Apache Kafka Architectures: Patterns and Best Practices from @confluentinc, by @manveerc confluent.io/blog/ai-kafka-…

People still say @ClickHouse is append-only. That is an eight-year-old myth. Standard #SQL UPDATE shipped in 2025. Lightweight updates use patch parts, skip table rewrites, and run 1000x faster. I analyzed 100+ merged PRs to prove it. dataanalyticsguide.substack.com/p/clickhouse-u… #database #clickhouse #dataengineering #analytics

"The model is the brain. The harness is the body." I sat down with @robinnewhouse from @cline We got into harness design, model-agnostic agents, and why the bottleneck in coding agents has quietly shifted. 🧵👇

Most AI SRE tools fail because they try to be "autonomous." I am skeptical of that. A model can't remediate production unsupervised, and it shouldn't. The real win is the "Companion" model. The AI does the legwork (triage, timelines, correlation). The human makes the judgment. I broke down 5 #AI #SRE workflows and the #MCP runtime infrastructure needed to make them safe in production on the Arcade blog. The goal: let the on-call start on page 5 instead of page 1. Full post here: arcade.dev/blog/claude-co… #AI #SRE #RELIABILITY #ONCALL #DEVOPS #MCP

2,500x faster than #MongoDB. 10x faster than #Elasticsearch. 9,000x faster than #DuckDB. On 1 billion JSON documents. Single node. #ClickHouse's native JSON type stores each path as a columnar subcolumn with type preservation and primary key support. I traced 80+ PRs across 4 years. The full evolution from String blobs to production-ready columnar JSON. dataanalyticsguide.substack.com/p/clickhouse-n… @ClickHouseDB #JSON #Performance

#ClickHouse JOINs in 2026: 6 algorithms. Cost-based reordering. Parallel hash by default. Runtime bloom filters. Correlated subqueries decorrelated. I audited 50+ PRs from 2022 to 2026. The "avoid JOINs in ClickHouse" advice is 3 years out of date. dataanalyticsguide.substack.com/p/clickhouse-j…

#OpenClaw's promise is great but the security model isn't there. I was already using #ClaudeCode and #WhatsApp constantly, so I built on that instead. Now I can text my assistant "prep me for my 2pm" or "latest for a customer project", seconds later I get a response right in my WhatsApp chat. Full working code: github.com/manveer/whatsa… Tutorial: arcade.dev/blog/secure-op…

WebMCP asks every developer on the internet to build a second interface for AI agents. Meanwhile, server-side MCP already exists and the browser already has the Accessibility Tree. Why are we adding a middleman? manveerc.substack.com/p/webmcp-false… #AI #MCP #WebMCP #LLMs

Building personal agents like @openclaw forces us to rethink how we run AI agents The reality: if you're running untrusted agent logic, a shared kernel is a liability. The blast radius is just too big. Wrote down some thoughts here on different options: open.substack.com/pub/manveerc/p…

AI SREs will fail on missing data before they fail on missing IQ. Most observability stacks aren't built for agentic workflows. They drop the exact high-cardinality dimensions like User IDs or Request IDs that an AI needs to find a root cause. My thoughts on this are up on the @ClickHouseDB blog. clickhouse.com/blog/ai-sre-ob… #AI #SRE #DevOps #observability

The old observability model is broken. Siloed tools can't handle high cardinality data well. We analyzed a unified stack for ClickHouse. clickhouse.com/engineering-re…

@motherduck linkedin.com/posts/ryguyrg_…

@motherduck You don't need to compromise on speed and quality. You can achieve both. Onward! 📈 #AEO #SEO #LLM #Marketing

SEO is changing. Fast. The proof? Check out these insane results from our work with the brilliant team at @MotherDuck 🚀 18.9% lift in share of voice 🚀 3x content velocity Here’s a quick look at how we did it 👇