Sumanth Puram

Starting to roll out today: Claude Whiteboards, Claude Sheets and Claude Data. Think a plan through on a board, build a tracker in a sheet, and tell a story with your data.

$SNOW continues to lose market share, and it's not just Databricks they need to worry about. While the entire market is growing based on hiring demand, the number of companies mentioning $MSFT Fabric jumped the most at +165%. Databricks grew +40%, while both $SNOW and $GOOG BigQuery increased the least at +15% from a year ago.

We just shipped a change to our JavaScript SDK. It now pins the vendor scripts it loads for device mode to exact versions and checks them with SRI hashes, with a strict mode that skips any it can't pin. Here's why and how.

Postgres 19’s release is being delayed as maintainers fix existing bugs and address security issues that AI helped uncover. AI can churn out slop quickly, but it can also make complex software more robust. Ultimately, it comes down to how you choose to spend your tokens

Introducing /REA-growth skill Reverse-engineer any company's growth - Name any company, get its growth blueprint - Every move on its timeline: SEO, AEO, ads, social - $0.58 for a full Lovable teardown - Fully OpenSource Try it at treg.to/rea-growth Partnered with @sharenow_today Repo link below 👇

Today we open sourced DevBox under MIT license. About 35% of our internal PRs are merged by DevBox now. You can run it on your own machine or run it in your cloud. Works natively with @linear and @github github.com/rudderlabs/devbox

The gap isn't only between startups and incumbents. With the companies I've talked to: engineering went AI-native, GTM still runs on 3-4 week loops. Our next goal, build AI GTM harness that make our own marketing experiment loops take half a day.

Day 9 of building DevBox, our internal coding agent. The biggest jump in quality didn’t come from a better model. It came from fixing how the agent reviews its own work. DevBox already reviewed its diff before opening a PR. But humans were still catching bugs it should have caught. So we looked at the traces. The reviewer ran for about 2 minutes, never executed any code, and came back with a short list of opinions. And the fixer was quietly rejecting medium-severity findings by default, even when the planner had flagged the same risk at the start. We did try a model upgrade. It caused session errors and we rolled it back. That made it pretty clear the problem was the workflow. So we rebuilt review. Each reviewer is now a separate agent that never sees the implementer’s reasoning. It only gets the task, the plan and the diff. The implementer already believes its code is right, so you want a reviewer who wasn’t in the room. The harness runs reviewers in parallel. A general code review always runs. The planner adds others depending on the change: a bug hunter that traces risky paths to an actual failure, a bird’s-eye reviewer that looks at callers, dependencies and the end goal, plus security and code quality. A config tweak gets one reviewer. An auth change might get security and the bug hunter too. Reviewers get a scratch space where they can run tests and repro scripts. If they say something is broken, they have to show it. A merge agent then dedupes the findings (same root cause, worded differently by different reviewers) and writes one report. Some rules live in code, not in a model. Critical/high findings without evidence get downgraded, there’s a cap of 8 findings per repo, and the harness decides the final verdict. Then a fresh fixer agent, with the implementer’s design notes, goes through each finding and either fixes it or writes down why not. The loop has a limit, and anything left over goes into the PR description so the human reviewer sees it. Our takeaway: when agent quality is bad, look at the process before you swap the model. A smarter model doing a 2-minute review without running anything is still a 2-minute review without running anything. Tomorrow, the last one: how we measure all of this.

Day 7 of building DevBox, our internal coding agent. We started on Codex CLI. Over the summer we moved stage after stage to Deep Agents. Here's why, and what it taught us about who should own orchestration. Codex CLI got us to a working product fast. It's a great coding agent. But we were driving it as a subprocess, and as the workflow grew we kept losing control of three things: what it read, which session it resumed, and whether each step actually ran. Examples: • Resume "last session" could pick a sub-agent's session when several shared a folder • Prompt updates weren't picked up on resumed rounds • An OOM-killed child process left the pod in an error state we kept polling We patched around them: resume by marker instead of "last", reinstall the system prompt on resume, detect dead pods. Each fix worked, but we were building an orchestrator out of workarounds around someone else's CLI. So we flipped it: Python owns orchestration, the model only does reasoning. With Deep Agents (LangGraph underneath), each repo gets its own in-process agent with its own context, checkpointed to SQLite, so it resumes exactly where it stopped. What moved from prompts into code: • Which files and skills each agent starts with • Retry and backoff, including rate limits with jitter so parallel workers don't retry in lockstep • Schemas for every handoff, enforced with structured output It wasn't a big-bang migration. Each piece shipped behind an experimental flag we could turn on per task: implementation first, then distillation and review. Old and new ran side by side until the new path won. One win, previously Codex agents would often ignore the instructions to start per repo subagents unless reasoning was set to high. This decision now moved to Python orchestration. Deepagent planner reports which repos are involved, harness owns starting implementation agents. Consistent behavior without unnessary reasoning tokens. Lesson: let the model reason and let code orchestrate. Every time we asked a model to "remember to do X next", it eventually didn't. Every time we moved X into code, it stopped being a problem. Tomorrow: proving the change actually works.

Day 4 of building DevBox, our internal coding agent. This is an important one. We assumed the agent will eventually be prompt-injected. What can it do then? It reads tickets, PR comments, docs and web search results, any of which could carry instructions. And it runs arbitrary code as root inside its sandbox. So the question is "what can it reach". Our rule: no real secret ever enters the sandbox. All egress goes through a proxy. Inside the sandbox, the GitHub token, model API key and search key are literally dummy strings. The proxy swaps in real credentials on the way out. Thanks to the team behind iron proxy (@mslipper). Even git works this way. Bootstrap rewrites every GitHub URL to HTTPS and adds a header with a dummy token. The proxy replaces it with a short-lived GitHub App token. A compromised agent can dump its whole environment and find nothing useful. Same for web search: the agent calls a credential-free MCP URL and the proxy injects the API key. We also allowlist which search tools the agent can use. We found out the hard way that a typo in the tool names silently allowed everything.

Over the last 6 months, we built DevBox, an internal coding agent at RudderStack. Delegate a Linear ticket to it and it plans, writes the code, runs tests, reviews its own work and opens a draft PR. Over the next weeks I'll share how we built it, one problem at a time 🧵 1/10

The future is verification-engineering. Proofs, (e2e) tests, benchmarks, linters… Some tests will be deterministic, some agentic. This looks great.

Today we share some exciting news: RudderStack raised a $21 million series A led by @kleinerperkins, and we’re announcing RSDX, the first #CDP for developers. Find out what makes RSDX a CDP for developers 👉 bit.ly/3zeLlH3 We're just getting started 🚀 #Customerdata