Johann SchleierSmith

Keep your AI agents running through process crashes and network drops. This tutorial shows you how to build a ReAct-style loop with the Gemini API and Temporal. Temporal persists every step so your agent resumes exactly where it left off. Learn more → goo.gle/4rvf0Wr

I'm claiming my AI agent "jssys01t" on @moltbook 🦞 Verification: burrow-P9LZ

I'm claiming my AI agent "jssysoc" on @moltbook 🦞 Verification: wave-7F5B

I'm claiming my AI agent "jsski" on @moltbook 🦞 Verification: coast-K3EL

Progress was already exponential before we had agents creating other agents. What's next?

Big News! Crystal DBA has been acquired by Temporal Technologies . Read more: crystaldba.ai/blog/post/temp… @temporalio @auto_dba

We've been building the pieces for years. Projects, AI Agents, Automations. Today, the dots connect. Introducing 🧬 Taskade Genesis Preview • One prompt → a full-stack AI app • Powered by your Workspace • Supercharged with GPT-5 Reply `Genesis` for early access 🚀

We’re excited to introduce RunLLM v2 today! 🎉 RunLLM v2 is rebuild of the product from the ground up focused on delivering the most powerful and flexible platform for enterprise support teams. Read the RunLLM v2 launch blog post: 👉 tinyurl.com/49st5ns2 Today’s launch includes: 🤖 A new agentic planner with fine-grained reasoning and tool use support ✨ A redesigned new UI that enables creating, managing, and inspecting multiple agents ⚙️ A Python SDK that allows you to exercise fine-grained control over support workflows We’ll be sharing more throughout the week, but today we’re focused on how RunLLM’s new agentic capabilities enable more precise answers and more effective debugging.

@auren Good point on LP transparency

Any VC that makes you pay for their lawyers is not founder-friendly. Founders barely affording rent should not be footing legal bills for VCs with private jets. And yet this is standard. a thread 🧵

@rajivayyangar SF/Bay Area is spoiled with interesting advertising. Other places billboards are often dominated by personal injury attorneys.

Most companies are bad at billboards. I see a lot IRL (in SF) and virtually (on Product Hunt). Here's my analysis and grading for 5 examples. 👇

Finding "top slow db queries" seems like a simple question, until you ask AI to answer it: dev.to/jssmith/what-c… #postgres #MCP #Database #sql

Confused about the new US tariffs 🤔🇺🇸? I built an interactive US Tariff Calculator — a simple tool to help you instantly calculate the new tariffs per country. Check it out here: tariffs.inasimonovska.com

Yesterday's re:Invent highlights in data and systems include a Aurora DSQL, a new distributed SQL database, new features in S3 that make it work like a database, and SageMaker evolving to unified platform for delivering value from data. linkedin.com/pulse/data-sys… via @LinkedIn

Keeping up the flood of AWS #reinvent announcements is always a challenge. This week I’ll be posting updates to save you time and keep you in the know about data systems. linkedin.com/pulse/data-sys…

The team at Zypsy is a group of true pros who really get early stage tech.

@reneeshah123 You can think of disaggregated memory as the next phase of scale up. It's a win for big workloads that don't naturally scale out.

This paper from 2022 was compelling. Right now, databases are separating storage and compute. In the future, databases may separate memory and compute: arxiv.org/pdf/2207.03027

@criccomini @OtterTuneAI We are fans of @OtterTuneAI . CrystalDB integrates a database service and focuses on Postgres only. We should dig in on technical differences—vision and inspiration is shared.

@jssmith Congrats! How do you compare this with @OtterTuneAI?

CrystalDB has been stealthy for a long time. No Longer! I'm really proud of our team for getting us to this point. 'Looking forward to your feedback and comments.

The HPTS 2024 submissions are now open. If you want to participate at the objectively best systems gathering of database systems architects, practitioners and academics (highly highly recommended!), please indicate it by submitting something at: hpts.ws #hpts

@vincentchu Yes. You probably want to run any cross-org analytics on logs that are stored elsewhere. That requires some upfront design but probably encourages good hygiene around security/privacy.

@jssmith I’ve been thinking about this too- less so for single users, but to segregate DBs for whole groups of users for SaaS apps that don’t aren’t that big. One potential issue/question is that it seems harder to run analytics, etc across many atomized sqllite instances.

Watch this space… multi-tenancy remains a huge pain point. It’s most visible at the database.