Johann Schleier-Smith

AI @ @temporalio

[Johann Schleier-Smith @jssmith]

@MichaelWel65481 @smehmood Are you using https://t.co/hvqMm9tITR ?

[Alexandr Wang @alexandr_wang]

i forgot about this until @ScottWu46 reminded me, but back in january 2017 when we were 19, scott and i had lunch in SF

at lunch, we talked about how our IMO/IOI/math competition gang could be the next paypal mafia. i knew the competition kids were geniuses by any standard, and felt confident in time we could take the tech world by storm

fast forward nearly 10 years later, and many of our friends from that time are some of the most exciting people in AI and technology (@ScottWu46, @akshat_b, @chameleon_jeff, Jerry Ma, @randomjohnnyh, @0xShitTrader, @stevenkplus1, @thejessezhang, @vickie_ye_, @alexwei_, @demi_guo_, @d_m_ziegler, @hughbzhang, @_mohansolo, @MarkSellke, and many others i'm sure i'm forgetting)

i'm now at that age where i reminisce about everyone i grew up with, and i've known most of these people since middle school (via MATHCOUNTS!). even though we were scattered around the country, we would gchat about math problems and hang out on AoPS, then we did math/algo camps together, and then we did internships together.

very crazy to think about the degree of sheer brilliance of this group when we were just teenagers, and so special to see so many go on to leave their mark on the world.

note to parents: if your kid is on gchat all day solving math problems with some anonymous group of cross-country asian kids, (s)he may just turn out alright.

[Johann Schleier-Smith @jssmith]

Big milestone for Temporal's AI Ecosystem

[Temporal @temporalio]

Friday in October’s Product Edition: AI Framework Integrations.

New framework. Same reliable execution.

Temporal’s AI integrations are now generally available. Build agents with Google ADK, OpenAI Agents SDK, AWS Strands, LangGraph, and more—without rebuilding how they recover from failures and resume their work.

Explore the final October Product Edition story: https://t.co/OVWFLXbqEe

[Temporal @temporalio]

Friday in October’s Product Edition: AI Framework Integrations.

New framework. Same reliable execution.

Temporal’s AI integrations are now generally available. Build agents with Google ADK, OpenAI Agents SDK, AWS Strands, LangGraph, and more—without rebuilding how they recover from failures and resume their work.

Explore the final October Product Edition story: https://t.co/OVWFLXbqEe

[Temporal @temporalio]

Tuesday in October’s Product Edition: Temporal Proxy.
Every new app needs to protect sensitive data. It shouldn’t need a new encryption library.

Temporal Proxy centralizes payload encryption with your keys, before data reaches Temporal Cloud.

Meet Temporal Proxy in today’s October Product Edition story: https://t.co/neV3bHavZk

[ClaudeDevs @ClaudeDevs]

We’re adding support for MCP Tasks and Elicitations in Claude.

Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.

[Marc Brooker @MarcJBrooker]

Did you know that even one lying fsync() on just one node can make a distributed Raft cluster lose data?

[Jason Steving @JasonSteving]

Had a great time giving some live demos of the Temporal Agent Harness on @temporalio's Vibe Check livestream - thanks for having me @nyghtowl!

https://t.co/IP8b0kIRAU

[Andy Pavlo (@andypavlo.bsky.social) @andy_pavlo]

The 4th round of SIGMOD 2027 has *659* submissions. This is 2-3x more than previous years!
I downloaded the abstracts & compared against last 10yrs of SIGMOD/VLDB papers. I then evaluated them to see how writing changed since ChatGPT in 2022. Many papers are clearly LLM written.

[Jason Steving @JasonSteving]

The one Temporal Agent Harness explainer to rule them all

[Jaana Dogan ヤナ ドガン @rakyll]

🥳 Google is donating Agent Substrate to CNCF, and our submissions is accepted today! This effort has now the full potential to become the underlying compute runtime layer for all agentic systems. https://t.co/tE1bhdVryl

[Johann Schleier-Smith @jssmith]

Preview of WIP at Temporal. Agent Harness is in a different category from coding harnesses like Pi, Codex, or Claude Code. It’s an outer harness providing durability and policy. It mediates how your agents interacts with the world and with one another. Please give feedback!

[Temporal @temporalio]

See a durable AI agent run end to end on the Temporal Agent Harness 👇

https://t.co/IyHzaJjdzv

[Johann Schleier-Smith @jssmith]

Network effects 💪

[Andy Jassy @ajassy]

A painful part of working with your data has always been that your live data and historical data are stuck in separate systems: the order a customer just placed lives in your database, while their last five years of orders sit in a data lake in S3.

And answering a real question usually needs both at once (is this a normal purchase for them, or should we flag it?), and to do that you had to move the data together first, copying history out of the data lake into your database (or the other way around), because the database couldn’t read it where it lived.

That meant guessing ahead of time which data you’d want, keeping a second copy of it all, building pipelines to move it, and constantly syncing so the two didn’t drift apart. A lot of plumbing, and slow going, all before you could answer one question. And even then, the answers were only as fresh as your last sync.

That now changes with Aurora PostgreSQL, which can call your live data and historical data in S3 together, in a single query. No copying, no pipelines to keep in sync.

And it’s fast, because we’ve built in DuckDB, a popular open source engine that’s really good at reading and analyzing data right where it’s stored. DuckDB reads the open formats like Parquet and Iceberg already sitting in your data lake, so there’s nothing to convert or move.

As folks build AI agents into their apps, the data their agent needs will depend on the task in front of it. Being able to query that specific data live, instead of copying it over just in case, is gonna be a big help for builders. https://t.co/R8h2Hcp1K7

[Diogo Almeida @CompleteSkeptic]

long shot: person at portola who called me the jev guy, took a photo with the team, then gave us "hot" stickers - can you share it? 🙏 we don't leave the office much and I think we'd treasure the pic forever 🥹

[Johann Schleier-Smith @jssmith]

@MarcJBrooker Great to see this. Is there a data point for Opus 5 with Claude Code? Perhaps I'm missing it.

[Johann Schleier-Smith @jssmith]

Harnesses matter. The green dots are the new frontier.

[Marc Brooker @MarcJBrooker]

Today we're excited to share Strands Harness. Strands Harness makes it easier to build reliable, cost-effective, agents with any model. It's open source, too!

And equal or better performance to proprietary harnesses with 28% fewer tokens!

[Johann Schleier-Smith @jssmith]

Emphasis on probabilities makes Jev natural for something like auto-approval / reviewer escalation. Follow @JasonSteving for more on this.

[Jason Steving @JasonSteving]

Jev powered "auto mode" in the Temporal Agent Harness is such a natural fit. Jev is a big unlock for efficient agent oversight. Very excited to see how straightforward it was to integrate along existing harness seams. More to come here for sure.

[Johann Schleier-Smith @jssmith]

@JasonSteving @temporalio followed you

[Johann Schleier-Smith @jssmith]

Where are all the Temporalites on X? Drop your handle below. I want to follow you. @temporalio

[Johann Schleier-Smith @jssmith]

Example code here: https://t.co/fyGneOuvCC

[Johann Schleier-Smith @jssmith]

Started out playing a game with Jev but the capability unlock is serious. It's neat to see how easily it drops into Temporal's experimental Agent Harness. Will share more soon...