Aaron Diamond-Reivich

@ishverduzco @NotionHQ Would love to!

Any NYC friends want to come to the @NotionHQ office next month? I’m hosting a mixer for Founders & Creators

A pattern I've seen is that notebook are great for one-off EDA and report automations, but if you start automating a lot of work (ie: three end of month reports) then you start wanting to have shared utilities, a dashboard to share with colleagues, etc. Jupyter isn't good at multi-file projects. So you end up moving to vscode and into .py files

Curious about this: Why do people who started with Jupyter Notebook switch to VS Code to write their Python programs as their knowledge grows?

The iron man helmet, but for spreadsheets. A proactive AI that: > calls your attention to incoming missiles (data quality issues that will blow up your analysis) > gives you readily accessible super (builds the most useful data visualizations, separates missing data into a separate file for manual review, etc.) There's so many details you need to pay attention to when building a real-world, real-stakes report automation. Our goal is to offload the mundane stuff to Mito AI so you can focus on the highest leverage work that you are uniquely skilled at: making sure the analysis handles your specific business context with 100% accuracy.

@floor_per_area This is a really awesome visualization. Excited to follow along

Upzone Park Slope, block by block.

@helloiamleonie OpenAI, Anthropic, Google SDKs for making inference requests routed through AWS lambda functions, and our own harness to orchestrate it all for data science workflows. Took a few refactors to get the harness right but now it works wonderfully and easily extendable

If you’re building AI agents, what’s your current stack?

The Citibike doc at the Navy Yard wework usually has an attendant so that it can hold ~130 bikes instead of it normal 30 bikes. Today was the dreaded 1 day of the quarter when she was not there, sending 100 people to race to the nearest docs. Would've loved a text from Claude Code this morning to leave the house extra early to make sure I got a nearby doc.

Subways alerts included on transit402[.]dev

@Jason I'm in

We started an AI founder twitter group... reply with "I'm in" if you're a founder and want to be added

@0xyorke @mattmurrs I want my agent to send a drone ahead to the CitiBike doc w/ one remaining ebike to scan the bike out and keep it safe until I get there

@mattmurrs Multimodal is such a gap in google maps. When agentic auction with allocative efficiency for citibike reservations?

You missed the subway and need an e-bike across NYC, transit402.dev gets you there. Real-time MTA + Citi Bike data in one API. Pay just cents via x402 or MPP Add to your agent and get around NYC your way

@leerob any advice here? It's getting incredibly hard to review agent changes. Notice it says 3 lines changes in the Agent taskpane, but the file is lit up with diffs all over the place

Cursor's review has been showing me inconsistent diffs. Notice here: 1. The Agent Taskpane review says two files were changed with only a few lines each 2. In the editor it's showing me way more new lines than the Agent reports (These are old, already committed changes that I made yesterday with a different Cursor agent) 3. In the editor toolbar it shows me that 13 files were edited. This all started, when I edited an svg file and now if I ever click the "Review Next File" button after I click "Keep File", it takes me to that svg file. Is there any way to reset my change history / fix this issue? It's making it very hard to review the agent's work! @leerob @cursor_ai Thanks for your help! Here is my build: Version: 3.0.16 VSCode Version: 1.105.1 Commit: 475871d112608994deb2e3065dfb7c6b0baa0c50 Date: 2026-04-09T05:33:51.767Z Layout: editor Build Type: Stable Release Track: Default Electron: 39.8.1 Chromium: 142.0.7444.265 Node.js: 22.22.1 V8: 14.2.231.22-electron.0 OS: Darwin arm64 25.3.0

@lucasgordon Very cool. Didn't know that getting an apartment across from a popular restaurant could give me a new income source :)

Weekend project. NYC lines.

@j_becke Looks awesome! I love that I can change the theme, fun to play around with

New website just dropped (please help us find rough edges!) macro.com

Being able to easily share these flows with the rest of your team is a huge deal. When we onboard new teams to Mito, usually one person takes on the role of context creator. They: 1. write up custom rules like: If you want churn data, merge these tables on these columns, etc. 2. try to teach the rest of their team how to use the custom rules, how to keep them in sync, etc. For teams that already use Notion, some of that context, and all of that collaboration piece is already taken care. Huge ops win.

Mainly: Notion custom agents can be shared with a team. Worker tools can be versioned in git with auto-deployment through Actions. Custom agents have a run history that can be audited by other people to understand what the agent is doing across complex systems and tooling.

@arvinds @abacusai Testing now

@_aaronDR @abacusai Should be fixed with our push earlier today

.@abacusai, @arvinds can you confirm how to set the response format for the LLM router: - /app/route-llm-apis says to use {"type": "json"} - /help/developer-platform/route-llm/api says to use {"type": "json_object"}

@arvinds @abacusai Appreciate it. Do you know if that response type is passed through to non-openai models. I opened an issue here github.com/abacusai/api-p…

@_aaronDR @abacusai Thanks for noticing - we are fixing /app/route-llm-apis - the developer-plaform {"type": "json_object"} is the correct way

Anyone else noticing that gpt-5.2-codex is prone to returning the complete response_format object twice in one completion? Haven't seen this issue with other models from openai

My new favorite hobby is trying to trick Apple AI into generating text summaries that have nothing to do with what I actually said

@leerob Version 2.4.31. I tried using the integrated browser with @browser and just telling it to use the Chrome tab that I have open as well

@_aaronDR What version are you on? And is this using the integrated browser inside of Cursor (e.g. @​browser)?

Getting Cursor to verify its own changes is such an unlocked workflow, but recently I've been having some issues getting Cursor to use the browser. Any ideas on what I'm doing wrong here @leerob? Appreciate any help greatly!