Pinned Tweet
I've been thinking about art (and "not art") for a long, long time. I finally started figuring out how to put some of those thoughts into words this year. Here's a first stab at it: medium.com/@TweetAnnaMarie/n…
AMC retweeted
Biggest news at ZapConnect yesterday:
The launch of Next Gen Zaps. Same workflows, 90% cheaper to run.
The amazing Anna Marie Clifton (@TweetAnnaMarie) demo’d it live.
Now you can use any AI (Claude, GPT, etc) to build and deploy @Zapier automations by describing them in plain language. No need to build step by step anymore. Your AI automatically chooses the right app connections, wires up the steps, and deploys the Zap for you.
The predictable steps run as code and AI only handles what needs judgment. That means reliability goes up and we help keep costs low.
We ran an example: pull the attendees, account details, emails, and recent news, then turn it all into a brief before a big call. The old way runs every step through an AI model. It works, and feels impressive. But it needs $1.12 a run, plus someone reviewing output.
Not anymore. Next Gen Zaps knows that pulling a name off your calendar doesn't need AI. Neither does finding the account or grabbing the emails, so those run as set steps. So AI reads everything and writes the brief, which is the one part that needs judgment. Only 12 cents a run.
That's the whole idea behind Next Gen Zaps. Build in whatever AI tool you like. Once it works, move it to Zapier and it runs on its own.
Try the Next Gen Zaps beta now, waitlist is open.
zapier.com/s/ngz-join-wait-l…
That feeling when Elon Musk points to the LLM benchmark you made with your team 🥲
Really proud of the zapier.com/benchmark work here.
AutomationBench tests how models perform on the trickiest, stickiest real-world workflows we know customers are actually trying to automate. 600 tasks, 6 domains, deterministic scoring.
And today our scores are featured on @AnthropicAI's official launch scorecard.
AMC retweeted
Gemini 3.5 Flash ranks #1 on Automation Bench (from Zapier), beating every other frontier model at a much lower cost
Wanna measure how good models are at executing super challenging, real world workflows? We just open sourced our benchmarks. Check it
We built an AI benchmark that measures real work.
Today we're releasing it to everyone.
AI evals tell you whether a model can do complex reasoning or generate code. Useful, but usually not the question our customers ask. They want to know: can this model find the right CRM record, send the right follow-up, and not break anything along the way?
We went looking for a benchmark that tested that. Nobody had built one, so we did.
@Zapier’s AutomationBench drops AI models into realistic business environments across six domains (Sales, Marketing, Ops, Support, Finance, HR) and checks whether the work actually got done.
The tasks include live CRM data, inbox threads with ambiguous context, and multi-step tool chains where one wrong call cascades.
Scoring is deterministic: either the right records were updated and the right messages were sent, or they weren't.
It’s useful enough that we're releasing it publicly today. Open task set, open methodology, open leaderboard. Everyone should have access to this.
No model has cracked 10%. Yet.
Try it here: zapier.com/benchmarks
Been a hot second, but I wrote a post this morning about a fun little framework I've been developing at the intersection of workplace productivity and personal growth
Using the ‘The Four Floors of Feeling’ to Give Feedback at Work medium.com/p/using-the-the-f…
AMC retweeted
next Thursday in SF!
Come hear from @dballona @TweetAnnaMarie and I about how the way people use MCP and tools is changing. Night and day different than 5 months ago…
Netflix’ biggest competitor is your sleep. OpenAI’s biggest competitor is your friends.
AMC retweeted
All eyes are on OpenAI DevDay.
Agent Builder was just announced: a new way to design AI-powered workflows right inside OpenAI. But it ships with only a few native integrations, and most businesses run on hundreds of tools.
That’s where Zapier MCP comes in. It instantly connects Agent Builder to Zapier's ecosystem of 8,000+ apps and 30,000+ actions.
Imagine this: an OpenAI Agent analyzes campaign performance data and, through Zapier MCP, updates budgets in Google Ads and syncs new leads to HubSpot.
Together, OpenAI’s Agent Builder and Zapier’s automation layer unlock the next wave of AI-native operations: intelligent logic meets real-world connectivity.
What you get:
- Production-ready connectors maintained by Zapier
- Secure, auditable calls from your agent to the tools your customers already use
- Faster time-to-value and fewer integration backlogs
Try Agent Builder with Zapier MCP today: lnkd.in/gzjsDic4
I had the chance to catch @rafalwilinski & @vitorbal’s eval talk and it was 🔥🔥
Love to see all the eval goodness y’all have been cookin’ turn into great content for other agent builders to learn from.
Congrats to @aiDotEngineer 2025 Best Speakers!
MCP: @zeeg
Tiny Teams: @alxai_
LLM Recsys: @devanshtandon_
GraphRAG: @danielchalef
Fortune 500 Day 1: @hwchase17
Architects Day 1: @denyslinkov
Infra: @dylan522p
Voice: @bnicholehopkins
Product Management: @bbalfour
Agent Reliability: @itamar_mar
SWE Agents: @bcherny
Reasoning: @natolambert
Evals: @rafalwilinski @vitorbal
Retrieval+Search: @WilliamBryk
Fortune 500 Day 2: @ritakozlov
Architects Day 2: @pk_iv
Security: @renebrandel
Design Engineering: @JohnPhamous
Generative Media: @sharifshameem
Autonomy+Robotics: @nikhilabm
Online Track: @MrAhmadAwais
Overall Best Speaker: @simonw!
For each track's best speakers we actually have a photo plaque printed for each of you with your speaker photo. come collect from me this weekend if you are still in town!
thanks to ALL our keynote, breakout, expo, workshop, attendee and more speakers for generously sharing their knowledge and working on the best AIE talks we've ever had! We appreciate you and are working to get them all edited and up online ASAP.
Love to see it!! 🔛🔝🔛🔝🔛🔝
Bringing back the Friday AI leaderboard!
⏫ @zapier agents
🔼 @cursor_ai + sonnet-4
🔼 @chatprd @linear agent
🫳 @chatprd > @v0
🫳 @ChatGPTapp o3
🫳 @DevinAI
⏬ @claude_code
⏬ @ChatGPTapp 4o
❌ @cursor_ai + Sonnet-3.7
❌ MCPs
❌ @meetgranola (I had v few meetings!)