Co-founder/CEO @Zapier
Missouri, USA
Joined January 2010
- Tweets7.7K
- Following81
- Followers26.3K
- Likes18.4K
Pinned Tweet
Today at ZapConnect, we debut Next Gen Zaps.
One of the most important product moments in @Zapier's history.
With Next Gen Zaps, customers can deploy agent-built Zaps in seconds. Simply describe your problem to your agent and it will build you a Zap that runs automatically, even when your laptop is closed.
Use it from Claude, ChatGPT, etc. to migrate existing Zaps, create new ones, or bring external automations onto Zapier. It's one line of text away.
My two favorite parts:
1. Hardening: Zaps will run the deterministic parts with code not AI. That means more reliability and lower cost.
2. Healing: When a Zap breaks, it falls back to agentic mode and can figure out how to recover without human intervention.
The early data shows how much we still have to learn. But we think it's good enough to share now.
One early access customer told us, "This is what Zaps were always supposed to be: easy."
Now in beta. Let us know what you think: zapier.com/s/ngz-join-wait-l…
Zaps now fix themselves, with AI.
Build your workflow in Claude, ChatGPT, etc. Zapier keeps it running.
When it hits an error? An agent reads it, tests a fix, and ships a new version.
Small fixes ship on their own. Anything bigger, or anything touching a login, waits for your OK.
All part of the new @Zapier. Describe the workflow, let your agent build it & host it in Zapier. We'll fix it when it breaks.
Just connect your AI to Zapier MCP: zapier.com/mcp
Agents now attempt my tasks before I even see them.
Email me, tag me, etc? My agent takes first crack at solving and responding.
I review (and often edit) every message, so it's still mine. Nothing goes out without my green light, and I'm saving a ton of time. Here's the setup:
- Anything where I get tagged or need to take action (Slack, email, Granola, etc) routes through a Zap into Todoist
- Each task kicks off a @Zapier cloud agent that's authenticated to all my tools: Slack, Gmail, Glean, Databricks, HubSpot, you name it
- It assigns an agent to attempt the task, propose what it thinks I'd do, and drafts the reply using a 'writing-as-Wade' skill I created.
- At my desk, I run a /sweep command in Cursor and blitz through all the low effort stuff: send, done, or edit.
- On my phone, I use a private Slack channel I created. "🚀" means send, "✅" means done, and a "🧵" reply means I have edits. The rest is usually voice-to-text, so I can handle stuff while I'm out.
It's my own agent factory, and it's working pretty dang good. But it only works because I worked really hard to make it sound like me. When AI dresses up a thought with the "veneer of smartness," it bugs me to no end.
I'd rather just get the sloppy human version of the output than the dressed up Claude version.
Fable 5.2 is here.
On Zapier workflows, it performs 2.3x better than Fable 5.1. It's the best
@AnthropicAI model we've tested to date.
At max effort, Fable 5.2 scores 51.4% on Zapier's AutomationBench.
@Claudeai's Sonnet 5.5, their previous best, scored 44.6%. Opus 5.5 scored 40.0%, and Fable 5.1 scored 22.4%. Huge jump over the previous Fable model, and a clear step past Sonnet and Opus too.
You don't need max effort to see the jump. Even at low effort, Fable 5.2 scores 39.7%, roughly the same as Opus 5.5 at max effort, for about the same cost per task ($1.30 vs $1.28).
Fable 5.2's biggest gains over 5.1:
1. Finance: from 16% to 53%
2. Sales: from 21% to 54%
3. HR: from 9% to 37%
Finance is also where it has the largest improvement over Opus 5.5 (36% to 53%)
Biggest difference with Fable 5.2 is how it works on each task. It averages about 97 tool calls per task, against 54 for Fable 5.1. It works harder and checks its work before it touches anything.
You do pay for that extra thoroughness. At max effort, Fable 5.2 averages about $4.64 per task, against $1.28 for Opus 5.5. So figure out which workflows need Fable 5.2, and run the rest on Opus 5.5 ($1.28 per task) or Sonnet 5.5 ($1.00 per task)
Fable 5.2 is live on @Zapier now.
We run every new model through Zapier’s AutomationBench: 657 workflows across 6 departments, to tell you what AI to use for your business.
Read the full leaderboard here: zapier.com/benchmarks
1
192
An agent shouldn't run your whole workflow.
Mine get the messy middle.
In fact most of my workflows follow the same 4-step shape: trigger, collect data, agent work, send it out.
The trigger, the data collection, and the 'send' run the same way every time. Code handles it all faster and cheaper than a model would.
Then the AI agent reads a pile of context and decides what matters. That's the only part that needs judgment, and the only part worth paying for AI for.
Keeping the model on the judgment step also keeps the bill down. Workflows that use AI only for judgment calls 𝗰𝗼𝘀𝘁 𝟳𝟭% 𝗹𝗲𝘀𝘀 𝘁𝗼 𝗿𝘂𝗻 than ones that send every step through a model.
One of my favorite workflows preps my to-do queue and drafts potential Slack replies in the background. The drafts show up right in Slack, so I just review, edit, and send.
The agent in that middle step is a hosted cloud agent. It carries context from run to run, which makes it a much stronger AI step than a one-off prompt.
I save the AI for the part that needs judgment, and let cheap code and automation handle everything else.
Any agent that connects to Zapier MCP can do that middle step: Claude Code, ChatGPT, Muse, Grok Bot, etc.
Which step in your workflows actually needs the agent?
With Next Gen Zaps, @Zapier figures that out for you. Repeat steps run as code, so you only pay AI for the steps that need it.
Next Gen Zaps fix themselves when they break.
In just one week, that saved 100,000 tasks that would have failed.
How it works: Say an app renames a field and your workflow fails. An agent reads the error, works out a fix, tests it, and publishes a new version of the Zap. Then it emails you what changed.
(Don't worry, the agent still checks in when it should. Small fixes go through on their own, but the agent asks you whenever a fix would make any big changes or touch a login)
For most of our history, a broken Zap meant a different email: your Zap broke, you gotta go fix it. We've sent a lot of those 😅
But more and more of our customers build workflows just by asking Claude, ChatGPT, Muse, Grok Bot, etc. That’s what we call Next Gen Zaps.
If you never touched the steps, you shouldn't be the one fixing them at 2am.
Connect @Zapier MCP anywhere you build with AI.
Something I'm hearing in more meetings: "Saying this for the agent."
Since AI call recorders showed up, people use that line to say the uncomfortable thing. Naming the elephant in the room. Asking someone to commit to a deadline and deliverables.
It's like the 2026 version of "with all due respect"
Part of it works like an accountability buddy. It reminds you what's actually needed from a call. Wanting a quick, painless AI summary pushes us to ask for the uncomfortable truths. Some of this might have felt a little harsh to say to another human but with an agent in the room, you get away with it.
So I've started inviting it. "If you have any concerns, say it now so the agent scoops it up." Now it's part of the process.
Basically "Speak now or forever hold your peace" 😂
The team, and our agents, seem better off for it.
Trick for optimizing your Grok usage:
Install @Zapier MCP and have Grok build automations instead of agents. In our modeling, using AI only for judgment steps cut workflow run costs by 71%
Agents are "probabilistic." That means they 𝘱𝘳𝘰𝘣𝘢𝘣𝘭𝘺 work.
Your business processes need to be 𝗱𝗲𝘁𝗲𝗿𝗺𝗶𝗻𝗶𝘀𝘁𝗶𝗰.
Ask an agent to do the same task twice and you'll get two different runs. Even if it gets the same result, it likely got there two different ways. That's useful for research and brainstorming. But updating the CRM, sending the invoice, routing the ticket? Those need to happen the same way every time, or you end up with bad data.
With Zapier, your agent builds the automation, and Zapier runs it. The agent does the part that needs judgment: it reads your request, figures out the steps, and sets it up. Then the automation runs on a trigger, like a new email, with the same steps every time. If a step breaks, Zapier switches back to an agent to figure out the fix.
It's cheaper too. Using AI only where it's needed cuts run costs by 71%.
Install @Zapier wherever you use AI (Claude, ChatGPT, Grok Bot, Muse, etc) and build an automation from a single prompt.
Zapier is one of the first plugins in Google Antigravity.
One click gives your agents access to 9,000+ apps.
Each Antigravity plugin packs agents, skills, and MCP servers into a single install.
Install the Zapier plugin to let Antigravity build and deploy Next Gen Zaps (now in early access) from a simple prompt. Each Zap runs on a trigger with the same steps every time, so it's faster and costs 71% less than using AI for each step.
The best part? Your admins will love you. They still decide which apps and actions are available to each team, so you can hand agents real work without anyone going rogue.
To set it up: open Customizations in Antigravity, click on Zapier, and sign in.
Connect Zapier, describe your problem, and watch your agent build the fix. And if something breaks? Zapier's agent fixes it on the fly, even while you're asleep.
Build it in @Antigravity, and @Zapier keeps it running.
Google just beat its own record on our AutomationBench.
Carbon hit 53.9%, just 4 weeks after their Argon model scored 51.3%.
Big month for @GoogleDeepMind and @OfficialLoganK.
Carbon's biggest gain over Argon is Finance (60%, up from 48%). It's also super strong for Operations (68%) and Marketing (64%).
It's weaker for Support (46%), and Argon still leads on HR.
I'd recommend running Carbon on Medium effort. Medium scored 53.0%, about the same as High, for about $1.65 a task. Even at Medium, Carbon beats Argon on High (51.3%) at about the same price ($1.70 a task).
Each lab has shipped different models for different jobs. If you run just one model (or lab) across the whole company, you're leaving points on the table somewhere.
Use any AI with @Zapier, and use Zapier anywhere you build with AI.
When people ask for an agent, they usually want a workflow.
But AI agents are for judgment. Automations are for anything that repeats…
The trick is just using your agent to build those workflows. One prompt and the agent builds a Zap to solve it, hosted on Zapier.
An automation gets that done cheaper, and the same way each time. No guessing.
Zapier gives the agent the parts that need judgment and lets a workflow run the rest. That costs 71% less to run than sending every step through a model.
Personal agents like Claude Duet, Muse, and Grok Bot are where people start now. Zapier works in all three, giving you access to 9,000+ apps you can connect to your workflows.
Use the agent to design the job, then let a Zap run it. Just tell your agent to connect @Zapier MCP.
Zapier is an official @SpaceXSI launch partner.
Just tell Grok Bot what you want to build. Instant access to 9,000+ apps through @Zapier.
Grok Bot can build automations, and Zapier hosts them. Each one runs on a trigger, deterministically (the same steps every time), so it's faster and costs less than having AI do the work on every run.
@ckor showed the team an example: @Bot set up a Zap on its own for a job that ran on every new email. Without Zapier, Grok Bot would have had AI check his inbox constantly. But the Zap, an automation, only runs when a new email shows up. Grok Bot picked the cheaper path.
Connect Zapier once and your agent can work in the tools your company runs on. That's 30,000+ actions it can take without connecting each app one by one or building an integration.
Companies need rules before handing personal agents real work. With Zapier, admins pick which apps and actions each team can use.
Just send this post to your Grok Bot and tell it to install Zapier.
Meet Claude Duet, Anthropic's new proactive agent.
Zapier is one of the official connectors at launch.
That means with one prompt, Duet can build an automation and run it on Zapier.
We call these Next Gen Zaps. Predictable parts run as code and AI only handles judgment, so workflows run as much as 90% cheaper through Zapier. Plus if something breaks, an agent works out a fix and keeps it running.
Zapier gives Duet 9,000+ apps to work with. Connect once and use the apps already connected in your Zapier account (you pick which)
@ClaudeAI's Duet is in research preview for US Pro and Max subscribers, waitlist only for now.
Don't have Duet yet, but use Claude? @Zapier works anywhere you build.
Just add Zapier under Settings > Connectors.
Trick for finding the AI automations to build first:
High value, easy to ship (top right of this grid)
This is one of the ways we help enterprise customers pick their first AI projects. By mapping their priorities.
Every idea gets scored on two things: what it's worth, and how hard it is to ship. Then it lands in one of four boxes:
1. Fund first: high value, easy to deliver
2. Second wave: high value, harder build. Scope these, then commit
3. Filler: easy to deliver, low value
4. Skip: low value, hard to deliver
(Keep in mind the above portfolio is just an example, but will help you think through your own automations)
Start in the top right. What sits there for you and your business? That’s what to prioritize.
Just send this tweet to your agent, connect @Zapier, and let it build the automations with Next Gen Zaps.
Full framework, including the scoring rubric to build your own grid: zapier.com/resources/guides/…
Build a Zap right from Claude, ChatGPT, Muse, Grok Bot, and more.
That's Next Gen Zaps, and it just had its biggest week yet.
Describe it once. @Zapier builds and runs it, even when your laptop is closed. It picks the apps, wires up the steps, and deploys the Zap for you. Then it keeps running on its own.
3 big differences:
1. Predictable: the steps that don't need AI run as code
2. Easier than ever to build: you describe it in plain language instead of building step by step
3. It fixes itself: if a run breaks, an agent works out a fix and tests it (the bigger changes ask you first)
Open beta is coming soon. In the meantime, request early access here:
zapier.com/workflow/early-ac…
Connect your Grok Bot to 9,000+ more apps.
Just tell it “@Bot add Zapier plugin” 👇
It'll connect @Zapier for you. Just approve the sign-in, then put it to work in the apps you already use.
That includes the apps your business runs on, but don't have their own Grok Bot plugin: Google Ads, Facebook Lead Ads, Instagram, Mailchimp, Pipedrive, Marketo, NetSuite, and thousands more.
Anywhere you build, Zapier connects the tools you need.
A few @Bot prompts you can try once Zapier is connected:
1. “Connect to any tools in Zapier and roast me based on what you find”
2. "Scan the newest Mailchimp subscribers for open deals in Salesforce and flag them”
3. "Add this week's Google and Facebook Lead Ads signups to one list and post it in the sales team Slack channel”
4. "Find every Pipedrive deal that hasn't moved in 2 weeks and draft follow-up emails for my review"
5. "Check BambooHR for new hires starting next week and draft a welcome note for each one”
Zapier is a launch partner for the Personal Agent Protocol:
A new open standard from @SierraPlatform and @Meta for how personal AI agents work with companies.
A growing share of your customers will reach you through an agent, and they'll never open your website. The Personal Agent Protocol gives agents a direct way in.
Here's what it means for your company:
1. Every agent says who it's acting for, so you know which customer is on the other end.
2. Your customer decides what the agent can do: look things up, or take action
3. You decide where agents can work: your website, your APIs, or your own agent.
The companies that are easy for agents to work with? Will win that customer. The rest get skipped without ever knowing they were in the running.
@Zapier has spent 15 years getting software to work with other software. This is the evolution of that job.
This is a work in progress, and a lot will change. But the rules for how agents work with companies are being written right now, and we want to help write them.
