# zapier-automation Published articles for zapier-automation. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Grok automation: How to use the Zapier Grok integration (Grok 4.7, Grok Bot, and more) DevFeed: [Grok automation: How to use the Zapier Grok integration (Grok 4.7, Grok Bot, and more)]() Original publisher: [Read original article]() Author: Nicole Replogle Published: 2026-10-30T05:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [workflow automation](), [AI Chat](), [AI for data automation](), [Image]() Tags: [agents](), [ai](), [ai-models](), [alternatives](), [anthropic](), [automate](), [automation](), [bot](), [connect](), [edge](), [google](), [grok](), [grok-4](), [grok-4-7](), [grok-bot](), [how-to](), [integration](), [live](), [models](), [offer](), [zapier-automation]() ### AI overview The article describes two ways to connect Grok with Zapier. In a Zap, Grok handles reasoning tasks such as researching leads, summarizing briefs, tracking trends, generating images, or extracting data, while predictable steps remain deterministic. This path requires a SpaceXSI API key and incurs separate Grok usage charges in addition to Zapier task use. Alternatively, Zapier MCP lets users trigger app actions from Grok Bot or Grok Build chat after connecting Zapier and running `/zapier-setup`; users choose which apps and actions are available, and successful actions consume their existing Zapier task allowance. MCP does not require a Grok API key, though a paid Grok plan may be needed depending on the plan. The article highlights Grok's live access to X for trend research and says Zapier manages app credentials. ### Source excerpt Grok has a very specific edge over other AI models: live access to X, so your agents can keep their finger on the pulse a little more easily. But outside of that, Grok models and agents are still solid alternatives to what OpenAI, Anthropic, and Google have on offer. And if you're using Grok for work, you'll want to connect it to the rest of your tech stack. The most secure and easiest way to do that is with Zapier. There are two main ways to automate Grok with Zapier. You can add Grok to the wo ## How a three-person hiring startup built its go-to-market engine before the rush DevFeed: [How a three-person hiring startup built its go-to-market engine before the rush]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-10-22T13:00:00Z Content type: news Language: en Sources: [Zapier]() Topics: [Flowable](), [Business, Industry, Usability, User Experience, User Research, Web Strategy](), [task management]() Tags: [2025](), [about](), [ai](), [attention](), [candidate](), [experience](), [eye](), [formatting](), [found](), [hiring](), [id](), [instead](), [job](), [platform](), [process](), [research](), [resume](), [show](), [skills](), [thought](), [zapier-automation]() ### AI overview Vetano, a three-person hiring startup, uses Claude, Zapier, Instantly, ZeroBounce, Google Sheets, Slack and HubSpot to handle outreach while keeping Chris Fairley in control of messages. Claude builds and tests welcome-email Zaps; test emails go to Chris for approval before launch, and the flow skips test accounts, validates addresses, prevents duplicate welcomes and still sends if ZeroBounce is unavailable. For expo outreach, 37 warmed mailboxes across 13 domains sent 19,569 emails; ZeroBounce excluded 2,874 dead or risky addresses, and 73 messages bounced (0.37%). Claude prepared weekly lead lists and drafts, while Viktor managed the sending fleet and flagged mailboxes above a 3% bounce rate. Chris reviewed personal drafts, replies and sends; Zapier routed replies and interested leads into Slack and HubSpot, and opt-outs onto a blocklist. At the expo, 71 welcome sends for 40 businesses and 31 candidates completed with zero errors. Chris plans to move sending to Resend as sign-ups grow. ### Source excerpt Chris Fairley founded the hiring platform Vetano in early 2025. After a particularly challenging job-hunting experience, Chris found that a strong resume was no longer enough. Resumes get about seven seconds of attention, according to Ladders' eye-tracking research. With AI now screening many of them, one formatting slip ends the read. If a candidate could show their skills on video instead, Chris thought, the whole process might work differently. Vetano replaces the resume with ID-verified skil ## How a recruiting agency uses Claude and Zapier MCP to find the candidates who aren't looking DevFeed: [How a recruiting agency uses Claude and Zapier MCP to find the candidates who aren't looking]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-10-20T17:08:35.617936Z Content type: news Language: en Sources: [Zapier]() Topics: [Claude](), [MSP MCP]() Tags: [automation](), [candidate](), [candidate-screening](), [capacity](), [ceo](), [claude](), [clients](), [code](), [company](), [hiring](), [management](), [mcp](), [property](), [property-management](), [real-estate](), [recruiting](), [recruitment](), [salesforce](), [scripts](), [team](), [zapier-automation]() ### AI overview Blue Castle Agency uses Claude to automate candidate sourcing and quality checks, connecting its applicant tracking system, sourcing tools, and Google Sheets through Zapier MCP. Claude selects active jobs, applies company and role success profiles, builds candidate lists, and runs a second review later in the day. Curtis Key reports that Claude's candidates are approved about 94% of the time, compared with 78-83% for human sourcers, and estimates the sourcing and review workflows save more than 240 hours weekly at current volume. A separate process on Blue Castle's server assesses candidates against job criteria using recruiter notes and Zoom transcripts, researches employers, and drafts submissions, saving an estimated four or more hours per recruiter each week. The agency says sourcing output has risen about fourfold, freeing recruiters to focus on candidate conversations. It is also moving repeatable tasks into Next-Gen Zaps, including weekday screening-call prep sheets and deal logging, with the aim of leaving Claude to handle judgment calls and reducing costs. These figures are Curtis's estimates; the excerpt does not detail how they were measured. ### Source excerpt Curtis Key has been building automation for about 20 years, first with basic code and scripts, then in Salesforce at a real estate brokerage that grew from 8 to 105 agents. But when hiring became the brokerage's hardest problem, he founded Blue Castle Agency, a recruitment firm exclusively for real estate and property management. Curtis keeps one idea in front of the team: the best candidates aren't looking. They're already employed, and a recruiter has to find them and earn a conversation. Most ## From a garage and a pickup truck to $3.8 million DevFeed: [From a garage and a pickup truck to $3.8 million]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-10-14T13:00:00Z Content type: news Language: en Sources: [Zapier]() Topics: [AI Chat](), [Google Analytics]() Tags: [2022](), [ai](), [ai-tools](), [alert](), [apps](), [army](), [audit](), [automatically](), [board](), [booking](), [business](), [button](), [campaign](), [chat](), [chatgpt](), [google](), [massachusetts](), [october](), [plumbing](), [truck](), [zapier-automation]() ### AI overview Since founding 3R Plumbing & Mechanical in 2022, Ross Hunt grew the South Shore HVAC and plumbing company from about $300,000 in annual revenue to a projected $3.8 million, with 15 employees. Its workflow centers on ServiceTitan as the system of record and Zapier as the connector. After using classic Zaps for forms and paperwork, Hunt adopted Next-Gen Zaps in 2026: he describes needs to Claude through Zapier MCP, then reviews and tests the generated workflows. The 36 live Next-Gen Zaps run about 1,400 times weekly across 30 apps, powering role-specific portals, scheduled reports, lead alerts, purchasing and follow-up flows, and Google Ads conversion data drawn from ServiceTitan. Hunt says the automations help surface stale leads, tracking errors, and wasted ad spend. The account had exceeded its monthly task limit as the business grew; the article describes this automation approach as the basis for a $5 million growth target. ### Source excerpt A missed call in home services is a missed job. In a Massachusetts October, that can be a five-figure heating replacement going to the next company on Google. Ross Hunt started 3R Plumbing & Mechanical in 2022 out of his garage with one pickup truck. In its early days, the veteran-owned residential HVAC and plumbing company did about $300,000 a year. This year, it's on track for nearly $3.8 million. It now has 15 employees, a shop in Norwell, Massachusetts, and customers in about 21 South Shore ## Gemini automation: How to use the Zapier Gemini integration (Gemini 3.8 Flash, Gemini Enterprise, and more) DevFeed: [Gemini automation: How to use the Zapier Gemini integration (Gemini 3.8 Flash, Gemini Enterprise, and more)]() Original publisher: [Read original article]() Author: Nicole Replogle Published: 2026-10-06T05:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [workflow automation](), [Automation](), [AI for data automation](), [AI for customer service automation](), [ai-governance]() Tags: [ai](), [all](), [apps](), [automation](), [but](), [can](), [chat](), [connect](), [cursor](), [docs](), [draft](), [ecosystem](), [enterprise](), [fast](), [gemini](), [gemini-enterprise](), [google](), [google-docs](), [how-to](), [integration](), [zapier-automation]() ### AI overview Zapier connects Gemini to workflows in two ways. AI by Zapier adds a selectable Gemini model as a step in an existing Zap, for tasks such as classifying support requests or summarizing feedback; ordinary deterministic steps can run without a model. The article says this option includes prompt testing, knowledge sources and agentic tool calling, with usage charged to Zapier tasks. A dedicated Google AI Studio integration is also available, and bring-your-own-key use of models not built into AI by Zapier is billed directly by Google. For work initiated in Gemini chat, Zapier MCP connects the app library to Gemini Enterprise, where admins enable the connector, authenticate and govern which apps and actions are allowed. The article describes this chat integration as available only in Gemini Enterprise, not personal Gemini. It also states that Zapier MCP works with other MCP-supporting agent interfaces. ### Source excerpt Anyone who lives in the Google ecosystem has probably used Gemini for a quick draft or a fast answer. (Or if you're like me, you've been driven to your limit by the Google Docs popups encouraging you to use AI whenever your cursor strays too close to the bottom of the screen.) But a chat window is just the beginning of what Gemini can do. Its real power shows up when you connect it to the rest of your apps and let it do work on your behalf. All of Gemini's models are available in Zapier, so you ## Meta Muse automation: How to use the Zapier Muse integration (Muse Spark 1.3 and more) DevFeed: [Meta Muse automation: How to use the Zapier Muse integration (Muse Spark 1.3 and more)]() Original publisher: [Read original article]() Author: Nicole Replogle Published: 2026-10-02T05:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [MSP MCP](), [workflow automation](), [AI Context Management]() Tags: [ai](), [ai-agent](), [api](), [automation](), [credentials](), [meta](), [zapier-automation]() ### AI overview A tutorial explains two ways to connect Meta Muse with Zapier: use Muse Spark as a reasoning step in existing workflows, or let Muse initiate actions across connected apps from chat through Zapier MCP. It describes setup, permissions, authentication, task usage, and example automations. ### Source excerpt The concept of "less is more" doesn't seem to have made it to Silicon Valley. Every time I blink, it seems like there's yet another AI agent available on the market. And right on cue, another AI bombshell has entered the villa: Muse is a personal AI agent from Meta (of Facebook fame) that can do things on your behalf, like opening a browser, filling out forms, and sending emails. But a personal agent is only as useful as what it can reach. Muse comes with roughly 40 native connectors, covering G ## How Alpine Roofing uses Zapier to make sure nothing slips through DevFeed: [How Alpine Roofing uses Zapier to make sure nothing slips through]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-30T14:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [Deployment-Driven Development](), [AI Chat]() Tags: [ai](), [api](), [app](), [automated](), [zapier-automation]() ### AI overview Alpine Roofing's founder uses Zapier to automate customer and office workflows, then uses Claude with Next-Gen Zaps to rebuild and test those workflows faster. The automations handle lead follow-up, estimates, and job updates, while the company is building an operations app on top of its connected tools. ### Source excerpt A single roof can be a $30,000 job. That makes a missed request from a new customer one of the most expensive mistakes a roofing company can make, and with "hundreds of small tasks going on" in every job, as Ben Beckett puts it, there's no shortage of chances to make it. Ben is the founder and owner of Alpine Roofing, and for about as long as the company has been around, his answer to that problem has been Zapier. Built on Zaps from the start Ben came to roofing from banking, and he's always bee ## ChatGPT automation: How to use the Zapier ChatGPT integration (GPT-6 + more) DevFeed: [ChatGPT automation: How to use the Zapier ChatGPT integration (GPT-6 + more)]() Original publisher: [Read original article]() Author: Steph Spector Published: 2026-09-23T07:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [ChatGPT](), [workflow automation](), [AI Integration Strategies](), [AI for data automation](), [AI for customer service automation](), [llm-reasoning]() Tags: [ai](), [ai-chatbot](), [ai-models](), [all](), [apps](), [automation](), [but](), [can](), [chatbot](), [chatgpt](), [existing](), [how-to](), [improvements](), [integration](), [leaving](), [love](), [means](), [models](), [openai](), [power](), [zapier-automation]() ### AI overview Zapier supports two ways to use ChatGPT with other apps. AI by Zapier adds a model step inside an existing workflow, so AI can handle tasks such as ticket classification while deterministic steps manage the rest. You can tune prompts, attach knowledge sources, enable tool calling, and choose a model; usage is billed in Zapier tasks, with advanced models costing three or five tasks in some cases. Using your own key for models unavailable there means paying the provider directly. The dedicated ChatGPT integration instead uses your OpenAI account; the source recommends AI by Zapier for its additional features and model-switching flexibility. Zapier MCP lets ChatGPT take actions in apps you authorize, with access governed through Zapier-managed authentication and permissions. It also works with other MCP-supporting agent harnesses. ### Source excerpt OpenAI is rolling out new models all the time, and you can see the improvements and power even in a quick back-and-forth with ChatGPT. But as much as we all love shooting the breeze with an AI chatbot, the real question is how you can put the AI models to use in your work. All of ChatGPT's state-of-the-art models are available in Zapier. That means you can add ChatGPT-powered steps to your existing workflows, or securely access and take action in apps directly from ChatGPT, without ever leaving ## Claude integrations: How to use Zapier with Claude (Fable 5.1, Opus 5.5, and more) DevFeed: [Claude integrations: How to use Zapier with Claude (Fable 5.1, Opus 5.5, and more)]() Original publisher: [Read original article]() Author: Steph Spector Published: 2026-09-23T07:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [Claude](), [workflow automation](), [AI Integration Strategies](), [AI for data automation](), [AI Chat](), [AI for customer service automation](), [Slack](), [Google Calendar]() Tags: [apps](), [automate](), [automation](), [automation-inspiration](), [benchmark](), [brain](), [but](), [can](), [claude](), [connect](), [contents](), [existing](), [faq](), [good](), [here](), [here-s](), [how-to](), [it-s](), [let](), [model](), [with](), [zapier-automation]() ### AI overview Zapier connects Claude to apps in two ways: AI by Zapier adds a Claude step to a background workflow, while Zapier MCP lets Claude invoke authorized app actions directly from chat. With AI by Zapier, deterministic steps can run without AI, and Claude can handle tasks such as summarizing or classifying incoming data. The article says this option includes prompt testing, knowledge sources, and agentic tool calling; model costs count against Zapier tasks, with no separate Anthropic bill. Users can instead bring their own key and pay the provider directly. The dedicated Claude Anthropic integration uses an Anthropic account and is described as having fewer workflow features. MCP connects Claude to actions across 9,000+ apps; users choose which actions to expose, then Claude can carry out sequences such as retrieving records and posting summaries. Setup involves generating a Zapier MCP server URL and adding it in Claude's Connector settings. The excerpt also says Zapier-managed authentication keeps credentials governed in one place. ### Source excerpt With every new model release, Claude tops almost every benchmark. And chatting with Claude makes it clear why: it's good at everything. But while there's power in a back-and-forth conversation, you can accomplish a lot more when you use Zapier to connect Claude to the rest of your apps and let automation carry out entire workflows for you. Here's how it works. Table of contents: Add Claude's brain to your existing workflows Automate workflows directly from Claude Claude automation FAQ Add Claude ## Which AI models can you automate on Zapier? (OpenAI, Anthropic, Google, Moonshot AI, Z.ai, and more) DevFeed: [Which AI models can you automate on Zapier? (OpenAI, Anthropic, Google, Moonshot AI, Z.ai, and more)]() Original publisher: [Read original article]() Author: Nicole Replogle Published: 2026-09-23T05:00:00Z Content type: tutorial Language: en Sources: [Zapier]() Topics: [AI Models](), [Claude](), [AI Chat](), [open-responses]() Tags: [ai](), [ai-models](), [anthropic](), [google](), [mcp](), [moonshot](), [moonshot-ai](), [openai](), [z-ai](), [zapier-automation]() ### AI overview This guide lists AI models available through Zapier's built-in AI step and direct provider integrations. It describes how the options differ, including account and billing arrangements, and points readers to AutomationBench for comparing model performance on business workflows. ### Source excerpt Staying up to date on the latest AI models is like trying to keep my house vacuumed in the height of my dog's shedding season (a losing battle). New AI models drop practically every week, and it's not exactly obvious which ones deserve a spot in your workflows. This guide is your cheat sheet, with every model you can automate on Zapier right now, sorted by provider. If you just want to cut to the chase and find out which model you should be using for which task, that's what AutomationBench is fo ## How Ethan Schwandt helped Jobber turn AI adoption into a building culture DevFeed: [How Ethan Schwandt helped Jobber turn AI adoption into a building culture]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T04:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [AI Strategy](), [workflow automation]() Tags: [2026](), [adoption](), [ai](), [ai-adoption](), [ai-transformation](), [apps](), [asana](), [automation](), [building](), [claude](), [code](), [culture](), [employees](), [enablement](), [feedback](), [google-calendar](), [google-sheets](), [governance](), [hackathon](), [work](), [zapier-automation]() ### AI overview At Jobber, Ethan Schwandt helped turn access to Zapier into a company-wide ability to improve work by pairing practical enablement with governance. The approach included a hackathon for 55 directors, hands-on training for 161 employees, office hours, learning resources, and AI in onboarding. Active Zapier builders grew 122% in the first 30 days; by summer, teams were running hundreds of workflows across 28 business-system apps, with Zapier MCP used across 20 apps. One onboarding team links Livestorm registrations to a live sheet, uses Claude to create presentation materials, and sends them to Slack; a separate workflow tracks attendance and summarizes chat feedback. The excerpt attributes broader adoption to helping employees build solutions for work they understand, reducing reliance on a single specialist. These figures and examples are drawn from the supplied excerpt. ### Source excerpt When companies talk about AI transformation, they often start with what they rolled out: the model, the license, the training program, or the pilot. Ethan Schwandt started somewhere more useful: the work. As Senior Manager, Talent Acceleration at Jobber, Ethan helped employees recognize where AI and automation could remove a recurring handoff, reduce manual work, or make information easier to act on. He paired that opportunity-spotting with practical enablement, clear governance, and hands-on su ## How Jocelyne Mendez-Guzman made follow-up faster DevFeed: [How Jocelyne Mendez-Guzman made follow-up faster]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T04:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [workflow automation](), [Tool]() Tags: [2025](), [2026](), [accounts-receivable](), [ai](), [awards](), [builder](), [can](), [faster](), [follow](), [giving](), [gtm](), [operations](), [revops](), [sales](), [speed](), [system](), [team](), [teams](), [this](), [up](), [zapier-automation]() ### AI overview BioRender RevOps specialist Jocelyne Mendez-Guzman built a call follow-up workflow that cuts drafting time from about 20 minutes to under three, an estimated 85% reduction. After each logged call, a Gong webhook sends transcript and metadata to Zapier; JavaScript structures the data, and AI by Zapier extracts the account, recipient, discussion points, and next steps. The workflow identifies internal participants' roles and call type, routes drafts through six paths for business development, account executives, and customer success, then assembles role-specific templates from the conversation. Drafts are formatted for Gmail, logged in Google Sheets, and sent to reps in Slack with a button to open them in Gmail. Launched in stages starting with customer success, the workflow has generated many thousands of drafts since March. The source reports the time savings as an estimate. ### Source excerpt Jocelyne (Joce) Mendez-Guzman is no stranger to the Zappy Awards. In 2025, she won our Operations Automator of the Year for a workflow that processed accounts receivable tickets 69% faster. With that win under her belt, she moved into BioRender's RevOps team, where her work now supports teammates across GTM. This year, she's back as the 2026 Sales AI Builder of the Year, helping those teams follow up on calls 85% faster. Joce built a follow-up system her reps can trust, giving GTM teams speed wi ## How Ignacio Piñeiro scaled fraud control with exception-based AI review DevFeed: [How Ignacio Piñeiro scaled fraud control with exception-based AI review]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [online-fraud-prevention](), [human review](), [Finance](), [Image]() Tags: [ai](), [control](), [exception](), [fintech](), [fraud](), [operations](), [zapier-automation]() ### AI overview Galgo's delivery-photo control now uses AI to make routine judgments and sends only flagged cases to human reviewers. When an agency logs a delivery, a trigger retrieves the deal and photo from HubSpot; AI by Zapier runs GPT-5-mini against rules requiring a real customer and eligible vehicle together in a real photo. Watermarks are allowed; stock photos and signed documents are rejected. Invalid submissions receive a reason classification, and every verdict is logged in Google Sheets with a Slack alert for the Success and Fraud team, which can inspect photos and correct prompt errors. The text reports invalid evidence falling from about 8% to under 2%, while fewer than 60 photos a month require manual review, down from roughly 150 hours spent reviewing over 3,000 submissions. Piñeiro estimates the reduction avoids tens of thousands of dollars in first-payment defaults. Human reviewers retain ownership and focus on exceptions; the system depends on monitoring and tuning for real failure modes. ### Source excerpt Ignacio Piñeiro runs operations at Galgo, a fintech that lends money for motorcycles across Mexico. Every loan he approves hinges on a simple question: Did this delivery actually happen as it should? Three thousand photos, one last chance Each motorcycle Galgo finances requires proof of delivery -- a photo of the customer with their new vehicle -- before they can start collecting the loan. That photo is the company's main defense against delivery fraud. If fake, wrong, or low-quality evidence slip ## How Ariel Chen built trust before she built automation DevFeed: [How Ariel Chen built trust before she built automation]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [workflow automation](), [human review](), [trust]() Tags: [accessible](), [ai](), [alignment](), [api](), [api-keys](), [apis](), [audit](), [automation](), [compliance](), [figma](), [international](), [lead-time](), [onboarding](), [operations](), [people](), [screen](), [system](), [team](), [time](), [trust](), [zapier-automation]() ### AI overview Ariel Chen's two-person People Operations team at Figma reduced background-check monitoring from more than three hours a week to a daily scan under 15 minutes. Four Zapier workflows sync Checkr events to a Google Sheet, keep an append-only status log, and use daily AI by Zapier triage to identify urgency from the specific pending screen and the candidate's start date. The system flags cases for escalation but leaves final judgment to people. Before relying on it, Chen compared outputs with Checkr screen by screen, fixed issues such as row misalignment, and required five consecutive days of matching results. The team still reviews output, consults audit and compliance experts, and uses a manual fallback when automation is unreliable. ### Source excerpt Ariel Chen coordinates People Operations at Figma, where a two-person team tracks over 100 background checks each month across 12 countries. In a role where a missed screen can delay someone's start date or create compliance issues, Ariel built a system her team can rely on. When every screen says "pending" Figma hires globally, and international background checks often take longer than the two-week lead time between onboarding cohorts. But every background check showed the same generic "pendin ## When systems won't talk, Nicholas Francoeur builds the bridge DevFeed: [When systems won't talk, Nicholas Francoeur builds the bridge]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [AI Integration Strategies](), [REST API](), [human review](), [Tool](), [Managed Services]() Tags: [ai](), [api](), [assets](), [data-quality](), [infrastructure](), [integration](), [logging](), [operations](), [zapier-automation]() ### AI overview Compucom cut field inventory and scheduling work by connecting its existing tools with two workflows. For inventory, technicians upload equipment photos through a form; AI by Zapier extracts make, model and serial numbers, while Foresight reference data, Zapier Tables and an OCR cross-check help flag unknown devices and mismatches for review. Surveys that took eight hours now take two to four, and reported asset-entry errors fell from 25% to roughly 1%. For scheduling, spreadsheet data flows through the Resource Guru API, reducing weekly builds for about 700 sites from 20 hours to one and pause-related rescheduling from 40 hours to about two. The approach assigns AI to messy inputs and deterministic logic to structured transfers; the excerpt says Compucom is adapting it for more teams and clients. ### Source excerpt Nicholas Francoeur manages infrastructure technology for Compucom, a 5,000-employee company running technology deployments and on-site support across hundreds of client sites nationwide. When off-the-shelf tools couldn't handle complex field operations at the scale he needed, Nicholas did not wait for vendors to catch up. The disconnect that costs hours every day Technicians spent entire eight-hour shifts manually logging 50 to 100 hardware assets per site. They photographed equipment, then hand ## How Doug Hamilton turned an AI tracker into a team of builders DevFeed: [How Doug Hamilton turned an AI tracker into a team of builders]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: article Language: en Sources: [Zapier]() Topics: [Artificial Intelligence](), [AI Integration Strategies](), [Slack](), [Tool](), [Claude Code]() Tags: [acquisition](), [ai](), [ai-tech](), [ai-tools](), [automated](), [claude](), [guide](), [intelligence](), [recruiting](), [relevance](), [slack](), [stack](), [system](), [talent](), [talent-acquisition](), [team](), [tech](), [tech-stack](), [tools](), [tracker](), [zapier-automation]() ### AI overview Doug Hamilton's AI Tech Stack Tracker helps Klaviyo's Talent Acquisition team turn frequent AI tool updates into role-specific ideas and team-built workflows. It polls more than a dozen tools hourly, uses Claude to explain updates for recruiting work, and sends personalized digests and Slack guides. Zapier routes requests, feedback and workflow events into a knowledge base; an agent filters failure alerts for new or worsening problems. A project registry records workflows and reported time savings. In three months, 80% of the 50-person team became Zapier seat holders and built 57 workflows; Hamilton estimates they save more than 30 hours monthly. The excerpt attributes wider adoption to workshops, office hours and coaching alongside the automated tracker. ### Source excerpt Doug Hamilton built an AI Tech Stack Tracker, an automated intelligence system that helps Klaviyo's Talent Acquisition team keep up with fast-moving AI tools and turn updates into action. Every hour, the tracker polls more than a dozen AI tools directly. Claude translates raw changelogs into plain-language relevance for recruiting work, then a weekly digest delivers updates based on what each teammate cares about. A "Try it out" feature sends a personalized, role-specific guide to Slack. A "Shar ## How Carlos Robledo turned a recruiting report into organizational infrastructure DevFeed: [How Carlos Robledo turned a recruiting report into organizational infrastructure]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: news Language: en Sources: [Zapier]() Topics: [workflow automation](), [AI Integration Strategies](), [knowledge-management](), [Tool]() Tags: [automation](), [building](), [friday](), [hiring](), [infrastructure](), [lead](), [major](), [open](), [organization](), [organizational](), [personal](), [product](), [recruiters](), [recruiting](), [report](), [reports](), [rex](), [spending](), [system](), [talent](), [zapier-automation]() ### AI overview Carlos Robledo turned recurring recruiting reports into Rex, a 19-workflow system built with Zapier around Ashby data, Airtable storage, and Slack. It provides scheduled and on-demand `/rex` pipeline reports alongside alerts for stale candidates, interview changes, overdue feedback, offers, and SLA issues. Features grew through recruiter testing and feedback; the system now serves recruiters across the organization. Carlos estimates it recovers up to 50 recruiter-hours weekly, including time spent compiling status across roughly 143 open requisitions. Rex keeps data gathering, rules, and reporting deterministic, while AI helps build and improve workflows and interpret requests or present data as readable briefings. Carlos's internal Ashby-connected bot offered better access control but produced less predictable, harder-to-scan output than Rex's structured Slack interface. ### Source excerpt When personal automation becomes organizational infrastructure Carlos Robledo is a Lead Technical Sourcer at Hims & Hers. When he got tired of spending hours every Friday building hiring reports for stakeholders, he built Rex, a 19-workflow system that now serves recruiters across the talent organization. There was a specific moment that triggered Rex. While working with his Chief Product Officer, Carlos was responsible for producing two major updates across several open requisitions. The work m ## Meet the 2026 Zappy Award winners: the builders who put AI to work DevFeed: [Meet the 2026 Zappy Award winners: the builders who put AI to work]() Original publisher: [Read original article]() Author: Rob Ayre Published: 2026-09-23T00:00:00Z Content type: news Language: en Sources: [Zapier]() Topics: [workflow automation](), [business logic](), [Developer experience]() Tags: [2](), [2026](), [acceleration](), [accountability](), [adoption](), [ads](), [ai](), [award](), [business](), [company](), [delivery](), [it](), [monthly](), [number](), [numbers](), [phone](), [reports](), [revenue](), [under](), [work](), [zapier-automation]() ### AI overview The 2026 Zappy winners show AI and automation value through changes to business measures, with systems built close to the work. Galgo used GPT-5-mini to flag suspicious delivery photos for review, reducing invalid evidence from about 8% to under 2% across 3,000-plus monthly submissions. Youtech matched paid-search clicks to phone revenue and uploaded conversions to Google Ads, attributing $213,000. Other examples combine AI with controls: BioRender uses AI to extract call details but deterministic code for exact pricing; Mercari routes uncertain or failed support cases to humans; Figma keeps human adjudication and manual fallback for background checks. The examples also emphasize practical enablement, audit logs, deduplication, retries, and measuring adoption and operational outcomes. ### Source excerpt Most companies still measure AI by what they roll out: seats bought, licenses assigned, and pilots launched. Those numbers prove that the company has started. They don't prove anything changed. The 2026 Zappy Award winners measure it differently. Every one of them moved a number that their business already reports on. At Galgo, the rate of invalid delivery evidence fell from about eight percent to under two percent across more than 3,000 monthly submissions. At Youtech, $213,000 in phone revenue