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 “Share a Win” flow turns one person’s result into a post the whole team can see.
Doug then went further, building a project registry where teammates log the AI workflows they are creating, with before-and-after time savings, attribution when someone logs a project for a colleague, and a public board showing what the team is building. One Slack shortcut starts the flow, and the system loops back with relevant updates for whatever tool a new project uses.
Zapier acts as the connective tissue. New tool updates, teammate requests, engagement data, and workflow events move automatically into the team’s knowledge base. When something breaks, a Zapier Agent judges whether the failure is new or worse than an existing alert before raising the alarm.
The result is infrastructure built to keep running, improving, and helping a whole team build.
With so many tools, where do you start?
When most people talk about automation wins, they mean personal productivity. Doug saw a different problem.
“We had so many tools at our fingertips it was difficult to know where to start, let alone how to best use each one,” he says. “I wanted the Tracker to provide a way to make it easy to know what new features and updates were happening in our AI tech stack, but also make it clear how to apply that to your day-to-day to save time and drive impact.”
The team had access to useful tools, but it was challenging to know which one to use for a given task. “There’s so much going on out there—it can be overwhelming,” Doug explains. “It’s hard to keep up because AI is changing all the time.”
His goal was not only to provide more knowledge. It was to make new capabilities relevant to each person’s actual work.
Building visibility that builds adoption
Doug built the tracker in Klaviyo’s Slack workspace so updates would arrive where the team already worked. The system polls AI tools via RSS feeds and release pages to capture feature launches and model updates.
Raw notifications would recreate the noise problem, so the tracker adds two layers that make updates actionable: AI-generated explanations of what each update means and personalization by role and individual work.
When Cursor ships a coding feature, recruiters get an explanation focused on technical interviews. When Claude improves its reasoning, the personalization engine can deliver specific action items relevant to someone’s recruiting focus.
The tracker has delivered 314 real updates in 90 days, with 61% including role-tailored guidance. Feedback arrives through Slack reactions and requests for new tools to monitor. Zapier Paths and Formatter route tool requests and automatically send outcomes back to employees. Separate Zaps push feedback, metrics, and tool requests into the team’s knowledge base for leadership reporting.
From system to movement
The tracker solved the visibility issue, but Doug didn't stop there. He ran workshops teaching Zapier and Claude Code to the broader team.
On a 50-person team, 80% became Zapier seat holders. In three months, the team built 57 workflows from zero. Multiple people are now running workflows daily, handling critical work.
One teammate built a workflow that aligns recruiters and hiring managers earlier in the search process, reducing the back-and-forth that slows down every hire. Another built morning briefs to start the day informed and save time. Doug built an automated referral and inbound applicant process that saves about an hour per candidate.
The time savings add up: Doug estimates the team now saves more than 30 hours monthly, with that number climbing as more workflows come online. One teammate described the automated hiring workflow as “a huge time saver.” Doug says the larger win is that the referral and internal applicant workflow removes stress and headache as much as it removes time.
The system also shows which tools the team uses, which it does not, and whether there is demand for a new tool. That makes otherwise invisible adoption and renewal signals visible to leadership.
The builder multiplier effect
Doug’s approach works because it solves for capability, not just workflow. Most automation initiatives create dependencies: people rely on one builder to maintain and expand the system. Doug cares more about creating teachers and tools that make more builders.
The tracker keeps running on its own: hourly polls, AI-generated personalization, Slack delivery, database logging, and leadership reporting. But the bigger system is human. Workshops, office hours, and one-to-one coaching turned tool-curious teammates into workflow builders who create their own solutions.
AI adoption struggles when people can't see relevance to their specific work. Give them personalized visibility into what is possible, teach them how to build, and capability spreads faster than any top-down rollout.
