I'm a Senior Workplace Coordinator at Airtable — running the 300-person San Francisco headquarters, supporting four global offices, and delivering the company's flagship events on a ~$300K annual budget.
I taught myself AI-agent development and turned my own team's busiest workflows into production automation: visitors, badging, desk booking, ticketing, shipping, and events. Winner of Airtable's company-wide builders prize.
Every project started as a manual workflow I personally ran, then rebuilt as software. The stickers are honest: live means running in production today.
Multi-office visitor management was hours of daily copy-paste between the visitor platform, Slack, and building-security portals. Reggie ingests visitor data via the Envoy API, posts daily digests to Slack, and completes building-portal registrations end-to-end through authenticated browser automation — verified at every step, so nothing is submitted unchecked.
Envoy wasn't keeping up with how the team actually runs operations, so I built its replacement. Event-driven on Kisi and Brivo webhooks and APIs, with eight Claude-coded interfaces: room and space booking, desk reservations with real-time alerts across 25+ desk situations, deliveries, badge analytics, and occupancy dashboards. A monitoring agent watches the pipeline — it caught a silently dropped webhook in production.
Workplace tickets were answered by hand, one at a time. I first deployed and trained Risotto AI, a vendor help desk, learned its limits, then built our own in-house agent grounded in the company's Atlassian knowledge base, so answers come from our real documentation instead of guesses. It deflects tickets from the Airtable ticketing system I also built, with Slack and email intake feeding one reportable queue.
The legacy badge-tracking base had drifted from reality: I measured 85% record drift and badges stranded with departed employees. I rebuilt the tables from the ground up, replaced 15 legacy automations with a self-correcting request/loan system, and added custom interfaces that made day-to-day badge work easy for the Workplace team.
Company events ran on tribal knowledge. I built the reusable machinery: a city-parameterized venue-outreach pipeline with reply tracking and no-double-email guards, an RSVP/check-in/feedback system with QR distribution and AI-summarized post-event ratings, and attendance analytics correlating 484 prior-year RSVPs against comms touchpoints.
Vendor compliance lived in inboxes. I built an 8-table system tracking 22 vendors and 64 contacts across four sites: certificate-of-insurance expiry against per-building requirements, service agreements per office, and budget-variance formulas tied to procurement.
Work-anniversary recognition meant manual gift orders every week. I built an agent that handles it end-to-end — finding upcoming anniversaries, staging shipments, and auto-generating shipping labels through the Shippo API — designed safety-first: stage-only purchasing with human-approved spend, read-only scoped tokens, and PII-safe logging. Validated end-to-end on synthetic data; in pre-launch.
Hosting onsite interview candidates took coordinated manual work across recruiting, calendars, and the visitor system. My working prototype chains recruiter intake into auto-created calendar invites with room booking, visitor invites with NDA delivery, and auditable minimal-PII confirmations. Phased rollout planned.
Event comms used to be a wall of Slack posts attendees had to dig back through. Now every company event, in every office, gets its own hand-coded landing page: event details, RSVP, photo galleries, FAQs, venue and travel info, dietary options — everything an attendee needs behind one link. Built for the full portfolio, from four-city simultaneous picnics (~150 guests per site, with dietary rollups and a live RSVP dashboard) to holiday parties.
The systems above aren't side projects. They automate work I own — and that operator context is why they get adopted.
Managed Airtable's Austin office (65–100 people) end to end, then relocated to run the 300-person San Francisco headquarters — building relationships, badge/access, and visitor programs, supporting NYC, Austin, and London remotely, and managing 8+ vendors day to day: performance, scopes of work, on/offboarding.
Own the company's flagship internal events (picnics, holiday parties, hack/build days, and 800-person all-hands where I draft the exec decks, run AV, and have MC'd) on a ~$300K annual budget.
Led two major company-wide food-program transitions (pantry and daily lunch, each a $1M+ annual contract) from vendor selection through multi-office rollout.
Onboarded 20+ hires monthly in Austin, then fully transitioned my successor when I relocated and helped train the NYC coordinator remotely.
Founding Culture Ambassador, advanced to the company Culture Committee alongside the Director of Employee Experience and Chief People Officer: company-wide culture, the ambassador program, and six ERGs.
Taught myself Claude Code, OpenAI Codex, and AI-agent development, then applied them to the workflows I knew best. Operator first, builder because of it.
Every system started as my own manual workflow. I don't guess at requirements. I've done the job the software replaces.
Least-privilege tokens, stage-only spending, PII-safe logging, human approval where it matters. Agents earn autonomy; they don't start with it.
Idempotent ingestion, verification before submission, and monitoring agents watching the pipelines; one caught a silently dropped webhook in production.
Live means live. Pre-launch means pre-launch. The same discipline applies to metrics: estimates are labeled as estimates.
Hiring for workplace ops, people systems, or AI deployment? Open to workplace & systems roles.