# How we keep interview loops on schedule Each day our Machine agent picks up candidates who are ready to book in Greenhouse, checks the panel's Google Calendars, and drafts the time proposal and invites for a coordinator to approve. Canonical page: https://themachine.myapps.ai/use-cases/interview-scheduler A candidate passes the screen, and suddenly booking the next round is a little project of its own. You check the interview plan to see who sits on the panel, hunt for a slot when all of them are genuinely free, offer it to the candidate, and get invites onto every calendar before that slot disappears. No single step is difficult. Multiply it by a few interviewers and a few candidates, though, and it turns into a slog. Each day it waits is a day the loop stands still. So an agent on Machine handles that coordination daily. For each candidate flagged as ready to schedule in Greenhouse, it reads the interview plan, looks up the panel's free time in Google Calendar, and drafts both a time proposal for the candidate and an invite for each interviewer. It sends nothing and has no say in hiring. A coordinator checks every proposal and invite before anything leaves. That's how our own interview loops keep moving. - **Team:** Machine - **Runs on:** A daily schedule - **Connected systems:** Greenhouse · Google Calendar · Email - **Mode:** Suggests times and writes drafts · a coordinator confirms and sends ## The problem Booking an interview loop means joining up two systems that never talk. The plan sits in Greenhouse: who's on the panel, how many rounds there are and how long each takes. Whether those people are free sits in their calendars. Checking both by hand for every candidate who passes a screen is exactly the sort of admin that falls behind as soon as you have more than one open role. The usual shortcuts break down. A shared booking link is only as good as each interviewer's habit of keeping it up to date, and it can't tell you who the panel should be for this particular candidate. A coordinator flipping between a stack of calendar tabs and Greenhouse can manage, but not beyond a handful of loops. And a missed invite makes you look disorganised to a candidate who is probably talking to other companies too. ## What we built Once a day a schedule wakes an agent on Machine. It opens a fresh session, a cloud sandbox, and reads every candidate in Greenhouse who is flagged as ready to schedule. For each one it opens the interview plan to find the panel, checks every panelist's Google Calendar for free time, and drafts a time proposal for the candidate plus one calendar invite per interviewer. All of those drafts go to the coordinator. The agent sends nothing and makes no decisions about the candidate. ## How it works ### Start once a day on a schedule A **cron trigger** starts the agent daily. Every run gets a brand new **session**, a fresh cloud computer (sandbox) just for that run, so both the list of candidates ready to book and the panel's true free time are worked out again from how things stand today. Nothing is carried over from yesterday. ### Teach it how we schedule The agent brings our habits along as **skills** and **memory**: how to read an interview plan, how many time options to offer, how far ahead to search for free slots, and what a good proposal to a candidate sounds like. If we change how our loops are set up, we update that file, and tomorrow's proposals follow the new rules. ### Hook up Greenhouse, Google Calendar and email The agent uses scoped **connectors**, connections that Machine brokers on the server so the model never sees a raw token. Through them it can: - **Check Greenhouse**: see which candidates are flagged ready to schedule, and open each one's interview plan for the panel, the round and the length. - **Check Google Calendar**: look up when each interviewer on the plan is free, so any time it suggests is one the whole panel can make. - **Write drafts in email**: a time proposal for the candidate and one calendar invite per interviewer, held for the coordinator. ### Stop at the draft Drafting is where the agent's work ends. It doesn't email candidates, it doesn't send calendar invites, and it never makes or hints at a hiring decision: no rejections, no moving someone to the next stage, no offers. Credentials are stored encrypted in the Secrets Manager and only handed to the agents you grant them to. ### Give the coordinator a ready batch From then on, every morning brings a batch of candidates ready to book, already matched to when interviewers are actually free: a suggested time for the candidate and an invite drafted for each panelist. The coordinator looks it over, confirms the time and sends, or tweaks things first. Nothing reaches a candidate or lands on an interviewer's calendar unless they do. > **The pattern** > Every day a **cron** opens a fresh session with **connectors** to Greenhouse > for the interview plan and Google Calendar for the panel's free time. Our > scheduling habits live in **skills** and **memory**. The agent drafts the > candidate proposal and the invites, then stops. The coordinator confirms and > sends. ## Guardrails The agent shapes a candidate's next step in hiring, so the line between "suggested" and "confirmed" is the control that counts: - **Isolation.** Each run happens inside its own sealed sandbox. The drafted proposal and invites are the only things that come back out. - **Scoped secrets.** Greenhouse and Google Calendar credentials are stored encrypted in the Secrets Manager and only handed to the agents you grant them to. - **Human approval gate.** The agent sends neither the candidate proposal nor any calendar invite. Each draft waits for the coordinator to check, tweak and send. - **No hiring decisions, ever.** Rejecting a candidate, moving them forward and making an offer are all beyond its reach. It books the next conversation; it never decides whether that conversation should take place. - **Everything is code.** Scheduling habits and each system's permissions live as files in the repo. They're versioned and only change through a reviewed **change request**, not a dashboard toggle. ## The outcome - **Every day:** Candidates ready to book, paired with times the panel can really make - **Zero:** Invites or candidate emails that go out before a coordinator checks them - **3 systems:** Greenhouse, Google Calendar and email, handled by a single agent Booking a loop now begins with a proposal and a set of invites already drafted from the panel's real calendars, rather than a coordinator juggling five tabs in search of one time that suits everyone. Their morning starts with a quick review, not a hunt. Every send, and every hiring decision, still belongs to a person.