Get started

How we coordinate interview loops

The interview-scheduling agent we run on Kortix — daily, it finds candidates ready to schedule in Greenhouse, checks interviewer availability on Google Calendar, and drafts a slot proposal to the candidate and the calendar invites for a coordinator to confirm.

Written by
The OpenChatly Team
Published
June 20, 2026
Reading time
7 min read
Topics
HR, Case Study, Enterprise

Once a candidate clears a screen, scheduling the next round becomes its own small project: read the interview plan to see who's on the panel, find a time when every one of those interviewers is actually free, propose it to the candidate, and get invites onto everyone's calendar before the slot goes stale. None of it is hard, but it's tedious across several interviewers and several candidates at once, and every day it sits undone is a day the loop stalls.

We run an interview-scheduling agent on Kortix that does the coordination every day. For every candidate marked ready to schedule in Greenhouse, it reads the interview plan, checks the panel's availability on Google Calendar, and drafts a slot proposal to the candidate plus the calendar invites for each interviewer. It never sends anything and never touches a hiring decision — a coordinator reviews every proposal and invite before it goes out. This is how we keep our own interview loops moving.

Team
Kortix
Runs on
Daily cron
Connected systems
Greenhouse · Google Calendar · Email
Mode
Proposes and drafts only · coordinator confirms and sends

The problem

Scheduling an interview loop means combining two things that live in different systems: the interview plan — who's on the panel, how many rounds, how long each one runs — sits in Greenhouse, while whether those people are actually free sits in their calendars. Checking both by hand, for every candidate who clears a screen, is the kind of coordination work that's easy to fall behind on the moment more than one requisition is open at once.

The usual workarounds don't hold up. A shared scheduling link only works if every interviewer keeps it current, and it says nothing about who the panel actually is for this candidate. A coordinator juggling several calendar tabs and a Greenhouse tab in parallel can do it, but it doesn't scale past a handful of loops, and a slipped invite reads as disorganized to a candidate who's interviewing elsewhere too.

What we built

On Kortix, a daily cron triggers an agent. It spawns a fresh session (a cloud sandbox) that reads every candidate marked ready to schedule in Greenhouse, pulls that candidate's interview plan to see who's on the panel, checks each panelist's Google Calendar for open slots, and drafts a slot proposal for the candidate along with a calendar invite per interviewer. Every draft lands with the coordinator; the agent sends nothing and decides nothing about the candidate.

How it works

1

Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it. The agent writes the agent file, the interview-scheduling skill and the daily trigger, and opens a change request for you to review. Prefer clicks? Choose Use this template instead.

Setup prompt

Set up a daily interview scheduling agent in this workspace.

  1. Create the agent agents/interview-scheduler.md. Its job is to draft interview slot proposals and calendar invites for the coordinator to review. It may use the Greenhouse and Google Calendar connectors and the coordinator review email channel.

  2. Create the skill skills/interview-scheduling/SKILL.md with these rules:

    • Read candidates in the Onsite, Ready to Schedule stage in Greenhouse who have no drafted proposal yet.
    • The panel, round and duration come only from the candidate's interview plan. Never add or drop an interviewer.
    • Propose 2 to 3 slots in the next few business days, and only slots where every panelist is free on their primary calendar.
    • Draft one proposal email to the candidate and one invite per interviewer, and put the batch in the coordinator review inbox.
    • Never send a proposal, never create a calendar event, and never change a candidate's stage or make a hiring decision.
  3. Add a cron trigger interview-scheduling-sweep to kortix.yaml. It runs the interview-scheduler agent every day at 08:00 with the prompt "Load the interview-scheduling skill and run one complete scheduling sweep."

  4. Tell me which of these connectors are not connected yet.

  5. Open a change request with all of it. Do not merge it.

2

Connect your tools

Open Connectors in your workspace and connect Greenhouse and Google Calendar, then connect the coordinator review inbox under Channels. Credentials are brokered server-side and never enter the agent's machine.

Greenhouse

Reads candidates ready to schedule and their interview plans.

Or useLeverAshby
Required
Google Calendar

Checks panel availability and drafts each interviewer's invite.

Or useOutlook
Required
Gmail

Delivers drafted slot proposals to the coordinator for review.

Or useSlack
Required
3

Run it once with this prompt

Merge the change request, then start a session with the interview-scheduler agent and send this prompt. Check the proposed slots against the panel's calendars before you let the schedule take over.

Prompt

Run one interview scheduling sweep.

  1. Find candidates in the Onsite, Ready to Schedule stage in Greenhouse with no drafted proposal.
  2. Read each candidate's interview plan: panel, round and duration.
  3. Find 2 to 3 slots where every panelist is free on their primary calendar.
  4. Draft a proposal email to the candidate and an invite for each interviewer.
  5. Put the batch in the coordinator review inbox. Do not send anything, create any event or change any stage.
4

Let the daily schedule take over

The change request added this trigger to kortix.yaml. From now on the agent runs every day at 08:00, each run in a new session on its own cloud computer. To change the time, edit the cron line, or open Triggers in the workspace.

kortix.yaml
triggers:- slug: interview-scheduling-sweep  name: Daily interview-scheduling sweep  on:    cron: "0 0 8 * * *"  run:    agent: interview-scheduler    prompt: Load the interview-scheduling skill and run one complete scheduling sweep.
5

Hold every proposal and invite for the coordinator

The agent has no send action and no action that creates a live calendar event. Every proposal and invite waits in the coordinator review inbox. The coordinator confirms the time with the candidate and sends everything. The agent never rejects a candidate, moves a stage or drafts an offer.

6

Read the morning batch

Each run ends with one batch in the coordinator review inbox. This is what a run looks like in the session:

Daily interview-scheduling sweep · 08:00
Load the interview-scheduling skill and run one complete scheduling sweep.
Worked for 2m 19s
greenhouse · list candidatesgreenhouse · get interview plan × 4google_calendar · find free busy × 4email · send → coordinator review

Found 4 candidates ready to schedule. Drafted proposals with 3 open slots each for 3 of them. 1 panel has no common free slot in the next 5 business days, so that candidate is listed for the coordinator to handle.

Illustrative example. Your counts depend on your pipeline.

The pattern

A daily cron spawns a fresh session with connectors into Greenhouse for the interview plan and Google Calendar for panel availability. The scheduling conventions live as skills and memory. The agent drafts the candidate proposal and the invites and stops — the coordinator confirms and sends.

Make it do more

Once it works, paste any of these into the same session.

Suggest a backup panelist

When a panel has no common free slot, name the interviewer who blocks the most slots so the coordinator can ask for a swap.

Respect time zones

Show each proposed slot in the candidate's time zone from Greenhouse, and in the interviewers' time zone in the invite drafts.

Weekly pipeline note

Every Friday, send the coordinator a list of candidates who have waited more than 5 business days for a confirmed slot.

Guardrails

The agent touches a candidate's next step in the hiring process, so the boundary between "proposed" and "confirmed" is the control that matters:

  • Isolation. Every run happens in its own isolated sandbox. Only the drafted proposal and invites are written back out.
  • Scoped secrets. The Greenhouse and Google Calendar credentials are encrypted in the Secrets Manager and injected into the sandbox at runtime, scoped to the agents you grant them to.
  • Human approval gate. The agent never sends the candidate proposal and never sends a calendar invite. Every draft is held for the coordinator to review, adjust, and send.
  • No hiring decisions, ever. The agent cannot reject a candidate, advance a stage, or send an offer. It schedules the next conversation; it never decides whether that conversation happens.
  • Everything is code. The scheduling conventions and per-system permissions are files in the repo, versioned and changed through a reviewed change request rather than a dashboard setting.

The outcome

Ready-to-schedule candidates matched to real panel availability
Every day
Invites or candidate emails sent without coordinator review
Zero
Greenhouse, Google Calendar, and email in one agent
3 systems

Scheduling an interview loop now starts with a proposal and a set of invites already drafted against the panel's real calendars, instead of a coordinator opening five tabs to find one time that works. The coordinator's day starts with a review instead of a hunt, and every send and every hiring call still stays with a person.

On this page

  • The problem
  • What we built
  • How it works
  • Make it do more
  • Guardrails
  • The outcome

Run this yourself

Install this exact setup — agent, connectors, schedule, and guardrails — in a guided flow.

More use cases.

  • How we handle GDPR data-subject requests on a deadline

    Legal·July 11, 2026

  • OpenChatly

    How we keep our docs in sync with the code

    Documentation·July 5, 2026

  • OpenChatly

    How we QA every pull request automatically

    QA·July 5, 2026

Own your AI.Start today, in our cloud.

Start for free

OpenChatly is the AI workspace for everything. One person directing, agents executing, from goal to finished work.

©2026 OpenChatly AI.沪ICP备2025124785号-5

Resource guide

  • Product overview
  • Skills marketplace

Terms of service

  • User agreement
  • Privacy policy

Contact us