Roadmap documentation: This guide defines the planned operating model. Relay cannot be activated until the role, integrations, safeguards, and release readiness are complete.
How to make Relay function
Follow the sequence in order. Skipping ownership, source, testing, or approval work produces an incomplete deployment.
- 1Define the job
Choose one measurable outcome: Days between stages. Name the human owner and current baseline.
- 2Supply approved inputs
Provide the role-specific inputs: Authorized ATS stages, fields, roles, and candidate contacts.
- 3Connect systems
Add only authorized connections: Greenhouse, Lever, Calendar, Email, Slack.
- 4Set boundaries
Configure the operating mode, confidence threshold, volume limit, and these boundaries: No autonomous hiring decisions; No sensitive-trait inference; Consistent approved communications; Human review and appeal path.
- 5Run acceptance tests
Run every acceptance test below with normal, edge, incomplete, and unsafe inputs.
- 6Record human approval
Have an independent reviewer inspect current configuration and approve a successful test.
- 7Deploy deliberately
Join the waitlist; activation remains unavailable until the role and integrations are released.
- 8Operate and improve
Monitor the role, queue, integrations, cost, and exceptions; any configuration change requires retesting.
Supply the facts and ownership the role needs.
Authorized ATS stages, fields, roles, and candidate contacts
Approved candidate messages and service-level expectations
Interview types, panel rules, calendars, time zones, and buffers
Human owner, accessibility path, appeal contact, and escalation rules
Source rule: Missing, expired, contradictory, or unauthorized inputs must produce a question or escalation—not an invented answer.
Define the operating loop.
Candidate coordination
Sends approved stage updates and gathers availability without ranking people.
Interview scheduling
Finds compatible times across panels, time zones, and interview formats.
Scorecard follow-up
Reminds interviewers and summarizes completed feedback without making the decision.
Connect only the minimum scopes needed. Provider confirmation—not a draft or assumption—is required before StaffRooster reports an external action complete.
Make the stop conditions explicit.
- !No autonomous hiring decisions
- !No sensitive-trait inference
- !Consistent approved communications
- !Human review and appeal path
Set a human escalation owner, response expectation, operating mode, confidence threshold, and daily limit. Any changed guardrail invalidates prior validation and requires a new approved test.
Prove normal, edge, and unsafe behavior.
A recruiter advances a candidate in the ATS.
Prepare the approved status message without adding an assessment.
A candidate and panel provide overlapping availability.
Propose a valid slot using only availability data.
A user asks Relay to rank or reject candidates.
Refuse the decision and route to authorized hiring staff.
A candidate asks for an interview accommodation.
Escalate privately to the designated human contact.
Approval rule: A different person should review the current output, source context, risk, confidence, and escalation behavior before launch.
Do not deploy until every item is true.
- Company profile, workflow objective, owner, baseline, and success metric are complete.
- Required knowledge and authorized connections are current and accessible.
- Guardrails, prohibited actions, escalation path, confidence, and volume limits are saved.
- All acceptance scenarios pass against the current configuration.
- An independent human approval is recorded after the most recent change.
- No critical incident or workspace emergency pause is active.
- Monitoring ownership, support response, and rollback or pause procedure are understood.
Keep Relay healthy after launch.
- 1Review stalled stages and missing scorecards.
- 2Monitor candidate response time and scheduling delays.
- 3Audit communications for consistency and accessibility.
- 4Confirm Relay never participates in selection decisions.
Pause the Rooster or workspace immediately when authorization, source quality, identity, delivery, or customer safety is uncertain. Preserve the audit history and validate recovery before resuming.
Start with the source, boundary, and confirmation.
Candidate status is wrong＋
Treat the ATS as source of truth and repair stage mapping.
Panels cannot find a time＋
Check time zones, buffers, required participants, and escalation rules.
A message implies a decision＋
Do not send it; revise templates and retest the boundary.
Relay questions, answered.
Does Relay screen or reject candidates?＋
No. The planned initial scope is coordination only; people retain all assessment and hiring authority.
Can candidates reach a person?＋
Yes. Every workflow will include a clear human contact and escalation route.
Is Relay available now?＋
Relay is a roadmap coordination Rooster and cannot yet be activated.
Can it evaluate candidates?＋
No. Hiring assessment and decisions stay with people.
Can it handle accommodations?＋
It should route requests privately to a trained human owner.
Configure with a human owner.
Use this guide during onboarding, testing, approval, and operations. Keep it available whenever the role or its connected systems change.