Recruiting intake and scheduling
Every application enters a fair, review-led funnel: evidence is structured, recruiter attention is prioritized and promising conversations start sooner.
Case note
The implementation was treated as a small operating system: visibility first, ownership next, automation only after the workflow was clear.
Use case
Recruiting intake and scheduling
Every application enters a fair, review-led funnel: evidence is structured, recruiter attention is prioritized and promising conversations start sooner. A people-operations team hiring for recurring roles spent too much recruiter time opening CVs, rewriting experience summaries and creating interview tasks. The administrative first pass slowed candidate response and made role criteria less consistent than the team wanted.
Result: Recruiters begin with a structured, evidence-linked candidate view and spend their judgment on fit, nuance and conversation. Promising candidates move toward scheduling faster, while every decision remains human and criteria-led.
Workflow map
Recruiting workflow from application to scheduling task
The workflow improves intake quality without making hiring decisions automatically.
Main database: Supabase
The workflow uses Supabase as the source of truth: it stores each record, status, and key event so the team can see what happened, retry failures, and debug without searching every tool.
Tool icons
System rationale
Recruiting automation should prepare review, not replace judgment
The workflow speeds intake by structuring applications, but keeps selection decisions with recruiters and makes role criteria explicit.
Summaries reduce first-pass admin
Recruiters can see experience, skills and gaps before opening every CV.
Criteria must be visible
The system applies explicit role criteria so reviewers understand why labels were suggested.
No automatic rejection
Ambiguous or sensitive cases remain in human review, protecting quality and fairness.
Add-ons that fit on top
The starting point
A people-operations team hiring for recurring roles spent too much recruiter time opening CVs, rewriting experience summaries and creating interview tasks. The administrative first pass slowed candidate response and made role criteria less consistent than the team wanted.
The diagnosis used real volume, connected tools, decision points and exceptions. The question was not only what to automate, but what proof would show that the workflow had completed correctly. The operating proof mattered as much as the automation.
The implementation
Ductio connected applications to a candidate tracker, stored original files, summarized CVs against explicit role criteria, applied review labels and created scheduling tasks for recruiter-approved candidates. The workflow never rejects candidates automatically.
The implementation separated rules, free-text context, human decisions and external effects. That let the system improve daily work without turning every exception into a black box. AI as support inside the process, not as autopilot.
What was used
Tooling was chosen from the process outward, not from a pre-decided technical preference. Each piece needed a clear owner, a stable integration path and a simple way to inspect errors.
In practice, the build combined Application form, Google Drive, Supabase, OpenRouter, ATS/Calendar, Resend. The tools visible to the team stayed close to their daily work, while integration logic was documented and kept separate from sensitive commercial decisions.
The improvement showed up in daily work.
Rather than treating the result as a dashboard, the team felt it in three specific moments: less manual preparation, less context hunting, and fewer doubts about who needed to act.
Admin effort: Manual candidate intake moved from High to Reduced.
Summary coverage: Applications with structured summary moved from Manual to Automatic.
Scheduling speed: Qualified candidates queued moved from Slow to Consistent.
Before/after proof
What changed in the operation
Before
After
Visible artifacts
- Candidate summary
- Screening labels
- Role criteria
- Scheduling task
- Weekly hiring status
- No-auto-reject control log
Controls
- Human hiring decision
- No automatic rejection without review
- Role criteria explicit
- Sensitive/fairness review required
- Raw CV retained for recruiter review
What changed after launch
Recruiters begin with a structured, evidence-linked candidate view and spend their judgment on fit, nuance and conversation. Promising candidates move toward scheduling faster, while every decision remains human and criteria-led.
The result was not only saved minutes. The team gained a shared sequence for reviewing inputs, understanding context, deciding, acting and checking that the workflow had been recorded. 60% admin reduction
The workflow in one line
How it was built
Applications and attachments are stored in Supabase/Drive, OpenRouter creates role-fit summaries, Python/FastAPI applies explicit labels and routing, ATS/calendar tasks are prepared for recruiter review and Resend handles candidate/recruiter notifications when approved.
The stack was pragmatic: Application form, Google Drive, Supabase, OpenRouter, ATS/Calendar, Resend. Tools were chosen for ownership, integration and maintainability, not for theater. The result is a system the team can understand and operate.
What was delivered
- Application intake
- CV source retention
- Role-fit summary
- Screening labels
- Recruiter review queue
- Scheduling task
- Weekly hiring status
- Recruiters reviewed structured summaries before opening every file.
- Interview scheduling became more consistent for qualified candidates.
- Weekly hiring status was available without manual spreadsheet cleanup.
- No candidate was automatically rejected by the workflow.
- Role criteria became explicit instead of hidden in recruiter memory.
- Sensitive or ambiguous profiles stayed in human review.
- Candidates receive a more consistent and responsive first experience without automating rejection.
