Deployed application (In real use)

RecruitTech ATS

Hiring falls apart in the tracking. Applications, CVs, statuses and interview notes spread across email and spreadsheets until nobody is sure where a candidate stands.

Status
Deployed application
Area
Recruitment & HR Automation, Custom AI Internal Tools
Workflow
6 steps · 3 failure paths
Stack

01 · Why it mattered

What the manual way was costing

  • Candidates slipped through the cracks between stages.
  • Recruiters spent their time on admin instead of people.

02 · System concept

What I set out to build

A proper app where each application creates a candidate record, the stage is always clear, and the recruiter can see what needs their action.

03 · Before / after

From manual steps to a system

Toggle between the manual process and the system. Click any step to see what it does, what tools it touches, and what happens if it goes wrong.

How it ran manually · depends on whoever is free

  1. 01Applications arrive through different channelsby hand
  2. 02Candidate details are copied into a spreadsheetby hand
  3. 03Status updates depend on someone remembering to change a cellby hand
  4. 04Recruiters dig through email to see what’s nextby hand

04 · Decision log

Why I built it this way

D-01A real app, not another sheet

Sheets were the problem, so I built it as a Next.js app on Supabase, with Airtable / Google Sheets still available where the team wanted them.

D-02Recruiter stays the decision maker

The app moves information around. Who gets hired is a human call, so recruiter action is a clear step in the pipeline.

05 · Reliability layer

What can go wrong, and who steps in

Where it happens
Step 02 Candidate record
What goes wrong
Same candidate applies twice
What the system does
Duplicate is caught so the recruiter isn’t working two records for one person.
Who handles it
The system handles it on its own

Human-in-the-loop points

  • Human in the loopRecruiter action
  • Human in the loopCandidate sitting in a stage with no action → recruiter

06 · Evidence

What exists today

  • Deployed on Netlify.

07 · What this demonstrates

What this demonstrates

Building a full application (not just a workflow) when the problem needs a proper interface and data model.

08 · Stack / integrations

What it’s built with

  • Next.jsApplication front end
  • SupabaseDatabase and auth
  • AirtableOptional team-facing views
  • NetlifyDeployment

Architecture · static view · 6 steps · 3 failure paths

    • → system handlesApplication is incomplete
    • → system handlesSame candidate applies twice
    • → recruiterCandidate sitting in a stage with no action

More systems

Keep reading

Completed workflow

AI Cold-Outreach Draft Helper

Each prospect row in a sheet gets qualified and a personalised draft written back next to it, ready for a human to review and send.

  1. Prospect row
  2. Qualification
  3. Personalised draft
  4. Written back to sheet
  5. Human reviews & sends
3 failure paths · 3 human handoffs
AI voice system / demo

Bright Smile Dental AI Voice Agent

A voice agent that answers inbound calls for a dental practice, answers treatment questions, handles appointment requests and escalates with a call summary.

  1. Inbound call
  2. Understand intent
  3. Patient / treatment info
  4. Appointment response
  5. Book or transfer
  6. +1 more
3 failure paths · 4 human handoffs

Similar workflow?

Got a process that looks something like this?

Tell me how it runs today and where it hurts. If it’s a good fit for automation I’ll tell you how I’d approach it. If it isn’t, I’ll tell you that too.

Tell me what you’re trying to automate