Skip to content
Datablare
Claude Code Human resources People & hiring

Recruitment funnel and time to hire

9,000 applications and 256 hires, 38 days to hire on average, the funnel stage by stage and which sources convert.

Data
Synthetic recruiting demo data (PostgreSQL)
Asked in
Claude Code
Updated
Try this on your data

1 · The brief

What Claude Code was asked

Create a recruiting dashboard: applications, hires, average days to hire and open requisitions, the funnel from application to hire, which sources produce hires, applications per month, and time to hire by department.

Given exactly like this. Claude Code asked Datablare which tables it could read, wrote the SQL itself, ran each query through Datablare and built the dashboard from what came back.

2 · The dashboard

The dashboard Claude Code built

Recruitment funnel and time to hire dashboard: Hiring funnel, Applications per month, Hire rate by source, Average days to hire by department

Built from 5 read-only queries. Every figure on the dashboard was read from the database through Datablare; nothing was estimated or typed in.

Headline numbers (June 2025 – October 2026):

  • Applications: 9,000 (All requisitions)
  • Hires: 256 (2.8% of applications)
  • Days to hire: 38 (Average, application to hire)
  • Open requisitions: 29 (Not yet filled)

What stands out:

  • Hiring funnel: 24% of applicants reach an interview; 39% of offers are accepted
  • Applications per month: About 547 applications a month
  • Hire rate by source: Referral converts best: 7.6% of applicants hired
  • Average days to hire by department: Marketing takes longest at 41 days

The data is a synthetic recruiting dataset made for this example, so the numbers describe no real company. The queries, the dashboard and the audit entries are real: Claude reached the database only through Datablare, read-only, and every query is on record with the question it served.

3 · What Datablare ran

5 read-only queries, nothing changed

Each query below is copied from the audit log of this run. Datablare checked that it only reads, ran it read-only, and gave only the rows to Claude Code; it never stores them.

  1. Query 1

    Applications, hires, average days to hire and open requisitions

    1 row · 51 ms

    SELECT count(*) AS applications, count(*) FILTER (WHERE hired) AS hires,
           round(avg(hired_at - applied_at) FILTER (WHERE hired), 1) AS avg_days_to_hire,
           (SELECT count(*) FROM hr.requisitions WHERE closed IS NULL) AS open_requisitions
    FROM hr.applications
  2. Query 2

    How many applications reached each stage of the funnel

    1 row · 53 ms

    SELECT count(*) AS applied,
           count(*) FILTER (WHERE furthest_stage IN ('Screen', 'Interview', 'Offer', 'Hired')) AS screened,
           count(*) FILTER (WHERE furthest_stage IN ('Interview', 'Offer', 'Hired')) AS interviewed,
           count(*) FILTER (WHERE furthest_stage IN ('Offer', 'Hired')) AS offered,
           count(*) FILTER (WHERE furthest_stage = 'Hired') AS hired
    FROM hr.applications
  3. Query 3

    Applications, hires and hire rate by source

    5 rows · 52 ms

    SELECT source, count(*) AS applications, count(*) FILTER (WHERE hired) AS hires,
           round(avg(CASE WHEN hired THEN 1.0 ELSE 0 END), 4) AS hire_rate
    FROM hr.applications
    GROUP BY 1
    ORDER BY 4 DESC
  4. Query 4

    Applications received per full month, June 2025 to September 2026

    16 rows · 44 ms

    SELECT to_char(date_trunc('month', applied_at), 'YYYY-MM') AS month, count(*) AS applications
    FROM hr.applications
    WHERE applied_at < DATE '2026-10-01'
    GROUP BY 1
    ORDER BY 1
  5. Query 5

    Hires and average days to hire by department

    6 rows · 56 ms

    SELECT r.department, count(*) FILTER (WHERE a.hired) AS hires,
           round(avg(a.hired_at - a.applied_at) FILTER (WHERE a.hired), 1) AS avg_days_to_hire
    FROM hr.applications a
    JOIN hr.requisitions r ON r.id = a.requisition_id
    GROUP BY 1
    ORDER BY 3 DESC
Tables read hr.applicationshr.requisitions

4 · The audit entry

Who asked what, on record

Every query is recorded with the person who asked, the question in their words and why the agent ran it. Admins see this in the audit log; nothing reaches the database without it.

How the audit log works

query_data_source

via Claude Code

Allowed
Who
The person signed in (hidden on this public page)
Question
Create a recruiting dashboard: applications, hires, average days to hire and open requisitions, the funnel from application to hire, which sources produce hires, applications per month, and time to hire by department.
Intent
Applications, hires, average days to hire and open requisitions
Result
5 queries, 29 rows, read-only

More use cases

All examples
  • Candidate conversion by source dashboard: Interview, offer and hire rates by source, Applications by source, Hires per month by source
    Claude Code Human resources People & hiring

    Candidate conversion by source

    Referrals bring 38% of hires and convert at 7.6%, against 1.1% for the weakest source, Agency; 39% of offers are accepted.

    Updated Open

  • Requisitions and time to fill dashboard: Filled and open requisitions by department, Average days to fill by department, Requisitions opened per month, Applications per requisition
    Claude Code Human resources People & hiring

    Requisitions and time to fill

    140 requisitions opened, 111 filled in 54 days on average, 29 still open; Sales takes longest.

    Updated Open

  • E-commerce sales and retention dashboard dashboard: Monthly revenue, Revenue by category, 2026, Lifetime revenue per customer, by channel, Orders per month
    Claude Code E-commerce Executive overview

    E-commerce sales and retention dashboard

    ₹5.21M revenue from 11,897 orders this year, a 57.9% repeat-customer rate, and which channels bring the customers who spend most.

    Updated Open

Build this on your own data.

Connect your database, choose the tables Claude may read, and give it the same brief. Claude is connected in about two minutes.

30 minutes with the founder. Or WhatsApp / [email protected]