Skip to content
Datablare
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.

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

1 · The brief

What Claude Code was asked

Which sourcing channels are worth it? For each source show applications, the share that reach interview and offer, the hire rate and offer acceptance, plus hires per month and the share of hires from each source.

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

Candidate conversion by source dashboard: Interview, offer and hire rates by source, Applications by source, Hires per month by source

Built from 3 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 – September 2026):

  • Interview rate: 23.9% (Applicants reaching interview)
  • Offer rate: 7.2% (Applicants receiving an offer)
  • Offer acceptance: 39.3% (Offers that became hires)
  • Hires from referrals: 37.9% (Share of all hires)

What stands out:

  • Interview, offer and hire rates by source: Referral leads at every stage
  • Applications by source: Most applications come from Job boards
  • Hires per month by source: Referrals are a steady share of hires

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

3 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

    Interview rate, offer rate, offer acceptance and referral share of hires

    1 row · 50 ms

    SELECT round(avg(CASE WHEN furthest_stage IN ('Interview', 'Offer', 'Hired') THEN 1.0 ELSE 0 END), 4) AS interview_rate,
           round(avg(CASE WHEN furthest_stage IN ('Offer', 'Hired') THEN 1.0 ELSE 0 END), 4) AS offer_rate,
           round(count(*) FILTER (WHERE hired)::numeric / count(*) FILTER (WHERE furthest_stage IN ('Offer', 'Hired')), 4) AS offer_acceptance,
           round(count(*) FILTER (WHERE hired AND source = 'Referral')::numeric / count(*) FILTER (WHERE hired), 4) AS referral_share_of_hires
    FROM hr.applications
  2. Query 2

    Interview, offer and hire rates by source

    5 rows · 73 ms

    SELECT source, count(*) AS applications,
           round(avg(CASE WHEN furthest_stage IN ('Interview', 'Offer', 'Hired') THEN 1.0 ELSE 0 END), 4) AS interview_rate,
           round(avg(CASE WHEN furthest_stage IN ('Offer', 'Hired') THEN 1.0 ELSE 0 END), 4) AS offer_rate,
           round(avg(CASE WHEN hired THEN 1.0 ELSE 0 END), 4) AS hire_rate
    FROM hr.applications
    GROUP BY 1
    ORDER BY 5 DESC
  3. Query 3

    Hires per month by source

    65 rows · 46 ms

    SELECT to_char(date_trunc('month', hired_at), 'YYYY-MM') AS month, source, count(*) AS hires
    FROM hr.applications
    WHERE hired AND hired_at < DATE '2026-10-01'
    GROUP BY 1, 2
    ORDER BY 1, 2
Tables read hr.applications

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
Which sourcing channels are worth it? For each source show applications, the share that reach interview and offer, the hire rate and offer acceptance, plus hires per month and the share of hires from each source.
Intent
Interview rate, offer rate, offer acceptance and referral share of hires
Result
3 queries, 71 rows, read-only

More use cases

All examples
  • 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

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

    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]