Skip to content
Datablare
Claude Code Education Admissions & enrollment

Test scores and scholarships

Enrolled students average 83.4 against 67.9 for all applicants, and scholarships lift yield from 62% to 89%.

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

1 · The brief

What Claude Code was asked

For the 2026 intake, show how test scores relate to admission and enrollment: average scores of applicants and enrolled students, applicants and enrolled by score band, admit rate by score band, average enrolled score by program, and whether scholarships make admitted students more likely to enroll.

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

Test scores and scholarships dashboard: Applicants and enrolled by score band, Yield with and without a scholarship, Admit rate by score band, Average enrolled score by program

Built from 4 read-only queries. Every figure on the dashboard was read from the database through Datablare; nothing was estimated or typed in.

Headline numbers (2026 intake):

  • Average applicant score: 67.9 (All applicants)
  • Average enrolled score: 83.4 (Enrolled students)
  • Enrolled on scholarship: 153 (20% of enrolled)
  • Scholarship yield: 88.9% (vs 61.5% without)

What stands out:

  • Applicants and enrolled by score band: Nobody below 70 is enrolled
  • Yield with and without a scholarship: Scholarships lift yield by 27 points
  • Admit rate by score band: 90+ scorers are admitted 89% of the time
  • Average enrolled score by program: B.Tech CS enrolls the highest scorers (97.1)

The data is a synthetic university admissions 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

4 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

    Average test score of applicants and of enrolled students, and scholarship holders among the enrolled, 2026 intake

    1 row · 52 ms

    SELECT round(avg(test_score), 1) AS avg_score_applicants,
           round(avg(test_score) FILTER (WHERE status = 'Enrolled'), 1) AS avg_score_enrolled,
           count(*) FILTER (WHERE status = 'Enrolled' AND scholarship) AS enrolled_with_scholarship,
           round(count(*) FILTER (WHERE status = 'Enrolled' AND scholarship)::numeric / count(*) FILTER (WHERE status = 'Enrolled'), 4) AS scholarship_share_of_enrolled
    FROM education.applicants
    WHERE intake = 2026
  2. Query 2

    Applicants, admit rate and enrollments by test score band, 2026 intake

    5 rows · 45 ms

    SELECT CASE WHEN test_score < 60 THEN '1. Under 60' WHEN test_score < 70 THEN '2. 60–69' WHEN test_score < 80 THEN '3. 70–79'
                WHEN test_score < 90 THEN '4. 80–89' ELSE '5. 90+' END AS score_band,
           count(*) AS applicants, count(*) FILTER (WHERE status = 'Enrolled') AS enrolled,
           round(avg(CASE WHEN status IN ('Admitted', 'Enrolled') THEN 1.0 ELSE 0 END), 4) AS admit_rate
    FROM education.applicants
    WHERE intake = 2026
    GROUP BY 1
    ORDER BY 1
  3. Query 3

    Average test score of enrolled students by program, 2026 intake

    8 rows · 48 ms

    SELECT p.name AS program, round(avg(a.test_score), 1) AS avg_enrolled_score, count(*) AS enrolled
    FROM education.applicants a
    JOIN education.programs p ON p.id = a.program_id
    WHERE a.intake = 2026 AND a.status = 'Enrolled'
    GROUP BY 1
    ORDER BY 2 DESC
  4. Query 4

    Yield of admitted students with and without a scholarship, 2026 intake

    2 rows · 49 ms

    SELECT CASE WHEN scholarship THEN 'With scholarship' ELSE 'Without scholarship' END AS offer,
           count(*) AS admitted, round(avg(CASE WHEN status = 'Enrolled' THEN 1.0 ELSE 0 END), 4) AS yield
    FROM education.applicants
    WHERE intake = 2026 AND status IN ('Admitted', 'Enrolled')
    GROUP BY 1
    ORDER BY 1
Tables read education.applicantseducation.programs

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
For the 2026 intake, show how test scores relate to admission and enrollment: average scores of applicants and enrolled students, applicants and enrolled by score band, admit rate by score band, average enrolled score by program, and whether scholarships make admitted students more likely to enroll.
Intent
Average test score of applicants and of enrolled students, and scholarship holders among the enrolled, 2026 intake
Result
4 queries, 16 rows, read-only

More use cases

All examples
  • Intake 2025 vs 2026 dashboard: Applicants by program, 2025 and 2026, Growth in applicants by program, Applicants by home state, 2025 and 2026
    Claude Code Education Executive overview

    Intake 2025 vs 2026

    Applicants up 20% to 4,098 and enrollments up to 765, led by B.Sc Data Sci (+100%).

    Updated Open

  • University admissions and enrollment dashboard: Applicants, admits and enrollments by program, Seats filled by program, Applications per month, Applicants by home state
    Claude Code Education Admissions & enrollment

    University admissions and enrollment

    4,098 applicants for the 2026 intake, a 28.5% admit rate and 65.5% yield, by program against seats.

    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]