AI Engineering Buildcamp: from RAG to Agents Cohort 3

Homework 4: Testing Statistics

Distribution of scores and reported study time for this homework.

Submissions

Median total score

Average total score

Score distribution

All values are points.

Metric	Min	Q1	Median	Average	Q3	Max
Questions score	5	5.8	7.0	6.4	7.0	7
Learning in public score	-	0.0	0.0	0.1	0.0	1
Total score	5	6.0	7.0	6.5	7.0	7

Questions score

Min: 5
Median: 7.0
Max: 7
Q1: 5.8
Avg: 6.4
Q3: 7.0

Learning in public score

Min: -
Median: 0.0
Max: 1
Q1: 0.0
Avg: 0.1
Q3: 0.0

Total score

Min: 5
Median: 7.0
Max: 7
Q1: 6.0
Avg: 6.5
Q3: 7.0

Time distribution

All values are hours reported by students.

Metric	Min	Q1	Median	Average	Q3	Max
Lectures	1.0	3.0	6.0	4.8	6.0	8.0
Homework	1.0	2.0	4.0	3.4	5.0	5.0

Lectures

Min: 1.0
Median: 6.0
Max: 8.0
Q1: 3.0
Avg: 4.8
Q3: 6.0

Homework

Min: 1.0
Median: 4.0
Max: 5.0
Q1: 2.0
Avg: 3.4
Q3: 5.0

Question breakdown

Correctness and answer distribution per question.

1. Set Up DuckDB

12 / 12 correct (100.0%)

1 1,964,624 0 (0.0%)

2 2,964,624 12 (100.0%)

3 3,964,624 0 (0.0%)

4 4,964,624 0 (0.0%)

2. Create the Agent

12 / 12 correct (100.0%)

1 2.78 0 (0.0%)

2 3.78 12 (100.0%)

3 4.78 0 (0.0%)

4 5.78 0 (0.0%)

3. Write Your First Test

12 / 12 correct (100.0%)

1 2,413 0 (0.0%)

2 12,413 0 (0.0%)

3 22,413 12 (100.0%)

4 32,413 0 (0.0%)

4. Testing Tool Calls

11 / 12 correct (91.7%)

1 get_schema 1 (8.3%)

2 run_sql 11 (91.7%)

3 describe_table 0 (0.0%)

4 list_columns 0 (0.0%)

5. LLM Judge Test

11 / 12 correct (91.7%)

1 4 0 (0.0%)

2 5 11 (91.7%)

3 17 1 (8.3%)

4 22 0 (0.0%)

6. Writing More Tests

11 / 12 correct (91.7%)

1 tip_amount 0 (0.0%)

2 fare_amount 0 (0.0%)

3 passenger_count 11 (91.7%)

4 trip_distance 0 (0.0%)

7. Cost Tracking (Bonus)

8 / 12 correct (66.7%)

1 Less than $0.05 8 (66.7%)

2 $0.05 - $0.20 0 (0.0%)

3 $0.20 - $1.00 0 (0.0%)

4 More than $1.00 0 (0.0%)

Calculated: 11 June 2026, 20:10