Course Management

Course overview

Total enrollments: 1717
Project submissions: 419
Project completion rate: 22.1%
Average total score: 12.2
Overall completion rate: 24.0%

Project outcomes

Score to pass: 11
Passed: 205
Failed: 214
Median project score: 19

Homework statistics

Median time and score by homework. Hover values on desktop for interquartile ranges.

Homework	Submissions	Completion	Lecture time	Homework time	Total time	Median score
Homework 1: Agentic RAG	628	36.6%	5h	3h	8h	6
Homework 2: Vector Search	505	29.4%	5h	2h	7.8h	6
Homework 3: Orchestration	434	25.3%	3h	1.5h	5h	6
Homework 4: Evaluation	374	21.8%	4h	3h	8h	6
Homework 5: Monitoring	315	18.3%	4h	2.2h	7h	6
dlt Workshop	213	12.4%	3h	2h	6h	3

Homework 1: Agentic RAG

Submissions: 628
Completion: 36.6%
Median score: 6
Lecture time: 5h
Homework time: 3h
Total time: 8h

Homework 2: Vector Search

Submissions: 505
Completion: 29.4%
Median score: 6
Lecture time: 5h
Homework time: 2h
Total time: 7.8h

Homework 3: Orchestration

Submissions: 434
Completion: 25.3%
Median score: 6
Lecture time: 3h
Homework time: 1.5h
Total time: 5h

Homework 4: Evaluation

Submissions: 374
Completion: 21.8%
Median score: 6
Lecture time: 4h
Homework time: 3h
Total time: 8h

Homework 5: Monitoring

Submissions: 315
Completion: 18.3%
Median score: 6
Lecture time: 4h
Homework time: 2.2h
Total time: 7h

dlt Workshop

Submissions: 213
Completion: 12.4%
Median score: 3
Lecture time: 3h
Homework time: 2h
Total time: 6h

Assignment difficulty

Ranked by lowest median question score relative to the maximum achievable. Normalizing by question count makes homeworks of different lengths comparable; a lower percentage indicates a harder assignment.

Rank	Homework	Median score	Score %	Completion
1	Homework 1: Agentic RAG	6 / 6	100.0%	36.6%
2	Homework 2: Vector Search	6 / 6	100.0%	29.4%
3	Homework 3: Orchestration	6 / 6	100.0%	25.3%
4	Homework 4: Evaluation	6 / 6	100.0%	21.8%
5	Homework 5: Monitoring	6 / 6	100.0%	18.3%
6	dlt Workshop	3 / 3	100.0%	12.4%

Question difficulty

Share of submitted answers that were correct, per question. A lower percentage points to a harder or more confusing question. Participation-only questions are excluded.

Homework	Question	Correct	Answers	% correct
Homework 1: Agentic RAG	How many lesson pages	608	628	96.8%
	Indexing and searching	597	628	95.1%
	RAG	578	628	92.0%
	Chunking	598	628	95.2%
	RAG with chunking	536	628	85.4%
	Turning it into an agent	552	628	87.9%
Homework 2: Vector Search	Embedding a query	492	505	97.4%
	Cosine similarity	484	505	95.8%
	Chunking and search by hand	484	505	95.8%
	Vector search with minsearch	477	505	94.5%
	Text search vs vector search	452	505	89.5%
	Hybrid search	447	505	88.5%
Homework 3: Orchestration	After trying the same prompt in ChatGPT vs Kestra AI Copilot, what is the primary reason AI Copilot generates better Kestra flows?	428	434	98.6%
	The non-RAG response about Kestra 1.1 features is best described as:	419	434	96.5%
	What is the approximate output token count for multilingual_agent when running with summary_length = short?	397	434	91.5%
	With summary_length = long, roughly how many times more output tokens does multilingual_agent use compared to the short summary?	387	434	89.2%
	After changing english_brevity to ask for 3 sentences instead of 1, how does the output token count compare to the original 1-sentence version?	329	434	75.8%
	For production workflows requiring deterministic, repeatable results with strict compliance requirements, which approach is most appropriate?	410	434	94.5%
Homework 4: Evaluation	When generating questions for the first 3 lesson pages, what is the average number of input tokens across these 3 calls?	354	374	94.7%
	After running text_search for the first ground truth question, what is the filename of the first result?	321	374	85.8%
	After running vector_search for the same question, what is the filename of the first result?	331	374	88.5%
	After evaluating text_search on the ground truth, what is the Hit Rate?	336	374	89.8%
	After evaluating vector_search on the ground truth, what is the MRR?	304	374	81.3%
	When evaluating hybrid_search for k values 1, 50, 100, and 200, which k gives the best MRR?	300	374	80.2%
Homework 5: Monitoring	How many spans does the trace produce?	309	315	98.1%
	How many input tokens do we see for the LLM call?	301	315	95.6%
	For a typical query, roughly how long does the LLM call take?	295	315	93.7%
	Which span names appear in the spans table?	307	315	97.5%
	Excluding the rag span, which span type takes the most total time?	311	315	98.7%
	How much do the input tokens vary across 4 runs of the same query?	289	315	91.7%
dlt Workshop	For the query "How do I run Ollama locally?", how many spans does a single agent run produce?	186	213	87.3%
	How many tables did dlt create in the agent_traces schema?	180	213	84.5%
	What is the range of total input token usage for the agent run from Q1?	191	213	89.7%

Submission timing

When homework submissions arrive relative to the deadline, across all assignments.

A week or more early: 300 (12.2%)
3-7 days early: 392 (15.9%)
1-3 days early: 412 (16.7%)
Final day: 934 (37.8%)
After the deadline: 431 (17.5%)

Engagement over time

Homework submissions per week, across all assignments. Bars are scaled to the busiest week.

Jun 01, 2026: 1
Jun 08, 2026: 61
Jun 15, 2026: 231
Jun 22, 2026: 569
Jun 29, 2026: 519
Jul 06, 2026: 315
Jul 13, 2026: 405
Jul 20, 2026: 296
Jul 27, 2026: 54
Aug 03, 2026: 12
Aug 10, 2026: 6

LLM Zoomcamp 2026 Dashboard