Homework 1/2: RAG
- Submissions
- 19
- Completion
- 48.7%
- Median score
- 5
- Lecture time
- 5h
- Homework time
- 2.5h
- Total time
- 7h
AI Engineering Buildcamp: from RAG to Agents Cohort 3
Course-level participation, homework, and project 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 1/2: RAG | 19 | 48.7% | 5h | 2.5h | 7h | 5 |
| Capstone Preparation 1/2 | 18 | 46.2% | 3h | 2.5h | 7h | 6 |
| Homework 3: AI Agents | 15 | 38.5% | 5h | 2h | 6.8h | 6 |
| Capstone Preparation 3 | 9 | 23.1% | 4.5h | 3h | 6h | 6 |
| Homework 4: Testing | 12 | 30.8% | 6h | 4h | 8h | 7 |
| Capstone Preparation 4 | 7 | 17.9% | - | 3h | - | - |
| Homework 5: Monitoring | 8 | 20.5% | 2h | 3.2h | 6h | 7 |
| Capstone Preparation 5 | 5 | 12.8% | - | - | - | - |
| Homework 6: Evaluations | 7 | 17.9% | - | 2h | - | 8 |
| Capstone Preparation 6 | 3 | 7.7% | - | - | - | - |
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 | Capstone Preparation 4 | 0 / 6 | 0.0% | 17.9% |
| 2 | Capstone Preparation 5 | 0 / 6 | 0.0% | 12.8% |
| 3 | Capstone Preparation 6 | 0 / 6 | 0.0% | 7.7% |
| 4 | Homework 1/2: RAG | 5 / 6 | 83.3% | 48.7% |
| 5 | Homework 5: Monitoring | 7 / 7 | 92.9% | 20.5% |
| 6 | Capstone Preparation 1/2 | 6 / 6 | 100.0% | 46.2% |
| 7 | Homework 3: AI Agents | 6 / 6 | 100.0% | 38.5% |
| 8 | Homework 4: Testing | 7 / 7 | 100.0% | 30.8% |
| 9 | Capstone Preparation 3 | 6 / 6 | 100.0% | 23.1% |
| 10 | Homework 6: Evaluations | 8 / 8 | 100.0% | 17.9% |
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 1/2: RAG | How many lines are in the extracted content from the "Think Python" book after converting to markdown? | 17 | 19 | 89.5% |
| How many chunks are produced for the "Think Python" book with size=100 and step=50? | 19 | 19 | 100.0% | |
| How many documents (chunks) did you index in total from all books? | 7 | 19 | 36.8% | |
| When searching for "python function definition", which book did the top result come from? | 19 | 19 | 100.0% | |
| How many input tokens did we use for the RAG query "python function definition"? | 18 | 19 | 94.7% | |
| How many MORE input tokens does the structured output version use compared to the unstructured version? | 18 | 19 | 94.7% | |
| Homework 3: AI Agents | How many total results did the Wikipedia search return for the query "capybara"? | 15 | 15 | 100.0% |
| How many of the search results contain the word "capybara" (case-insensitive) in their title? | 15 | 15 | 100.0% | |
| How many characters are in the Capybara page content? | 15 | 15 | 100.0% | |
| Homework 4: Testing | Set Up DuckDB | 12 | 12 | 100.0% |
| Create the Agent | 12 | 12 | 100.0% | |
| Write Your First Test | 12 | 12 | 100.0% | |
| Testing Tool Calls | 11 | 12 | 91.7% | |
| LLM Judge Test | 11 | 12 | 91.7% | |
| Writing More Tests | 11 | 12 | 91.7% | |
| Cost Tracking (Bonus) | 8 | 12 | 66.7% | |
| Capstone Preparation 4 | Think About Test Scenarios | 0 | 7 | 0.0% |
| Implement a Test | 0 | 7 | 0.0% | |
| Add an LLM Judge Test | 0 | 7 | 0.0% | |
| Homework 5: Monitoring | Create and Run the Agent | 8 | 8 | 100.0% |
| Set Up Monitoring | 6 | 8 | 75.0% | |
| Play a Full Session | 8 | 8 | 100.0% | |
| Grouping Traces | 5 | 8 | 62.5% | |
| Reconstruct Runs and Calculate Costs | 8 | 8 | 100.0% | |
| Feedback Tracking | 7 | 8 | 87.5% | |
| Capstone Preparation 5 | Monitoring Platform Setup | 0 | 5 | 0.0% |
| Interaction Data Collection Plan | 0 | 5 | 0.0% | |
| Running and Collecting Data | 0 | 5 | 0.0% | |
| Homework 6: Evaluations | Did the agent hallucinate on the almond milk substitution question? | 6 | 7 | 85.7% |
| Approximate cost of the almond milk substitution scenario | 6 | 7 | 85.7% | |
| Did you and the judge agree on the almond milk scenario? | 5 | 7 | 71.4% | |
| Capstone Preparation 6 | Design Scenarios and Collect Data | 0 | 3 | 0.0% |
| Label Your Data and Build a Labeling Tool | 0 | 3 | 0.0% | |
| Build and Validate a Judge | 0 | 3 | 0.0% |
When homework submissions arrive relative to the deadline, across all assignments.
Homework submissions per week, across all assignments. Bars are scaled to the busiest week.
11 students completed the course and received certificates.