Prompt & Context Engineering: sections and modules
Multimodal Prompting
Prompt Gemini with images, PDFs, audio and video.
- Lessons
- 5 lessons
- By
- Sourav Banerjee
- Prerequisites
- None
Lessons
Start modulePractise and Check
- Deliverable
- Report reader: answer five questions about a chart-heavy PDF page by prompting a multimodal model with the page image.
- Assessment
- Answer the five Interview questions without notes, then run the lab.
- Interview probe
- Larkspur summarises recorded export walkthroughs with GPT-4o, sampling a frame every 3 seconds. A customer's summary says the export "may not have finished", but the recording shows an "Export ready" toast. What went wrong, and how do you fix it?
- Common mistakes
- Re-sending a recording's bytes with every prompt instead of reusing one uploaded handle
- Sampling video frames at a gap longer than the shortest event
- Checking that the balance sheet adds up in the prompt, not in code
Your Progress
Saved in this browser when you leave the box.