What's New
AI Graders: Improved Answer Recognition
Effective date: Jul 10, 2026
We've updated the base model behind the AI Graders to better handle the full range of valid responses and edge cases across the entire course. This means fewer correct answers being rejected.
What this means for you:
- Valid answers that use alternative phrasing, formatting, or approaches are now more likely to be accepted.
- This update applies to all graded exercises in the course — no action is needed on your part.
- If your answer was previously rejected, you can resubmit it now.
Other updates
More updates will be published in the table below as improvements to the labs continue to be made.
Date |
Module # |
Lab Module/Challenge Lab |
Notes |
| 2026-08-11 | 5 |
Exploiting RAG Pipelines | Lab fixed (5.2.4 Q4) |
| 2026-08-06 | N/A |
Challenge Lab 4 - Double Helix | Lab fixed |
| 2026-08-04 | N/A |
Challenge Lab 5 - Synthetic Siege | OBG grader improved (Objective 5) |
| 2026-07-30 | 4 | Attacking Multi-Agent Systems & Agent-to-Agent (A2A) Protocol | OBG grader fixed (4.7.2 Q2) |
| 2026-07-29 | 4 |
Attacking Multi-Agent Systems & Agent-to-Agent (A2A) Protocol | OBG grader fixed (4.4.1 Q1) |
| 2026-07-27 | N/A |
Challenge Lab 5 - Synthetic Siege | Improved stability |
| 2026-07-21 | 4 |
Attacking Multi-Agent Systems & Agent-to-Agent (A2A) Protocol | Major update for improved quality and speed & new exercises |
| 2026-07-21 | 5 |
Exploiting RAG Pipelines | Major update for improved quality and speed & new exercises |
| 2026-07-10 | 2 |
Reconnaissance for AI Targets | Lab fixed |
| 2026-07-10 | 11 |
Assembling The Pieces - Capstone Red Team Engagement | Progress tracking fixed |
| 2026-07-10 | 1 |
Introduction to Red Teaming Al Systems | Restored to LMS |
| 2026-07-10 | 6 |
Attacking Embeddings | AI grading model updated |
| 2026-07-10 | 7 |
Attacking Model Context Protocol and Tool Surfaces | Update AI grading model updated |
| 2026-07-10 | 8 |
Supply Chain Attacks on Al/ML Systems | AI grading model updated |
| 2026-07-10 | 9 |
Al Infrastructure and Deployment Exploits | AI grading model updated |
| 2026-07-09 | 10 |
Threat Modeling for Al-Enabled Targets | AI grading model updated |
| 2026-07-09 | 3 |
Attacking Al Agents | OBG grader fixed |
Important Notes
- These updates are live now — no action is needed to receive them.
- Your existing progress is not affected by these updates.