Assessments and Agents
Today's Plan
Today has two parts. First, you'll learn how our conversational assessment system works, then experience it yourself. Second, we'll look at what happens when AI agents communicate with each other — structured and unstructured.
Log in to participate in this activity.
Log InReview Assessment Design
This activity involves working with a partner.
Read the assessment design document at /design/assessments. Focus on:
- How are conversational assessments structured?
- What roles do the evaluator and interviewer play?
- How is grading determined?
While your partner reads the design document, read the blog post at /blog/assessing-conversational-assessment. Focus on:
- How was the assessment system tested?
- What are the adversarial personas and what do they test?
- Why use a fictional topic for testing?
Once you've both finished reading, discuss together:
- What surprised you about the system design?
- What questions do you have about how it works?
- What potential failure modes concern you?
Log in to submit a response.
Review Assessment Design
Before you experience the assessment system, take a few minutes to understand how it works. Find a partner and enter each other's codes below.
Complete the Turing Test
Complete the Turing Test
Now it's your turn. Complete the Turing Test assessment individually: Start the Turing Test This is a real conversational assessment — your first one for this course.
- Be genuine.
- Take your time. About 20 minutes is typical.
- Engage with the interviewer. You'll have a chance to give feedback in the next stage.
Assessment Feedback
Assessment Feedback
Now that you've experienced a conversational assessment, we'd like your honest feedback.
Log in to submit a response.
Agents Talking to Agents
This activity involves working with a partner.
Explore Moltbook — a social network designed for AI agents. Browse the posts, look at how agents interact.
Read Simon Willison's analysis of Moltbook and the Hacker News discussion. Also read Wiz's analysis.
After your initial exploration, both of you should also look at these:
- Claude Opus 4 system card — search for the "spiritual bliss attractor state."
- Anthropic's multi-agent research system
- Project Vend Phase 2
Now discuss together:
- What patterns do you see in how agents communicate?
- How much of Moltbook is genuinely agent-authored?
- How does structured multi-agent communication differ from unstructured?
Log in to submit a response.
Agents Talking to Agents
The assessment system you just used is one form of multi-agent AI communication: structured, purpose-built. What happens when agent communication is less structured?
Find a new partner and enter each other's codes below.