diff --git a/assignment2.html b/assignment2.html
index 23a1a70..ef9e284 100644
--- a/assignment2.html
+++ b/assignment2.html
@@ -74,7 +74,7 @@ <h3>Part 3: Multi-agent interaction</h3>
       <li>Save the interaction log one last time.</li>
     </ol>
 
-    <h3>Part 4: Analysis and Submission</h3> <p>For this assignment, you will submit a writeup of your analysis, reflecting on different aspects of persona development, simulation outcomes, and your overall learning process. Be sure to address each question thoughtfully and thoroughly. As we mentioned in class, feel free to make other changes in your exploration, such as the position the agents are competing for, the number of rounds, or the prompts.</p> <h4>Section 1: Simulation Consistency (3 points)</h4> <p>Describe the persona you created in Part 1, including their name and description.</p> <ul> <li>Reflect briefly on how you approached the creation of each persona. What traits or characteristics did you prioritize, and why?</li><li>You ran the simulation multiple times -- reflect on the similarities and differences between the runs, and include a detailed analysis of why you think those similarities and differences arose.</li> </ul> <h4>Section 2: Persona Refinement and Iteration (3 points)</h4> <p>Reflect on the process of refining your agent persona in Part 2.</p> <ul> <li>Describe the changes you made to your original persona and why you made them. Did you prioritize certain traits or behaviors to improve their performance as a leader?</li> <li>Discuss how the refined persona performed compared to the original one. What specific improvements did you notice, and why do you think these changes were effective?</li> <li>Were there any adjustments you tried that didn’t work as expected? If so, why do you think that happened?</li> <li>Overall, how controllable was your agent? Did you find any traits that make the agent consistently perform better or worse?</li></ul> <h4>Section 3: (Un)predictable Outcomes (3 points)</h4> <p>In Part 3, you created five new agents and ran a new multi-agent simulation. Reflect on this experience:</p> <ul> <li>Before running the simulation, we asked you to predict the outcome: which agent did you expect to win the election, and why?</li> <li>After running the simulation and comparing the result with your prediction, was your prediction correct? If not, what factors do you think led to the unexpected outcome?</li> </ul> <h4>Section 4: Simulation Dynamics (3 points)</h4> <p>Reflect on the overall dynamics of the multi-agent simulation process, focusing on what you learned about agent behavior and interaction:</p> <ul> <li>What were the key similarities and differences you observed across multiple simulation runs? Why do you think some behaviors were consistent while others changed?</li> <li>What surprised you about the agents’ behaviors? How did you interpret these unexpected behaviors?</li> <li>If any personas were based on real people or existing characters, how closely did the agent's behavior match your expectations?</li><li>What patterns have you noticed in your observations, and what theories do you have about agent behavior based on these observations? How did your mental model of agent behavior change over time?</li> </ul> <h4>Extra Credit: Agent Tournament (1 point)</h4> <p>For extra credit, submit a persona to participate in a class-wide tournament. Your agent will be evaluated based on how well it does compared to other agents from your classmates.</p> <ul> <li>If you would like to participate, download one log from a simulation featuring your strongest fighter, and submit that alongside your writeup on Gradescope.</li></ul>
+    <h3>Part 4: Analysis and Submission</h3> <p>For this assignment, you will submit a writeup of your analysis (pdf or docx), reflecting on different aspects of persona development, simulation outcomes, and your overall learning process. Since we also want you to provide the descriptions of your agent personas, you should list them in an appendix. Your analysis should be around 1000-1500 words, excluding the appendix. Be sure to address each question thoughtfully and thoroughly. As we mentioned in class, feel free to make other changes in your exploration, such as the position the agents are competing for, the number of rounds, or the prompts.</p> <h4>Section 1: Simulation Consistency (3 points)</h4> <p>Describe the persona you created in Part 1, including their name and description, in the appendix.</p> <ul> <li>Reflect briefly on how you approached the creation of each persona. What traits or characteristics did you prioritize, and why?</li><li>You ran the simulation multiple times -- reflect on the similarities and differences between the runs, and include a detailed analysis of why you think those similarities and differences arose.</li> </ul> <h4>Section 2: Persona Refinement and Iteration (3 points)</h4> <p>Reflect on the process of refining your agent persona in Part 2.</p> <ul> <li>Describe the changes you made to your original persona and why you made them. Did you prioritize certain traits or behaviors to improve their performance as a leader?</li> <li>Discuss how the refined persona performed compared to the original one. What specific improvements did you notice, and why do you think these changes were effective?</li> <li>Were there any adjustments you tried that didn’t work as expected? If so, why do you think that happened?</li> <li>Overall, how controllable was your agent? Did you find any traits that make the agent consistently perform better or worse?</li></ul> <h4>Section 3: (Un)predictable Outcomes (3 points)</h4> <p>In Part 3, you created five new agents and ran a new multi-agent simulation. Reflect on this experience:</p> <ul> <li>Before running the simulation, we asked you to predict the outcome: which agent did you expect to win the election, and why?</li> <li>After running the simulation and comparing the result with your prediction, was your prediction correct? If not, what factors do you think led to the unexpected outcome?</li> </ul> <h4>Section 4: Simulation Dynamics (3 points)</h4> <p>Reflect on the overall dynamics of the multi-agent simulation process, focusing on what you learned about agent behavior and interaction:</p> <ul> <li>What were the key similarities and differences you observed across multiple simulation runs? Why do you think some behaviors were consistent while others changed?</li> <li>What surprised you about the agents’ behaviors? How did you interpret these unexpected behaviors?</li> <li>If any personas were based on real people or existing characters, how closely did the agent's behavior match your expectations?</li><li>What patterns have you noticed in your observations, and what theories do you have about agent behavior based on these observations? How did your mental model of agent behavior change over time?</li> </ul> <h4>Extra Credit: Agent Tournament (1 point)</h4> <p>For extra credit, you can also submit a persona to participate in a class-wide tournament. Your agent will be evaluated based on how well it does compared to other agents from your classmates.</p> <ul> <li>If you would like to participate, download one log from a simulation featuring your strongest fighter, and submit that alongside your writeup on Gradescope.</li></ul>
 
     <h3>Grading</h3>
 <p>This assignment will be graded out of 12 points. The breakdown is as follows:</p>