Rollins College College of Liberal Arts

SE 395-2: AI Tools for Social Impact

Lab 5

Proposal Polish and Peer Review. You have your proposal seed from Lab 4. Stress-test it, get real feedback, and submit a proposal your partner can say yes to.

"Every big change starts as one small, deliberate action."

First Ripple

Student Access

Token provided in class or on Canvas.

Professor Meirelles van Vliet

Fall 2026 · T/R 3:30-4:45 PM · KWR 310

SE 395-2: AI Tools for Social Impact
05

Week 8 · Thursday · AI Lab

Proposal Polish and Peer Review

You have your proposal seed from Lab 4. You should have expanded it into a full draft. Now stress-test it, get real feedback, and submit a proposal your partner can say yes to.

Time
75 minutes in class + homework
Tools
Claude, ChatGPT, or Gemini (your choice) + your team's GitHub repo
Note
No separate submission. Feeds into Project Proposal (Oct 19).
Overview

What This Lab Is For

This is the last lab of the Discovery phase. You have the proposal seed from Lab 4. Between labs, you should have expanded it into a complete draft proposal covering all eight sections. Now you stress-test it, get real feedback from another team, and polish it into a document your partner can say yes to.

The proposal is not a wish list. It is a contract between your team and your partner organization. It says: here is the problem we understand, here is what we plan to build, here is what stays human, here is what we need from you, and here is how we will know if it worked. By the end of today, you will know exactly what needs to change before you submit on Sunday.

You must arrive with a complete draft. Your proposal seed from Lab 4 was the foundation. You should have expanded it into a full draft with all eight sections before today. This lab is peer review and polish. If you do not have a draft, you have nothing to review and nothing to get feedback on. Teams without a draft will not receive credit for the peer review portion.
The Exercise

Five Steps

Steps 1-3 happen in class. Steps 4-5 are homework over the weekend.

1 Quick Audit

In class, 10 minutes. Before you hand your proposal to another team, do a quick self-check. Read through your draft with fresh eyes and mark anything that feels vague, incomplete, or like a chatbot wrote it.

Self-Check Questions

  1. Does every section have real specifics? (Named tools, actual numbers, concrete steps.)
  2. Is the "what stays human" section convincing? Would you trust this system if you were the partner?
  3. Are there any sections where you are guessing instead of drawing on partner visits or Lab 3-4 work?
  4. Read Section 3 (Proposed Solution) out loud. Can someone outside your team follow it?
  5. Does your timeline have specific deliverables at each milestone, or just week numbers?

Mark the weak spots. You do not need to fix them now. You need to know where they are before peer review.

2 Peer Review

In class, 30 minutes. Swap your draft proposal with another team. Each team gets 15 minutes to read and give written feedback, then 15 minutes for face-to-face discussion.

Peer Review Questions

  1. Can you explain their proposed solution in one sentence? If not, it is not clear enough.
  2. Is the "what stays human" section convincing? Would you trust this system if you were the partner?
  3. Are there risks they have not considered? (Technical, ethical, adoption.)
  4. Is the timeline realistic? Are the milestones specific enough that you could tell whether they hit them?
  5. Does the proposal feel like it was written by people who know this partner, or could it be about any organization?
  6. What is the strongest part of this proposal? What is the weakest?

Write your feedback directly on their document or on a separate sheet. Be specific and honest. "This is good" is not feedback. "I do not understand how the AI tool connects to the workflow you described in Section 2" is feedback.

Do not skip peer review. The proposals that get the best final grades are always the ones that went through real critique first. Defend your choices when the feedback is wrong. Revise when it is right.

3 AI Stress Test

In class, 20 minutes. Take your proposal and have Claude (or ChatGPT) poke holes in it. This is not asking AI to rewrite your proposal. It is asking AI to find what you missed.

Stress Test Prompt

I am going to paste my team's project proposal for a course on AI for social impact. We are proposing an AI solution for a real nonprofit partner. Read the entire proposal. Then do three things:

1. Identify the three weakest claims in the proposal. For each one, explain why it is weak and what evidence or specificity would make it stronger.

2. Name two risks we have not addressed. Not risks we mentioned and dismissed. Risks we did not think of at all.

3. Read our success criteria. Are they actually measurable? Could an outside observer tell whether we hit them? If not, suggest how to make them testable.

Be direct. Do not compliment the proposal. Just find the problems.

The AI is not always right. Some of its critiques will miss context you have from the partner visit. That is fine. The value is in forcing you to defend your choices or acknowledge that you need to strengthen them.

4 Revise and Polish

Homework, over the weekend. After peer review and the AI stress test, revise your proposal. Address every piece of feedback, either by incorporating it or by noting why you disagree.

Read the entire document out loud as a team (or have one person read it). If something sounds awkward, vague, or like a chatbot wrote it, fix it. The partner will read this. It should sound like your team, not like AI.

The polish test: Print it or view it as a PDF and read it as if you were the partner seeing it for the first time. Would they say yes to this? If not, what needs to change?
After Lab 5

What Happens Next

Lab 5 is not graded separately and there is nothing to submit for this lab. The work you do here feeds directly into the Project Proposal, which is due Sunday, October 18 by 11:59 PM.

Use the weekend to revise your proposal based on peer review feedback and the AI stress test. Push the final version to your team's GitHub repo and upload to Canvas.

On honesty: Your partner will read this proposal. Do not overcommit. A clear, achievable project that delivers real value is better than an ambitious plan that falls apart in Week 10. Scope it to what your team can actually build in the time you have.
SE 395: AI Tools for Social Impact · Rollins College · Fall 2026 · Professor Meirelles van Vliet

Exemplary Submission

Sample Project Proposal

A professionally branded project proposal following all 8 sections. Written for the fictitious Sunrise Community Kitchen partner by Team Ripple Consulting. Use this as a reference for depth, specificity, formatting, and honest gap identification.

View below or download as a document.

Download PDF

Exemplary Submission

Sample AI Conversation Log

A full AI conversation log showing how AI was used across all phases of Lab 5: quick audit, peer review preparation, AI stress test, and post-review revision.

View the full AI conversation log below or download it.

Download PDF