SE 395-2: AI Tools for Social Impact

Week 5 · Thursday · AI Lab

AI Co-Collaboration and Problem Mapping

Your first team lab. Agree on how you work together, divide research, map your partner's problem landscape with AI, and compile everything through GitHub.

Time

75 minutes in class + homework

Tools

Claude, ChatGPT, or Perplexity + GitHub

Due

Tuesday, Oct 6, 11:59 PM

Part 0 · In Class

Team Working Agreement

Before you touch any AI tool or write any code, you need to agree on how your team works together. This is not a formality. Teams that skip this step spend the rest of the semester dealing with misaligned expectations, missed deadlines, and resentment. Teams that do this well avoid most of that.

Sit together. One person opens Granola on their laptop to record the conversation. Granola will transcribe everything automatically. You are going to have a 15-minute discussion using the questions below. After the conversation, you will use the transcript to draft your team's working agreement.

0 Record your team discussion

Open Granola on one team member's laptop and start a new meeting. State the date, your team name, and everyone present. Then work through the questions below. You do not need to answer every single one, but you need to cover the big ones. Let the conversation be natural. Granola will handle the transcription.

Guiding Questions

Communication

What tool will you use for team communication? (iMessage group, Discord, Slack, WhatsApp, etc.)
What is a reasonable response time? If someone messages at 10 PM, when should they expect a reply?
How will you handle it if someone goes silent for more than 24 hours?

Work expectations

When will you meet outside of class? How often?
What does "done" mean for your team? If someone says their section is done, what standard is that held to?
How will you divide work? By topic, by skill, by volunteering, by assignment?
What happens if someone's section is not done by the agreed deadline?

Decision-making

How will you make decisions when you disagree? Majority vote? Discussion until consensus? Someone has final say?
Who is the team's point of contact with your partner organization?
Who is responsible for sending the follow-up email after each partner meeting?

Quality and accountability

Will you review each other's work before submitting? How?
What is your policy on using AI? (Everyone uses it, but how much editing and verification is expected?)
If someone is struggling with their part, how should they ask for help? When is "too late" to ask?

The hard question

What will you do if a teammate is not pulling their weight? At what point do you escalate to the instructor?

Do not skip the recording. The transcript is your evidence. You will use it to generate your working agreement, and it goes in your repo. If a conflict arises later in the semester, this document is what we go back to.

A Generate your working agreement

End the Granola session. Copy the transcript from Granola (it generates one automatically when the meeting ends). Paste it into Claude or ChatGPT along with this prompt:

Working Agreement Prompt

Here is a transcript of our team's discussion about how we want to work together this semester. We are a team of [3 or 4] students working on a consulting project for [partner name].

Based on this conversation, draft a Team Working Agreement with clear, specific rules. Organize it into these sections:

Communication (tool, response times, what to do if someone goes dark)
Meetings (when, where, attendance expectations)
Work standards (what "done" means, deadlines, quality expectations)
Decision-making (how disagreements are resolved, who has final say on what)
Accountability (what happens when commitments are missed, when to escalate)

Use our actual words and decisions from the transcript. Do not add rules we did not discuss. If something was left unresolved, flag it as "UNRESOLVED: [topic]" so we can decide.

[Paste transcript here]

Review the generated agreement as a team. Edit anything that does not match what you actually agreed to. Resolve any items flagged as unresolved. Every team member should read the final version and confirm they agree.

Save this file as docs/team-working-agreement.md in your repo. This is the first file your team pushes to GitHub.

Part 1 · Setup

Connect to Your Team Repository

Your team has a GitHub repository already set up. Every team member needs to clone it to their laptop and verify they can push changes. You will do all of this through your AI tool's desktop app.

1 Clone your repo through your AI tool

Before you start: If your team has not yet replied to the setup email I sent yesterday with your team name and GitHub usernames, do that first. I cannot add you as a collaborator until I have your username, and you cannot clone or push until you are a collaborator. Check your email for the message with subject "SE 395 — Team [#] Setup and Next Steps."

Open the Claude or ChatGPT desktop app. Open your team's repo folder as a project (or tell the app to clone it first):

Clone Prompt

Clone this GitHub repository to my Documents folder: https://github.com/matiasmeirelles/se395-team1-ideas-for-us

Your AI tool will run the git commands for you. Once cloned, open the folder as a project so the app can see all the files.

You should now have folders: discovery/, docs/, src/, and deliverables/. Your partner brief is in the README.md at the root of the repo.

If you get a permission error: Make sure the instructor has added your GitHub username as a collaborator. Check your email for a GitHub invitation and accept it before cloning. You may also need to authenticate with GitHub. Tell your AI tool: "Help me authenticate with GitHub" and it will walk you through it.

2 Test that you can push

Every team member should do this independently to confirm their access works:

Test Push Prompt

Create a test file called test-[my name].txt, commit it, and push it to GitHub. Then delete the test file, commit, and push again.

If the push succeeds, you are set up.

If someone cannot push: Do not skip this. Every team member must be able to push before you move on. Raise your hand and the instructor will help.

+ What your AI tool can do with your repo

Once your repo folder is open as a project, you can work entirely through conversation. Your AI tool can read your files, create new ones, and handle all git operations. For example:

"Read the partner brief and summarize what we know about their operations"
"Create my stakeholder map section as a markdown file in discovery/findings/"
"Pull the latest changes, then commit and push my work"

You do not need to use the terminal. Your AI tool reads, writes, commits, and pushes for you.

Part 2 · Planning

Divide the Problem Map

Your team is going to build a Problem Map for your community partner. This is a structured analysis of the problems and opportunities your partner faces, informed by what you learned during the partner visit, your own research, and AI-assisted exploration.

Each team member owns one section. You will work on your section individually using AI, push your work to GitHub, and then one person will compile everything into a single professional report.

This lab will also surface what you do not know yet. Pay attention to the gaps. Where is your understanding based on assumptions rather than evidence? What questions do you still need to validate through deeper conversation with your partner, observation in the field, or follow-up interviews with stakeholders? Those gaps become your discovery agenda for the weeks ahead.

If your partner brief in the repo is thin, do not wait for more information to be handed to you. Visit your partner's website, find them on LinkedIn, look at their social media, read any press coverage. Identify specific people in the organization you should be talking to. And if you have not yet scheduled a follow-up meeting or interview with your partner, the time is now. Proposals are due in two weeks. Every week you wait is a week of discovery you lose.

Teams of 4

Person A: Operations Map

How does the partner organization actually work day to day?
What are their core processes, workflows, and routines?
Where does information flow and where does it get stuck?
What tools and systems do they currently use?

Person B: Pain Points and Bottlenecks

Where does the partner spend too much time on manual or repetitive work?
What tasks fall through the cracks or get done inconsistently?
What frustrations did the partner express during their visit?
What workarounds do they use because the "right" solution does not exist?

Person C: Stakeholder Map

Who does the partner serve? Who are their beneficiaries, clients, or audience?
Who else do they interact with? (Funders, government, volunteers, other orgs)
What does each stakeholder group need from the partner?
Where are there tensions or trade-offs between stakeholder needs?

Person D: Opportunity Analysis

Based on the pain points and stakeholder needs, where could AI genuinely help?
Which opportunities are realistic for this organization's size and budget?
What are the risks of each opportunity? (Dependency, cost, data privacy, etc.)
Rank the top 3 opportunities by impact and feasibility

Teams of 3

Person A: Operations + Pain Points

Combines the Operations Map and Pain Points sections above
How the org works, where time is wasted, what is manual that could be improved

Person B: Stakeholder Map

Same as Person C above
Who the partner serves, interacts with, and what each group needs

Person C: Opportunity Analysis

Same as Person D above
Where AI could help, what is realistic, rank top 3

Decide who does what before you leave class. Write it down. Each person should know exactly what they are responsible for before they start working.

Part 3 · Individual Work

Build Your Section with AI

This is the core of the lab. Each team member works individually, using AI to research and write their assigned section. You are not just asking AI to generate text. You are using it as a research partner to build a thorough, evidence-based analysis of your partner's situation.

3 Research your section

Start by reviewing what you already know. Your repo's partner-brief/ folder has the partner visit transcript and key information. Read it. Then open your AI tool and start a conversation focused on your assigned section.

Starting Prompt (adapt for your section)

I am a university student working on a consulting project for [partner name], a [brief description]. Here is what I know about them from a class visit:

[Paste key details from the partner brief relevant to your section]

I am responsible for [your section: operations map / pain points / stakeholder map / opportunity analysis]. Help me build a thorough analysis by:

Identifying the key questions I should be answering in this section
Analyzing the information I already have from the partner visit
Flagging gaps where I need more information (things I should ask the partner next time)
Suggesting how organizations similar to this one typically handle [the focus of your section]

Base your analysis on what I have shared. Do not invent details about the partner. If you are drawing on general knowledge about similar organizations, say so.

Follow up. Push back. Ask the AI to go deeper on the most interesting findings. Challenge claims that feel generic. The conversation should be at least 8-10 exchanges, not a single prompt and copy-paste.

Follow-Up: Go Deeper

You mentioned [specific finding]. That feels generic. Can you give me a more specific analysis based on what I told you about [partner name]? What would this look like in practice for an organization of their size ([X people])? What would they actually need to do differently?

Follow-Up: Find the Gaps

Based on the information I have shared, what are the biggest unknowns? What questions should I ask [partner name] in our next meeting to fill in the gaps in this analysis? Be specific. Give me questions I can actually ask, not vague topics.

4 Write your section

Once you have a solid research conversation, write your section as a markdown file. Your section should be 400-600 words, well-structured, and grounded in what you actually know about the partner.

Each section should include:

A clear summary of your findings (what you know)
Evidence from the partner visit (reference specific things the partner said)
Analysis (what the findings mean, not just a list of facts)
Open questions (what you still need to find out)

Save your file with a clear name in the discovery/findings/ folder:


discovery/findings/operations-map-[yourname].md
discovery/findings/pain-points-[yourname].md
discovery/findings/stakeholder-map-[yourname].md
discovery/findings/opportunity-analysis-[yourname].md

Write it yourself. You can use AI to help with research and to check your reasoning, but your section should be in your own words. If the instructor reads it and it sounds like ChatGPT wrote it, that is a problem. Read it out loud. If you would not say it that way in conversation, rewrite it.

Part 4 · Push

Push Your Work

5 Commit and push

When your section is written and saved in the right folder, push it to the team repo.

Tell your AI tool: "Pull the latest changes, then commit and push my section and my conversation log." It will handle the git commands.

Always pull before you push. If a teammate pushed changes before you, your push will fail unless you pull first. Tell your AI tool to pull first and it will handle this automatically.

Make sure you also push your AI conversation log. Export or copy your conversation and save it as:

discovery/findings/conversation-log-[yourname].md

Part 5 · Compile

Compile the Team Report

6 One person pulls, compiles, and pushes

Designate one team member as the compiler. This person:

Pulls the latest changes to get everyone's sections
Reads all sections and checks for consistency, gaps, and contradictions
Combines the individual sections into a single, professionally formatted team report
Adds an introduction that frames the problem map and a conclusion that identifies the top 3 priorities
Saves the final report as deliverables/report/lab3-problem-map.md
Commits and pushes the final report

Compilation Prompt

I am compiling a team report from four individual sections written by different team members. The report is a Problem Map for [partner name]. Here are the four sections:

[Paste all sections]

Help me compile this into a single, cohesive report. I need you to:

Write a brief introduction (2-3 paragraphs) that frames the problem map and explains the methodology
Integrate the four sections so they flow naturally. Resolve any contradictions or redundancies
Add transitions between sections
Write a conclusion that identifies the top 3 priorities based on the analysis
Flag any inconsistencies between sections that I should resolve with my teammates

Keep each person's analysis intact. Do not rewrite their work. Just connect it and add framing.

The compiler should review the AI's output carefully. Make sure the report still sounds like it was written by your team, not by an AI. Edit anything that feels generic or disconnected from your actual partner.

Tell your AI tool: "Commit the compiled report and push it to GitHub."

Part 6 · Submit

Individual Submission

Every team member submits individually on Canvas, even though this is a team lab. Upload a PDF or Word file (.docx) that contains the compiled team report. Every submission should be the same final report. You are submitting it individually so that each person is accountable for the team's work.

What to Submit on Canvas

The compiled team report (the same document for everyone on the team)
Your individual AI conversation log (unique to you)

Both files are required. The team report shows the final product. The conversation log shows your individual contribution and how you used AI. Without the conversation log, I cannot verify your work.

Rubric

What Strong Work Looks Like

Strong (full credit)	Weak (minimal credit)
Your team working agreement has specific, actionable rules drawn from your actual conversation	Your working agreement is generic boilerplate that could apply to any team
Your individual section is grounded in partner-specific details from the class visit	Your section is generic analysis that could apply to any organization
Your conversation log shows 8+ exchanges with follow-ups, pushback, and deepening questions	Your conversation log shows 2-3 prompts with copy-pasted outputs
The compiled report flows as one document with a clear introduction, connected sections, and priorities	The compiled report is four individual sections pasted together with no framing or integration
Open questions are specific and would be useful in your next partner meeting	Open questions are vague ("learn more about the organization")
All work is in the GitHub repo with clear commit messages	Work was done outside the repo or pushed without meaningful commit messages

Grading

How This Gets Graded

Individual section is thorough, specific, and grounded in partner details

30%

Compiled team report is cohesive with clear introduction, analysis, and priorities

25%

AI conversation log shows iterative, critical use of AI as a research partner

20%

Team working agreement is specific and grounded in recorded discussion

15%

GitHub usage: clear commits, proper file placement, all team members pushed

10%

Due: Tuesday, October 6 by 11:59 PM. Each team member uploads the compiled team report and their individual conversation log to Canvas.

Length: The compiled team report should be 4-6 pages, professionally formatted (PDF or .docx). Conversation logs can be any length.

On contribution: I will check the GitHub commit history. If someone's name does not appear in the commits, I will follow up. The working agreement and the commit log together tell me who did what. Make sure your contribution is visible.

Exemplary Submission

Sample Problem Map Report

This report uses O-Town Compost (not one of our actual partners) to demonstrate what a strong Lab 3 submission looks like. Use it as a reference for structure, depth, and the level of partner-specific detail expected.

SE 395-2 · Lab 3 · Problem Map

O-Town Compost: Problem Map

Team Ripple Consulting: Alex Torres, Jordan Reeves, Mia Chen, Sam Okafor

October 6, 2026

Introduction

O-Town Compost is a for-profit food waste recycling company operating across seven Florida cities, from Jacksonville to St. Petersburg. Founded by Charlie Pioli, the company collects food scraps from residential, commercial, and event clients, processes them into compost, and donates or distributes the finished product to local farms, schools, and community gardens. The team is small: four full-time staff members handling operations across all service lines.

During their class visit, Charlie described starting the company "with a pitchfork and a Camry" and scaling to over 14 million pounds composted. Despite this growth, many of their internal processes remain manual, and the team is stretched thin across seven cities and six distinct service lines. This problem map examines their operations, identifies where effort is wasted or inconsistent, maps the stakeholders they serve and depend on, and evaluates where AI tools could realistically help an organization of this size.

1. Operations Map

Section by Alex Torres

O-Town Compost runs six service lines: residential, commercial/food service, office, multi-family, events, and farm dumpster composting. Each has a different sales process, pricing structure, and operational workflow.

Residential is the highest-volume service. Customers sign up online, receive a 5-gallon bucket with a compostable liner, and get weekly or bi-weekly pickups. Drivers swap dirty buckets for clean ones. Customers receive text reminders the night before. Pricing ranges from $24/month (bi-weekly) to $42/month (weekly, two buckets), with a discounted Lake Nona rate of $22/month through a community partnership. Billing is automated through Stripe.

Commercial, office, and multi-family sales follow a different pattern: the customer fills out a web form, Erin (GM) or Charlie follows up with a consultation, and they develop a custom proposal. Office accounts use stainless steel step-cans instead of buckets and include a complimentary lunch-and-learn presentation. Pricing for offices starts at $85/month for 10 or fewer employees.

Events are the most labor-intensive service. They require consultation with all event vendors, provision of bins and compostable bags, on-site waste ambassadors, post-event hauling, data reporting, and compost donation. Events must be booked at least two weeks in advance.

Across all lines, the customer portal (accounts.o-towncompost.com) allows subscribers to track waste diversion, manage payments, order compost, and suspend service for vacations. Drivers use Stopsuite routing software for residential and commercial routes.

Open questions: How much of the commercial sales pipeline is tracked in a CRM vs. email/spreadsheets? How does the team coordinate route changes when a new commercial client is onboarded mid-week? What does the handoff look like between sales (Charlie/Erin) and operations (Stephen/Erik)?

2. Pain Points and Bottlenecks

Section by Jordan Reeves

The most significant bottleneck is the mismatch between the company's geographic footprint and its team size. Four people serve seven cities across 200+ miles of Florida. Charlie handles sales and strategy, Erin manages day-to-day operations and customer service, Stephen runs the warehouse (cleaning and sanitizing hundreds of buckets weekly), and Erik manages the driver fleet and routes. When any one person is unavailable, the gap is immediately felt.

Commercial sales is almost entirely manual. When a restaurant or office fills out the web form, someone (usually Erin or Charlie) reads the submission, assesses the account size, prepares a proposal, and follows up by email or phone. There is no templated proposal system, no automated follow-up sequence, and no way to track where a lead is in the pipeline without checking email threads. Charlie mentioned during the visit that they "lose track of leads sometimes" when things get busy.

Event coordination is high-touch and unscalable. Each event requires vendor consultation, custom serviceware guidance (they maintain a detailed list of what is and is not truly compostable), on-site staffing, and post-event data reporting. The serviceware education alone is time-consuming: many clients think PLA bioplastic cups are compostable when they are not. Charlie noted they have had to reject contaminated loads from events that used incorrect serviceware.

Customer education is repetitive. The FAQ on their website covers 20+ questions, but Erin still fields many of the same questions by phone and email: what can go in the bucket, where to leave it, how to get compost back, how to pause service. These are not edge cases. They are the same questions from every new subscriber.

Reporting for commercial clients is manual. Commercial and office clients receive monthly waste diversion reports. These reports are generated from driver pickup logs, but the process of compiling the data, formatting it, and sending it to each client is manual.

Open questions: How much time does Erin spend per week on customer service inquiries that could be answered by the FAQ? What percentage of commercial leads convert, and where in the pipeline do most drop off? How are event post-mortems (waste diversion data) compiled, and how long does that take?

3. Stakeholder Map

Section by Mia Chen

Primary Stakeholders

Stakeholder	Relationship	What They Need
Residential subscribers	Paying customers (~thousands across Central FL)	Reliable pickup, clean buckets, text reminders, easy payment, free compost returns twice/year
Commercial clients (restaurants, offices, hospitals, universities)	Paying customers, custom contracts	Waste diversion reports for sustainability compliance, clean/professional equipment, social media recognition
Event clients (weddings, conferences)	One-time or recurring contracts	Turnkey zero-waste service, on-site ambassadors, post-event metrics to report to stakeholders
Farm partners (4Roots Farm, Froot Farm, Everoak Farm)	Receive donated compost	Consistent supply of quality compost, free of contamination

Secondary Stakeholders

Stakeholder	Relationship	What They Need
Municipal governments (Alachua County, Lake Nona/Tavistock)	Partners, potential regulators	Waste diversion data for sustainability goals, reliable service, community engagement
Schools and community gardens	Receive donated compost	Consistent supply, educational component
Drivers and warehouse staff	Employees (mix of FT/PT)	Fair pay ($17-28/hr), benefits, manageable routes, functioning equipment
Prospective customers	Leads via website forms	Quick response, clear pricing, easy onboarding

Tensions and Trade-offs

Growth vs. quality. Expanding to new cities (they now cover Jacksonville to Tampa) increases revenue but stretches the four-person team thinner. Every new city means new routes, new driver logistics, and new customer service volume without proportional staff growth.

Residential vs. commercial. Residential is high-volume but low-margin ($24-42/month per household). Commercial accounts are higher-margin but require significant upfront sales effort and custom proposals. The team must constantly balance where to allocate their limited time.

Contamination management. Farm partners need clean compost. Event clients often use incorrect serviceware despite guidance. Every contaminated load hurts the relationship with farm partners and wastes processing effort. This is an ongoing tension between serving event clients (revenue) and maintaining compost quality (mission).

Open questions: How does O-Town Compost prioritize which new cities to expand into? What is the customer churn rate for residential vs. commercial? How often do contamination issues with event loads actually occur, and what is the cost?

4. Opportunity Analysis

Section by Sam Okafor

Based on the pain points and stakeholder needs identified above, three AI-assisted opportunities stand out as realistic for an organization with four staff members and limited budget.

Opportunity 1: Automated Customer Onboarding and FAQ (High Impact, High Feasibility)

A significant portion of Erin's time goes to answering the same 20 questions that are already on the website. An AI-powered chatbot or email responder trained on O-Town's FAQ, pricing, service areas, and acceptable materials list could handle first-line customer inquiries. This would free Erin to focus on commercial sales and operations.

Realistic implementation: A custom GPT or Claude project trained on their FAQ content, pricing tables, and service area data. Could be embedded on the website or used to draft email responses.

Risks: Must handle edge cases correctly (e.g., "Is my address in the service area?" requires real-time data). Incorrect answers about compostable materials could lead to contamination. Would need human review for non-standard requests.

Opportunity 2: Commercial Proposal Automation (High Impact, Medium Feasibility)

Commercial proposals are currently written from scratch for each lead. An AI tool could take the web form submission (business type, employee count, location) and generate a draft proposal with the right pricing tier, service description, and sustainability talking points. Charlie or Erin would review and customize before sending.

Realistic implementation: A prompt template that takes form data as input and outputs a formatted proposal draft. Could be built as a Claude project with their standard pricing and service descriptions as context.

Risks: Proposals still need the personal touch that closes deals. Over-automation could make outreach feel generic. The tool needs accurate, up-to-date pricing data.

Opportunity 3: Waste Diversion Report Generation (Medium Impact, High Feasibility)

Monthly diversion reports for commercial clients are compiled manually from driver logs. An AI tool could take raw pickup data (dates, weights, client) and generate formatted reports with charts, comparisons to previous months, and environmental impact calculations (CO2 equivalent saved, landfill space saved).

Realistic implementation: A script or AI workflow that reads pickup log data (likely from Stopsuite or a spreadsheet), calculates metrics, and outputs a formatted PDF report per client.

Risks: Requires clean, consistent data input from drivers. If pickup weights are estimated rather than measured, the reports are only as good as the estimates.

Deprioritized: Route Optimization

While route optimization is a natural fit for AI, O-Town already uses Stopsuite for routing. Replacing or layering another tool on top would add complexity without clear benefit unless Stopsuite's limitations are better understood. This should be explored in follow-up conversations but is not a top-3 priority today.

Conclusion: Top 3 Priorities

Customer FAQ automation — highest ROI. Frees the most staff time with the lowest implementation risk. Start here.
Commercial proposal drafting — addresses the lead-tracking gap and could shorten the sales cycle. Requires more setup but has clear revenue impact.
Diversion report generation — reduces a recurring manual task and improves the professional quality of client deliverables. Strengthens commercial retention.

All three opportunities are realistic for a four-person team using tools that already exist (Claude projects, GPTs, or lightweight automation scripts). None require custom software development or significant budget. The next step is to validate these priorities with Charlie and Erin: do these match where they actually feel the pain, or are we missing something that only shows up in their day-to-day?

Exemplary Submission

Sample Agent Session Log

This shows what a strong session log looks like when working with an AI agent (Claude or ChatGPT desktop app). Notice how the student directs the agent, follows up on findings, pushes back on generic analysis, and uses the agent to read partner files and create documents directly in the repo.

Agent Session Log

Stakeholder Map — Mia Chen

Tool: Claude Desktop App · Project folder: ~/Documents/se395-team6-o-town-compost

Date: October 3, 2026 · Duration: ~40 minutes

Mia (prompt 1)

Read the partner brief files in the partner-brief folder. I need to understand everything we know about O-Town Compost before I start my section. I am responsible for the stakeholder map.

READ partner-brief/organization-overview.md

READ partner-brief/class-visit-transcript.md

READ partner-brief/project-areas.md

Claude

I have read all three partner brief files. Here is what we know about O-Town Compost that is relevant to stakeholder mapping:

Organization: For-profit food waste recycler founded by Charlie Pioli. 4 full-time staff (Charlie, Erin the GM, Stephen in warehouse, Erik managing fleet). Operates in 7 Florida cities. Over 14 million pounds composted to date.

Service lines: Six distinct service types: residential (bucket pickup/swap, $24-42/month), commercial/food service (custom proposals), office ($85-160/month with step-cans), multi-family (property managers), events (zero-waste with on-site ambassadors), and farm dumpster composting.

Key relationships mentioned in the visit:

Farm partners who receive donated compost: 4Roots Farm, Froot Farm, Everoak Farm
Lake Nona / Tavistock community partnership (discounted residential rates)
Alachua County government (free food waste drop-off program funded by Circular Economy Grant)
Schools and community gardens (compost donations)
Fleet Farming (Erik came from there; they receive event compost)

Tensions Charlie mentioned: Contamination from events using wrong serviceware. Difficulty tracking commercial leads. Small team stretched across wide geography.

Where would you like to start?

Mia (prompt 2)

Help me organize the stakeholders. I want to split them into primary (direct, regular interaction) and secondary (indirect or occasional). For each one I need: who they are, what the relationship looks like in practice, and what they need from O-Town Compost.

Claude

Here is a draft stakeholder map based on the partner brief:

Primary stakeholders: residential subscribers, commercial/food service clients, event clients, and farm partners. Each of these interact with O-Town on a weekly or per-engagement basis and have direct service relationships.

Secondary stakeholders: municipal governments, schools/community gardens, employees (drivers, warehouse), and prospective customers (leads).

[Provided detailed breakdown for each with needs and relationship descriptions]

Mia (prompt 3)

That is a good start but it feels too clean. Where are the tensions? Charlie talked about how event clients use the wrong serviceware and it messes up the compost quality. That is a direct tension between serving event clients and keeping farm partners happy. What other tensions exist between stakeholder groups?

Claude

Good catch. Here are the tensions I see in the data:

1. Event clients vs. farm partners (contamination). Events generate revenue but also the highest contamination risk. PLA bioplastic cups look compostable but are not. Every contaminated event load threatens compost quality for farm partners. Charlie has to choose between rejecting contaminated loads (losing revenue, frustrating clients) or processing them (compromising quality).

2. Growth vs. service quality. Expanding to new cities brings more residential subscribers (volume) but stretches the four-person team. More cities mean more routes, more customer service inquiries, more driver logistics. Residential subscribers need reliable weekly pickups. If growth outpaces hiring, reliability suffers.

3. Residential vs. commercial allocation. Residential is high-volume, low-margin (~$30/month per household). Commercial is lower-volume but higher-margin (custom pricing). Erin's time spent answering residential FAQ questions is time not spent closing commercial deals. These two customer groups compete for the same scarce resource: staff attention.

4. Municipal partners vs. independence. Government partnerships (Lake Nona, Alachua County) bring scale and credibility but may come with reporting requirements, price constraints, or political risk. If a county contract ends, the volume loss could be significant.

Mia (prompt 4)

The municipal tension is interesting but I am not sure we have enough evidence for it from the visit. Charlie mentioned the Lake Nona and Alachua County partnerships positively. I do not want to speculate about risks he did not mention. Can you flag that as an open question instead?

Claude

You are right. I was extrapolating beyond what Charlie actually said. The Lake Nona partnership was presented as a success (community-wide initiative, discounted rates), and the Alachua County program is grant-funded with a defined timeline. There is no evidence of tension there.

I will move the municipal dependency question to "open questions" as something to ask in the next partner meeting: "How dependent is your revenue on municipal partnerships? What happens when the Alachua County grant period ends?"

Mia (prompt 5)

Good. One more thing. I want to include the employees as stakeholders. Charlie listed job postings starting at $17/hour for residential drivers and $24-28 for CDL commercial drivers. Those are real numbers. But I do not know much about driver retention or satisfaction. What questions should I ask about this?

Claude

For the employee stakeholder section, here is what you know vs. what you need:

What you know: Pay ranges ($17/hr residential, $24-28/hr CDL commercial). Benefits for full-time (32+ hrs): 401k with 3% match, $800/month healthcare stipend, YMCA membership, PTO. Routes start 4-5 AM for commercial drivers. They are actively hiring for both driver roles and a regional sales rep.

What you do not know (open questions):

What is the driver turnover rate? Is the early morning start time a retention issue?
How many drivers do they have across seven cities? Are some cities served by the same drivers doing long routes?
The careers page includes a testimonial from "Christy, O-Town's first driver." Is she still with the company?
With only four named staff and active hiring, are they currently understaffed?

Mia (prompt 6)

OK, I think I have enough to write my section. Create the stakeholder map as a markdown file. Put it in discovery/findings/stakeholder-map-mia.md. Include the primary and secondary tables, the tensions section with the three we confirmed, and the open questions. 400-600 words.

WRITE discovery/findings/stakeholder-map-mia.md (487 words)

Claude

Created the file at discovery/findings/stakeholder-map-mia.md. It includes:

Primary stakeholders table (residential, commercial, event, farm partners)
Secondary stakeholders table (municipal, schools/gardens, employees, prospects)
Tensions section (3 confirmed: contamination, growth vs. quality, residential vs. commercial)
Open questions for next partner meeting (5 questions)

487 words total. Want me to read it back so you can review before pushing?

Mia (prompt 7)

Yes, read it back to me.

READ discovery/findings/stakeholder-map-mia.md

Claude

[Read back the full stakeholder map content for review]

Mia (prompt 8)

In the tensions section, change "compromising quality" to "risking the relationship with farm partners." It is more specific. Also, in the open questions, add one about whether they have considered hiring a part-time customer service person to take pressure off Erin.

EDIT discovery/findings/stakeholder-map-mia.md (2 changes)

Claude

Done. Changed "compromising quality" to "risking the relationship with farm partners" in the contamination tension. Added open question: "Has the team considered hiring a part-time customer service role to handle residential inquiries and free Erin for commercial sales and operations?"

Mia (prompt 9)

Looks good. Pull the latest changes from the repo, then commit and push my stakeholder map and this conversation log.

RUN git pull origin main

RUN git add discovery/findings/stakeholder-map-mia.md

RUN git commit -m "Add stakeholder map section - Mia"

RUN git push origin main

Claude

Pulled latest (2 new files from Alex and Jordan). Committed and pushed your stakeholder map. The push succeeded.

Mia (prompt 10)

Now export this conversation as my session log and save it as discovery/findings/conversation-log-mia.md, then push that too.

WRITE discovery/findings/conversation-log-mia.md

RUN git add discovery/findings/conversation-log-mia.md

RUN git commit -m "Add conversation log - Mia"

RUN git push origin main

Claude

Saved and pushed. Both files are now in the repo.

"Notice how the student directed the conversation: she pushed back when the AI speculated beyond the evidence (prompt 4), asked for specific edits rather than accepting the first draft (prompt 8), and used the agent to handle git operations (prompt 9). The session shows 10 exchanges with genuine iteration, not a single prompt and copy-paste."

git

Reference

Git Quick Reference

The commands you need for this lab. Bookmark this tab. You will use these commands every week for the rest of the semester.

The Basics

Daily Workflow

Every time you sit down to work, follow this sequence:

1. Pull latest changes


git pull origin main
# Always do this first. Gets your teammates' latest work.

2. Do your work


# Write your files, save them in the right folders.

3. Stage your changes


git add discovery/findings/my-section.md
# Or stage everything you changed:
git add -A

4. Commit with a message


git commit -m "Add stakeholder map section - Kara"
# Be specific. "Update" is not a good commit message.

5. Push


git push origin main

Common Problems

When Things Go Wrong

"Your branch is behind" or "rejected"

This means a teammate pushed before you. Fix it by pulling first:


git pull origin main
# Then try pushing again:
git push origin main

Merge conflict

This happens when two people edited the same file. Git will mark the conflict in the file with <<<<<<< markers. Open the file, decide which version to keep, remove the markers, then:


git add [the-conflicted-file]
git commit -m "Resolve merge conflict in [filename]"
git push origin main

To avoid conflicts: each person works in their own file. If everyone writes in different files, merge conflicts almost never happen.

"Not a git repository"

You are in the wrong folder. Navigate to your cloned repo:


cd ~/Documents/se395-team1-ideas-for-us

Check what is going on


# See what files have changed
git status

# See recent commits (yours and teammates')
git log --oneline -10