CopaMigo
Case study · AI Tools & Strategy
A student-facing AI triage tool that reads a community college student’s problem in their own words, in the language they think in, and routes it to the right human service with a warm handoff card.
CopaMigo takes routine, repetitive questions off advisors and financial aid staff: hours, deadlines, process steps, what to bring, the “we will get back to you in a few days” scheduling email. Nobody is replaced. Staff write the answers, own them, and receive every student the tool routes. Every path CopaMigo opens ends at a human.
1. Summary
CopaMigo reads a stuck community college student’s problem in plain language, in the language they think in, and routes it to the right human service with a warm handoff card. It takes routine, repetitive questions off staff while every path it opens ends at a person who owns the answer. It is in testing, and it is built to prove a specific point: that a college can run a useful student-facing AI tool that collects no student data.
2. Goal
Get a stuck student to the right person quickly, without asking them to name the office or already know the institutional vocabulary. This is a student-success problem before it is a technology one. The students most likely to fall through the cracks are the ones who do not yet know that what they are feeling has an office attached to it: a student with undiagnosed ADHD will never search for “disability resources,” and a student one missed payment from dropping will not describe it as a financial aid appeal. Meeting them in plain language and doing the translation for them removes a barrier that sits in front of every service, and it does so at the moment a student is willing to reach out rather than days later.
A second goal shapes every technical decision that follows: prove a college can run a useful student-facing AI tool that collects no student data. The district declined a vendor AI add-on to its student CRM because it would have put student data within reach of a third-party model. CopaMigo is the argument that the data-sovereign path is available, not only the data-harvesting one.
3. Users and context
Community college students at GCC, a Hispanic-Serving Institution, and the staff who serve them. It is built for the student who describes a problem in everyday words rather than the correct term, the prospective or returning student for whom a phone call already feels like a commitment, the student avoiding a label (an IEP history, anxiety, or ADHD that they do not name as disability), and the multilingual student who wants to be answered in the language they think in rather than through a translate button. CopaMigo answers in the student’s own language, not just English and Spanish: it runs on a model optimized for about a dozen languages that handles many more, so a student can write in Arabic, Vietnamese, Tagalog, or whatever they think in.
On the other side are the advisors, financial aid staff, disability resource staff, veterans coordinator, librarians, counselors, social workers, and tutoring staff who write and own the answers the tool delivers. They are the audience too: the design goal for them is fewer repeat questions, students who arrive with context already attached, and content they can correct the same day it changes.
4. How it works
A student types or speaks a problem in their own words. CopaMigo reads it for urgency and need, answers directly when the responsible department has already supplied the answer, and otherwise hands off to a person. Unlike a website chat widget that scans pages and returns links, every answer is written by the staff who already field these questions. The AI is the delivery layer, not the author.
The handoff card
The card is where the tool does its most careful work, because it is built to remove every remaining unknown between the student and the door. It is specific, not a generic office listing, and every field is there so the student never has to run a second search. The card carries:
- The office name, and one plain-language line on what it actually does.
- The exact location, down to the building and the room number, and it is campus-aware: a student at North Campus gets the North office, a student at Main gets Main, so the directions are never for the wrong place.
- A map that points to that exact building, not a general campus map.
- The office website.
- The hours, so the student knows whether it is open right now.
- The phone number.
- What to say when they arrive or call, the specific opening line, so a nervous student never has to improvise the ask.
- The specific next step to take.
The point is that a student can act on the card immediately, in person or by phone, without a second search and without having to work out what to ask.
The student experience
Everything on the student’s side is designed to lower the cost of asking. The student writes or speaks in everyday words, is met with a human acknowledgment before any label or form, and receives a card they can act on in the moment. Voice in and voice out let a student speak instead of type and hear the answer read back in their own language (for example, speak Spanish and be answered in Spanish), and the whole thing runs on a phone. No login, no name, and no account stand between the student and help.
Every incoming message sorts into one of three routing tiers. The tier is decided by the nature of the question, not its topic.
| Tier | Behavior | Examples |
|---|---|---|
| 1, bot answers directly | The department has already supplied a current, correct answer. The bot delivers it in plain language. | Tutoring hours. Food pantry location. Last day to withdraw. How to request a transcript. |
| 2, bot answers, then opens a path | A useful general answer exists, but the student’s specifics need a person. The bot answers, then hands over phone, scheduling link, and walk-in location. | What happens to aid if I drop a class. How do I request accommodations. Where do I start on transferring. |
| 3, direct to human | No answer attempted. Empathy and the fastest possible warm handoff. | Self-harm or safety risk (immediate escalation to counseling and 988). Title IX. Imminent eviction or hunger. |
A few rules hold across all three tiers, and each exists for a reason grounded in how students actually ask for help.
- Empathy first, label second. The first response acknowledges what the student said in human language. The office is named only after the student has been received, because a student who leads with shame will not stay for a form.
- One situation can route to several offices at once. “I am failing and my aid is on hold” reaches advising and financial aid, each with context, so the student does not have to tell the story twice.
- The bot names no courses. Training data on course codes is unreliable across semesters, and a hallucinated course name sends a student to register for the wrong class. The tool links the verified published program checksheet (a plain JavaScript lookup table of program to URL, no AI-constructed links) and routes first-semester students to an advisor before they register.
- Crisis and Title IX routing is hard-coded and runs ahead of everything else, including when the topic is raised indirectly.
- Voice in, voice out through the browser-native Web Speech API, so a student can speak instead of type and hear the answer read back in their own language (for example, speak Spanish and be answered in Spanish). No translation service and no per-message cost.
The prototype covers more than two dozen service areas, from advising and financial aid to disability resources, counseling, tutoring, library, basic needs, veterans, records, and crisis and Title IX routing, with more than 100 verified service links behind the cards. The full list of what it recognizes and where each path routes is in Appendix A.
5. Data, privacy, and governance
CopaMigo collects no student data and no personally identifiable information. No login, no MEID, no name, no email, no student record.
The only data leaving the browser is the student’s question and the response, and no identity is attached because none is collected, so there is nothing to mask or redact. This is the data-sovereign line the whole tool is built to prove: no student conversation data is retained to train an underlying model, under any hosting arrangement. In production the AI call moves to one stateless server-side function that holds the credential in a secrets manager, adds the system prompt, and returns the response, so the browser never holds a key and never sees the prompt. Anonymous routing counts (which cards showed, detected language, success or error) are the only thing logged; question text, response text, and any free-text field are not. The one place a student may choose to share contact information is the handoff itself, with the receiving staff member only. FERPA review rests on that anonymous-first design, and a production release targets WCAG 2.1 Level AA.
6. Build and portability
The build
- A single HTML file, vanilla JavaScript, no framework, no backend, hosted on GitHub Pages, mobile-first. It ships two ways from one codebase: a standalone page a college can link from a homepage, a Canvas tab, or a QR code, and an embeddable widget that drops into an existing student services page. Same prompt, same cards, one deployment to maintain.
- Voice input and speech output run in the browser through the Web Speech API. No audio is sent anywhere.
- Routing logic, tier behavior, service cards, and every department-written answer live in one system prompt. The checksheet lookup is a plain JavaScript table, and the staff intake forms are ordinary web forms with no AI in them.
- The AI layer is the Claude API. In the prototype the call is made with a tester-supplied credential; the production architecture moves that call to a stateless server-side proxy, so the credential is handled off the browser entirely. Standing up that proxy is the single hardening step before a live pilot.
Model portability, Claude to Gemini
CopaMigo is built on the Anthropic Claude API, and the Maricopa district is standardizing on Google Gemini. That is a solvable mismatch by design, not a rebuild. Every AI call runs through a single request function, so moving the tool to Gemini means changing three things in one place: the endpoint, the authorization header, and the shape the response is parsed from. The system prompt, service cards, and department-written content are provider-agnostic text, and the routing, multilingual behavior, verified links, checksheet lookup, and intake forms are untouched by the swap. What changes is a re-run of the test set to re-tune wording, which is tuning, not re-architecting.
No student PII is ever sent to any model, so the privacy posture does not change with the provider. The order of preference is a campus or district Claude for Education account first, because the prompt was tuned against Claude and it keeps the key off student devices behind a server-side proxy. If that account does not come through, the fallback is the district Google tenant: point the request function at Gemini and run the key through the same server-side proxy on Maricopa infrastructure. Either way the credential lives server-side, never in the browser, which is the one hardening task independent of which model wins.
District infrastructure, the path forward (in progress)
The provider question above is being resolved at the district level. A pilot protocol has been requested through the AI Resource Center to reside at the district, and the district plans to stand up a small sanctioned model instance (Claude, and possibly a second such as OpenAI) that approved pilots can call. Because CopaMigo already runs every AI call through a single relay and sends no student data, pointing it at a district-hosted Claude instance is a configuration change, not a rebuild, and it removes any need for a personally-held credential. A district GitHub account has also been applied for, which would host the tool under district control in place of a personal account. Until those are live this is a roadblock and the build stays a prototype. Once they land, this is where CopaMigo runs.
7. Pilot and testing
A pilot is not “launch it and watch.” It is a bounded test with the questions and the yardstick set before any student logs in, so the result can be trusted. This is the sequence, and it is the same shape every tool in this portfolio uses.
- Frame the question first. The pilot has to answer two things: does plain-language triage route students to the right human more reliably than the status quo of a college website, and does the anonymous, no-data architecture hold under real traffic. Everything measured traces back to one of those.
- Set a baseline. Decide what “better” is measured against before launch: today a stuck student either guesses at the right office from a website menu or gives up. Department-reported repeat-question load and a short pre-launch read on how students currently find services give a point to compare against.
- Scope it to one college and get the content owned. One college, GCC Main and North, one semester, Fall 2026 target. Every participating office signs off on its own card content and names a person to keep it current, because a tool that routes to stale hours or a dead number fails the student it was built for. Students are told at the point of the handoff what, if anything, they are choosing to share, which is the consent step.
- Instrument only what is anonymous. Because the tool stores no identity by design, evidence comes from anonymous routing outcomes, an optional thumbs up or down after a handoff card, a counseling-team audit of crisis escalations, and department surveys on repeat-question load. Measure the routing behavior, not satisfaction.
- Run one semester without moving the target. Fix only what is broken during the run and save redesign ideas for after, so it stays possible to tell what produced the result.
- Analyze against the baseline, then decide keep, iterate, or sunset. A pilot that produces a clear negative is a successful pilot. If routing is unreliable, or staff cannot sustain the handoffs, that is a finding that changes the next build rather than a failure to hide.
8. Definition of success
Version 1.0 means the pilot passed and the tool is cleared for rollout. Clear thresholds, not aspirations.
- Students confirm the routing was correct most of the time, on an optional thumbs up or down with no identifying data attached, and the share of questions that end with no service match stays low.
- Crisis routing appears within one exchange, every time, confirmed by a counseling-team audit of escalation conversations.
- Every first-semester course question ends in an advisor prompt, with zero self-advising outcomes and zero fabricated course names.
- Every participating office has signed off on its card content and named an owner, and changes to hours and deadlines appear within a day or two.
- Departments report less repeat-question load, and staff assess the handoff volume as sustainable rather than a new burden.
- Zero incidents of student-identifying data collected, transmitted, or logged. This one is pass or fail, not a percentage.
- The WCAG 2.1 Level AA audit is complete and blocking issues are resolved.
Anything short of that keeps the tool labeled a prototype.
9. Rollout
The pilot is scoped to one college, GCC Main and North, for one semester, with each participating office owning its own card content. If it passes the thresholds above, the same one-codebase deployment extends outward the low-cost way: the standalone page or the embeddable widget goes to additional offices, then to other Maricopa colleges, each bringing its own staff-authored content and named owners. Explicitly out of scope for now: any version that collects student data or requires a login, and any answer authored by the model rather than by staff. Growth is by adding staff-owned content and offices, not by loosening the no-data design.
10. Open questions and risks
- Server-side credential handling. Moving the AI call to a server-side proxy is the one hardening step before any live student use; until it is in place the tool stays a prototype.
- Which sanctioned model backs it. Campus or district Claude, the district Gemini tenant, or the coming district instance is unresolved. The single-relay design makes the swap a configuration change, but the decision is not ours alone.
- Handoff sustainability. Whether staff can absorb the routed students as routine questions fall is a genuine pilot question, not an assumption.
- Content staleness. Stale hours, deadlines, or a dead number would fail the student the tool exists for. Mitigated by a named owner per office, but it is the standing operational risk.
11. Roadmap
Near term and blocking: stand up the server-side proxy so credentials are handled off the browser entirely. Then point the single relay at the district-sanctioned model instance once it is stood up, with a district GitHub account hosting the code. Complete the WCAG 2.1 Level AA audit before any live release. Longer term, and only if the pilot passes, extend to more offices and colleges on the same no-data design, each with its own staff-owned content. Version 2 adds a live link to a human directly from the handoff card, so a student can reach a person in the moment, a warm connection rather than only directions to go find one later.
Appendix A. Service routing directory
This is the full map of what CopaMigo listens for and where it sends each student, transcribed from the tool itself. It is here so Student Services can see everything programmed into the prototype in one place, whatever tool the college ultimately adopts. Every row is a service area the tool recognizes from plain-language input, the kinds of things a student actually types or says, and the office the handoff card points them to. Routing runs on what the student is trying to accomplish, not the keyword they use, and one situation can open more than one card at once.
Each office below has a full handoff card in the tool: a plain-language line on what it does, the exact building and room (campus-aware for Main and North), a map link to that building, the website, hours, phone, what to say when the student arrives or calls, and the specific next step. Crisis and Title IX routing run ahead of everything else, including when raised indirectly.
| Service area | What a student says or asks | Routes to |
|---|---|---|
| Advising | What classes to take next, changing majors, transfer planning, degree-progress checks, new-student advisement. Not for struggling inside a class. | Academic Advisement; Gaucho New Student Advisement for new-to-college students |
| Financial aid | Bills, FAFSA, award letters, book advances, dropped for non-payment, scholarships, payment plans, Pell, SAP, W grades and aid, dropping or withdrawing and its aid impact, refunds, loans, first-time borrowers, DACA and undocumented aid, tuition deadlines, how to read an award letter. | Financial Aid Office |
| Accessibility and disability | ADHD, autism, testing anxiety, learning disabilities, an IEP or 504 from high school, accommodations, extended time, dyslexia, dysgraphia, dyscalculia, physical or mobility needs, Deaf or hard of hearing and interpreter requests (4+ weeks ahead), chronic illness, TBI, PTSD affecting academics. Suspected but undiagnosed also routes to GCC Cares. | Disability Resources and Services (DRS) |
| Counseling | Feeling overwhelmed or anxious, personal or academic distress, wanting to talk to someone, career exploration, crisis walk-in, referral to ongoing community mental-health care. | Counseling |
| Tutoring | Struggling with coursework in any subject, failing tests, lost in a class, don’t understand the material, essay or paper help, citations, study help, after-hours or off-campus help. Talk to the instructor first, then tutoring as backup. | Center for Learning (CL); Math Solution (HT2); Writing Center (HT2); Ask a Librarian; Brainfuse 24/7 |
| Library | Research help, finding sources, citations, databases, academic-integrity citing questions; borrowing a calculator or a short-term laptop; a take-home WiFi hotspot (Main campus only). | Library and Ask a Librarian; Circulation for account questions |
| Basic needs | Food, housing, child care, transportation, emergency funds, textbooks, technology, life circumstances getting in the way of school. | GCC Cares |
| Career | Job search, internships, resume help, what to do after graduation. | Career Services |
| Student life and belonging | Clubs, making friends, belonging, loneliness, campus activities, and identity-based groups (LGBTQ+, cultural, religious, Native American, Latinx or Chicano, and others). | Student Life |
| Fitness and wellness | Gym access, working out, lap swim, group fitness classes, personal training, fitness assessments, adapted fitness, PED credit courses. | Fitness Centers at Main and North |
| AI policy and use | Using AI tools for class, what is allowed, whether AI counts as cheating, GCC’s AI policy, prompt help, which free tool to pick, a syllabus that says nothing about AI. | Direct answer and guidance; recommends the free tools in order Claude, then Gemini, then ChatGPT |
| Accused of AI misuse | A professor flagged their work, being accused of using AI, a grade penalty, worry about a formal process. Kept separate from AI policy questions. | Dean of Students conduct process |
| Dean of Students | Student-conduct matters: cheating accusations, student-to-student harassment that does not rise to Title IX, safety concerns, being accused of academic dishonesty. | Dean of Students |
| Title IX | Sexual misconduct, harassment, or assault; dating or domestic violence; stalking; pregnancy or parenting discrimination. Shown even when raised indirectly; anonymous reporting noted. | Title IX Coordinator (with Crisis if there is immediate danger) |
| Campus safety (non-emergency) | Feeling unsafe on campus, needing a walking escort, lost and found, parking issues, reporting something suspicious that is not an emergency. | GCC Campus Police, non-emergency |
| Crisis | Self-harm, suicidal thoughts, immediate safety risk, a crime in progress, a medical emergency. Answered first, ahead of everything else. | 911 for immediate danger; 988; Counseling for immediate support |
| IT help | MEID, Canvas, student email, Duo two-factor, password resets, campus WiFi (Eduroam), computer labs, borrowing a laptop for the semester. | IT Service Desk (Main 623-845-3555; North 623-888-7124); Maricopa District 24/7 Help Desk |
| Contact and credit hours | How much time a class takes, hours of work outside class, what a credit hour means, how many classes to take, whether a load is too heavy. | Direct answer from the built-in data, then the student’s own course syllabus |
| Saving files | Where to save school files, Google Drive, OneDrive and Microsoft 365, the fact that campus computers erase nightly, submitting video projects. | Direct answer, with the IT Service Desk as fallback for access problems |
| Printing | How and where to print on campus, cost, adding money to a Pay-for-Print account, printing from a personal laptop. | Campus printing and Pay for Print |
| Veterans and military | Veterans, active duty, Guard or Reserve, military spouses and dependents; GI Bill (Chapters 30, 33, 35, 1606, 1607, VR&E), tuition assistance, MyCAA, DEA, Fry Scholarship, the Arizona Purple Heart Waiver; semester benefit re-certification. | Veteran Services Center |
| Bookstore | Textbooks to buy or rent, apparel, supplies, refunds, charge accounts; online ordering with North Campus pickup. | GCC Bookstore, in the Student Union |
| Peer coaching | Staying on track, getting organized, time management, balancing school with work and family, accountability, wanting a mentor to check in with, feeling lost about how to do college. | Peer Success Coach |
| Special populations | High-school students taking college classes (ACE, dual enrollment), current or former foster youth, American Indian or Native American students (American Indian Outreach, Hoop of Learning), immigrant, DACA, or undocumented students, and the Nina Mason Pulliam scholarship. | The one matching Maricopa support program named for the student’s situation |
| Records and registration | Transcripts (official or unofficial), registration help, enrollment verification, name changes, FERPA, residency questions, transferring credits in to GCC. | Admissions and Records, in the Enrollment Center |
| Testing | Course placement testing (Accuplacer, EdReady), CLEP for credit by exam, CELSA for ESL placement, nursing admission tests, the biology assessment, faculty make-up exams, and online or hybrid course exams. | Testing Center (TS3; North Campus in Chinle) |
| International students | International (F-1) students, I-20 questions, study abroad, ESL admission for international students, and in-state tuition for students from Sonora, Mexico. | International Education Office |
Beyond routing: the domain knowledge built in
Alongside the routing above, the tool carries the detailed, verified knowledge each handoff depends on, so a student gets a real first answer and not just a door number. The deepest areas are:
- Veterans and GI Bill. Plain-language triage across GI Bill chapters, the Arizona Purple Heart Waiver eligibility tiers, in-state tuition for recent separations, MyCAA for spouses, benefits paid in arrears, monthly enrollment verification, and every-semester re-certification.
- Disability resources. The step-by-step DRS registration process, why a high-school IEP or 504 does not carry over to college, the documentation typically needed, and the specific accommodations DRS provides.
- Financial aid rules. How dropping or withdrawing affects aid, SAP, book advances, refunds, and how those rules interact with VA benefits.
- The instructor-first rule. A student struggling inside a class is guided to the instructor, then the department chair, then the dean of instruction (Maricopa AR S-6), with tutoring offered as backup.
- Course routing without course names. The tool never names a course from model memory; it links the verified published program checksheet and routes first-semester students to an advisor before they register.
The prototype recognizes more than 100 verified GCC service links behind these cards, and the full source of truth is the tool’s own system prompt, which every answer is drawn from.