← Home
← Back to portfolio

Render

Product Requirements Document · Career Launch Dashboard

A student-facing AI career readiness tool for Digital Media Arts graduates

Version: 0.5 · Status: Usability Testing · June 30, 2026

Michelle B. · Digital Media Arts Faculty · Glendale Community College

1. Executive Summary

The Problem

Creative students at community colleges graduate with strong portfolios but no systematic plan for using them. They lose Canvas access after graduation, and with it, all their coursework, with no career launch infrastructure in place.

The typical result: students graduate, say “now what?”, and lose momentum at the most critical moment of their career launch.

The Solution

Render is a personal learning environment (PLE), a student-facing AI career space populated during AVC 248 (Design Self Promotion at GCC) and owned by the student after graduation. It is connectivism in practice: one place the student owns where goals, work, skills, and connections live together rather than scattered across a course that ends.

Students don’t face a blank AI prompt, they interact with a structured environment designed for their specific situation, anchored to one real reach job they choose on day one. The PLE’s final layer is a portable career agent and personal learning plan: Render does not get replaced by the agent, Render builds the agent.

By graduation, students leave with a fully populated career launchpad: goals, job search strings, links, resume drafts, job search history with cover letters, skills gap analysis (software, professional skills, and industry workflows), networking contacts, interview practice, a personalized weekly schedule, and a 90-day professional development plan, all exported as a standalone HTML file they own forever. They also leave with the capstone output of the PLE: a portable career agent and personal learning plan, a Markdown file derived from a gap analysis between what they built and their day-one reach job, aligned to the goals they set at the start, that runs in any AI tool (Claude, ChatGPT, and others) and that they keep iterating.

1.1 Audience

Who Render is for

Render is built for students launching their careers. The core audience is community college students using it for career readiness as they finish a creative program and step into the job or freelance market. They are not seasoned job seekers. They are early-career people who need structure, not a blank prompt.

It is built in partnership with campus Career Services, so the tool reinforces the same guidance students would get from a career advisor rather than competing with it. Career Services benefits from anonymous, aggregated employer interest data that helps them build internship pipelines.

Render is anonymous by design. It collects a first name only. No email, no student ID, no address, no phone number. There is no personally identifiable information in the tool, and resume drafts are kept free of contact details until the student sends a resume out.

2. Product Vision

2.1 Vision Statement

What if students left your course not just with completed assignments, but with a personal learning environment they built themselves, and a career agent that environment generated, that they keep using in any AI tool?

Render is the answer to “now what do I do?”, a personal learning environment (PLE) that students build incrementally across a semester and take with them when they graduate. The pedagogy is connectivism: a PLE is a space the learner owns where goals, work, skills, and professional connections live in one place and keep developing. Render is one big version of that environment, with the career agent and personal learning plan as its final export. The student does not graduate from Render into a separate tool, Render builds the tool. Product 2 is not a static export, it’s a personal dashboard students continue to update as their career develops after graduation.

2.2 The PLE-to-Agent Arc

Stage What happens in Render 1 · Day one The student sets robust goals, guided by the right questions, and picks one real reach job as their anchor. Every later module aligns to that anchor. 2 · All semester Render runs alongside the whole AVC 248 capstone as the student’s launchpad: profile, goals, job log, resume vault, skills tracker, networking, interview prep, every module aligned to the reach job. 3 · Capstone Render analyzes the gap between what the student actually built and what the reach job requires, then generates a portable personal learning plan and career agent: a Markdown file aligned to the day-one goals. 4 · Take-with-you The student leaves with Render itself (data and dashboard, exportable and owned) and the agent and learning plan, which runs in any AI tool (Claude, ChatGPT, and others) and which they keep iterating.

2.2.1 Assessment Model, Formative and Summative

Render runs on a deliberate assessment arc. All semester it works as ongoing formative assessment: every real job a student saves refreshes a running read of where they need to tool up, and the skills-gap analysis, tailoring iterations with student reflection, interview coaching, instructor feedback on drafts, and Diagnose Your Search panel all feed low-stakes, improvement-focused signals the student acts on while there is still time to close the gap. At the capstone, that accumulated evidence becomes a summative synthesis: Render compares everything the student built against their day-one reach job and generates a personal learning plan and portable career agent. The plan does not end at graduation. The companion Training Plan Agent keeps running on a weekly loop, checking the student’s progress against the plan, and when a skill is demonstrated well enough it promotes that skill onto the resume the student will use to land the job. Formative all semester, summative at the capstone, and formative again for life.

2.3 Two-Product Architecture

# Product Purpose Status 1 In-Class Gathering Interface Structured data entry tool used during AVC 248. Students populate it week by week as assignments are completed. AI assists with analysis, cover letters, search strings, and coaching. ✓ Built 2 Post-Graduation Dashboard + Career Agent A persistent, updatable career dashboard exported from Product 1, plus the PLE’s capstone layer: a portable career agent and personal learning plan (Markdown) derived from the day-one reach-job gap analysis, runnable in any AI tool. Students continue to use and update both after graduation. 4 color themes. No login required. Includes weekly schedule and PD plan. Students own it forever. ✓ Built

3. Users & Context

3.1 Primary Users

User Context Needs from Render DMA Students Finishing AVC 248. Portfolios done. May be seeking employment, freelance clients, or both. Structured guidance, not blank prompts. Somewhere to put work they’ve already done. A plan for what comes next. Animation Students Portfolio-focused. Targeting studios, production companies, streaming platforms. Reel is primary job search tool. Reel link prominent. Industry-specific job analysis. Animation software skill tracking. Photography Students Mix of commercial and fine art. Client-finding as relevant as job-searching. Instagram and portfolio site are key. Freelance client track. Social media links. Commercial vs. editorial distinction. Video Production Targeting agencies, corporate video, broadcast, or building a freelance production company. Both tracks relevant. Reel + portfolio. Spec sheet and contract templates. UX Design Students Most likely pursuing employment at tech companies. Case study portfolio is critical. LinkedIn is primary platform. Job search focus. Case study links. UX-specific skill gap analysis. Instructor (Michelle B.) Runs AVC 248. 24 students. Wants Career Services to benefit from the data. Instructor settings panel. Google Sheet pipeline to Career Services. No FERPA-sensitive data transmitted. Career Services (GCC) Wants employer intelligence to build internship pipelines and employer relationships. Anonymous aggregated data: employer names, job titles, programs. No student names or MEIDs.

3.2 Course Context

4. Features

Everything in this section is built and in the current prototype. Planned, not-yet-built work lives in the Roadmap and Future Enhancements sections. The “When in the course” column shows when each capability is used during the 15-week AVC 248 semester, since Render is course-embedded.

Feature area When in the course What it does Profile + Goals + Links Hub + Search Strings Weeks 1–3

First name only, no email, no MEID, no personally identifiable information collected. Program selection, employment/freelance track (both can be active simultaneously), weekly commitment sliders, links hub (LinkedIn, Behance, portfolio, reel, Instagram, GitHub), goals & identity statements, dream job/client, target market, 3-year vision. Day one of the PLE: guided questions help the student set robust goals and pick one real reach job as their anchor, the target every later module aligns to and the basis for the capstone gap analysis. A Guided Goals Builder walks the student through targeted questions (role, industry, setting, location, day-to-day work, timeline, values, and pay range) and assembles a strong goals statement, so day-one goals are specific rather than two vague sentences.

AI Search String Generator: Based on the student’s goals and target market, generates ready-to-paste search strings optimized for LinkedIn, Indeed, Glassdoor, and Google site: searches. Each string has an individual copy button. Saved to localStorage and included in the Product 2 export.

Job / Client Log Weeks 2–13

Employment tab: paste job description, AI skills gap analysis, AI cover letter generation, status tracker (Saved → Applied → Interview → Offer/Pass). Full job description, resume edits, and cover letter stored together per entry.

Freelance tab: describe ideal client type, AI generates search strategies + 8–10 real prospect names, outreach guidance, pricing check.

Career Services transparency notice: When a student saves a job entry, Render sends the employer name, job title, and program area to a shared Google Sheet. Career Services uses this data to identify employers students are interested in, build relationships with those companies, and pursue official internship opportunities. No student names or personal information are included.

Resume Vault Weeks 4–9

Base resume drafts (1st–4th) and a base cover letter field, with instructor feedback fields and an active resume flag. Base materials rule: the first resume and first cover letter are written by the student, by hand, in a plain Google Doc or Word, no AI, no template, then pasted in. AI tailors later, never writes the first version. Each job entry holds tailored AI resume edit suggestions alongside the cover letter.

Privacy note displayed to students: Resume drafts in Render should not include your name, address, phone number, or other personal contact information. When you are ready to send a resume to an employer, add your contact details to the version you send, but keep them out of Render.

Skills & PD Weeks 5–13

Software stack checklist by program (6 categories, ~60 tools). Skills-to-build list, add manually or pull gaps from saved job entries via AI.

Gap analysis now surfaces professional skills and industry workflows (project management, client presentations, creative briefs, production planning, budget management) alongside software tools. Named free learning resources (specific YouTube channels, Coursera courses, Adobe tutorials). Portfolio project idea generator. PD activity log.

Across the semester this functions as formative assessment: each saved job refreshes a running read of where the student needs to tool up, so gaps surface early enough to act on rather than at the end when it is too late to close them.

Networking Tracker Weeks 11–12 Contact log with type tagging (mentor, employer, peer, alumni, industry). Outreach status tracker. AI drafts personalized LinkedIn connection requests under 300 characters. Redraft capability per contact. Interview Prep Week 13

Role-specific questions generated from saved job descriptions. General questions by role type. Answer practice with AI coaching feedback (coach, not cheerleader). Saved Q&A log. Big Interview integration.

Thank-you / follow-up note generator: after an interview or application, AI drafts a short, specific thank-you or follow-up note in the student’s voice, with timing guidance (when to send the post-interview thank-you, when to follow up if you haven’t heard back). No PII enters AI, the note is a plain-text draft the student personalizes and sends themselves.

Launch Plan + Career Agent (Capstone Export) Week 15

The PLE’s final layer. AI 90-day professional development plan generator based on all student data. Semester stats at a glance.

Career Agent & Personal Learning Plan: Render analyzes the gap between what the student actually built across the semester and the requirements of their day-one reach job, then generates a portable career agent and personal learning plan as a Markdown file aligned to the goals set on day one. The student takes it into any AI tool (Claude, ChatGPT, and others) and keeps iterating. Render does not get replaced by the agent, Render builds it.

Training Plan Agent. This capstone gap analysis is the summative synthesis of a semester of formative gap-finding. A companion Training Plan Agent turns the gaps collected from the student’s real saved jobs into a sequenced 90-day learning plan, mapping each gap to a specific, low-cost resource (named YouTube channels, Coursera and Adobe courses, freeCodeCamp, and the AVC 248 AI unit). It keeps running after graduation on a weekly loop: it checks the student’s progress against the plan, and when a skill is demonstrated well enough it promotes that skill onto the resume the student will use to land the job, so the plan stays a living document tied to real job-search goals. Prototype: render/training-plan-agent.html.

AI Weekly Schedule Builder: Generates a concrete Monday–Sunday time-blocked schedule based on the student’s committed hours, goals, skill gaps, and job targets. Includes specific activities, platforms, networking touches, and a Sunday review block.

Product 2 export with 4 color themes (Floral, Studio Dark, Clean Minimal, Bold Editorial). Export includes search strings, weekly schedule, and the career agent / personal learning plan Markdown.

Tailor This Application + Base Materials + Critical AI Review Weeks 4–13

Base Materials rule. Render adds a base cover letter field alongside the base resume drafts, and enforces a hard rule: the student’s first resume and first cover letter are written by the student, by hand, in a plain Google Doc or Word, no AI and no template, then pasted into Render. AI never writes the first version. AI only tailors later, once a real base written in the student’s own voice exists. The Tailor flow refuses to run until a base resume and base cover letter are present.

Tailor This Application flow. For a saved job, Render first shows the job-match read (skills match, gaps, positioning, red flags), then takes the saved job description plus the student’s active base resume plus their hand-written base cover letter and produces tailored first drafts of both. A built-in iteration loop lets the student re-prompt by naming exactly what to change, and a reflection field captures what the student learned and what they edited. The flow preserves the student’s voice, invents nothing (no fabricated jobs, skills, or metrics), returns plain text only, and contains no PII.

Critical AI Review checklist. A checklist renders under every AI output, Accuracy (is every claim true), Voice (does it still sound like you), Proof (can you back it up), Format (is it formatted in your own document, not pasted raw), and Fit (does it answer this specific job), plus a “format it yourself, this is plain text” reminder and a clean-text copy button so the student moves the output into their own Google Doc or Word to format. Students never submit a first AI draft.

Application Support Materials Weeks 7–14

References sheet builder. Students assemble a clean, professional references sheet that matches their resume styling, kept free of personal contact details inside Render until they send it.

Online presence audit checklist. A guided checklist for auditing what an employer sees when they search the student: LinkedIn, portfolio, public social accounts, and Google results, with cleanup actions and privacy steps.

Salary research helper. AI guidance (no PII) on researching realistic pay using BLS, Glassdoor, Levels.fyi, and Built In, plus coaching on how to answer the salary-expectations question with a researched range rather than a single number or a blank.

Job Search Loop home + Diagnose Your Search Weeks 1–15

Job Search Loop home view. The home view frames the whole tool as one repeatable 10-stage system the student runs for every job, target, build base materials by hand, find roles, then for each job research / tailor / iterate / apply / log, follow up, network, prep for interviews, track the pipeline, and diagnose, a loop the student keeps running after graduation with Render and their career agent.

Diagnose Your Search panel. A rules-based funnel diagnosis reads the student’s own logged activity (applications sent, responses, interviews) and tells them where the search is stalling and what to change, with an optional AI deeper dive for a more detailed read. No PII enters AI.

“How to use this section” directions. Every data-entry section now opens with thorough, professional directions explaining what to put there, why it matters, and how it connects to the rest of the search, so students never face a blank field without guidance.

5. Data Architecture & Privacy

5.1 Student Privacy Commitment

Student Privacy Commitment

Render collects only a first name, no email, no student ID, no address, no phone number. Students are understandably skeptical about AI tools and data collection. Render is designed to earn trust by collecting the absolute minimum and being transparent about what happens with every piece of data.

Resume drafts stored in Render should not include personal contact information. A visible note reminds students: “When you’re ready to send this to an employer, add your name and contact info to the version you send, but keep them out of Render.”

Job search entries trigger a transparent notification: students are told that employer name, job title, and program area are shared with Career Services so they can build employer relationships and pursue internships on students’ behalf. No student-identifying information is included.

5.2 Data Storage

All student data in the current prototype is stored in browser localStorage, data stays on the student’s own device. This is intentional for the pilot semester.

5.3 FERPA Considerations

Data Type Where It Goes FERPA Status First name only (no email, no MEID, no address), goals, job history, resume text (without personal contact info) Browser localStorage only, stays on student’s device ✓ Safe, never transmitted Employer name, job title, URL, interest level, program area Google Sheet via Apps Script (Career Services pipeline) ✓ Safe, no student identifiers Full student data export (JSON) Student’s own Google Drive, they control it ✓ Safe, student owns data Future: full cloud sync Maricopa Google infrastructure or school server ⛑ Requires FERPA agreement, not yet implemented

5.4 Career Services Pipeline

When a student saves an employment job entry, Render sends an anonymous row to a Google Sheet via Google Apps Script. Career Services uses this data to identify employers students are interested in, build relationships with those companies, and pursue official internship and job placement opportunities.

Data sent to Career Services Google Sheet

Date · Employer Name · Job Title · Job URL · Interest Level · Program Area

NOT sent: student name, first name, or any personally identifiable information.

Why Career Services receives this data: GCC Career Services uses employer data from Render to identify companies students are interested in, build relationships with those employers, and pursue official internship and job placement opportunities for current and future students. Students are told this when they save a job entry.

6. Technical Specification

6.1 Current Stack

6.2 AI Functions

Model: claude-sonnet-4-20250514. All calls include student profile + goals as context. No PII enters any AI call, and AI outputs are plain text. 20 functions total:

AI Function Input Output analyzeWithAI() Profile + goals + job description Skills match, gaps, positioning advice, red flags generateCoverLetter() Profile + job desc + analysis Tailored 3-paragraph cover letter sendToSheet() Job description (up to 1500 chars) 2–3 sentence summary to Career Services sheet getResumeEdits() Active resume + job description Specific resume edits for this job pullGapsFromJobs() Saved job descriptions (up to 6) 8–12 skills: software, professional, workflows getRecommendations() Profile + skills gap list Named free learning resources getProjectIdeas() Profile + targets + gaps 5 portfolio project ideas with time estimates draftLinkedInMessage() Contact info + notes Personalized connection request under 300 chars redraftMessage() Contact + previous message Fresh message for existing contact generateInterviewQuestions() Profile + job description 10 role-specific questions generateGeneralQuestions() Profile + role type 8 questions for any creative role getFeedback() Question + student answer What’s working, what to improve, stronger version generatePDPlan() All student data + hours + focus Personalized 90-day plan generateSearchStrings() Goals + dream job + market Copy-paste strings for LinkedIn, Indeed, Glassdoor, Google buildWeeklySchedule() Hours + goals + gaps + targets Mon–Sun time-blocked schedule generateCareerAgent() All student data + day-one goals + reach job Portable career agent / personal learning plan (Markdown) from the reach-job gap analysis tailorApplication() Job desc + active base resume + base cover letter + match read Tailored first drafts of resume + cover letter in the student’s voice, plain text, invents nothing generateThankYou() Job + interview/application context Short thank-you / follow-up note in the student’s voice, with timing guidance researchSalary() Role + market (no PII) Realistic pay range from BLS / Glassdoor / Levels.fyi / Built In + how to state expectations diagnoseSearch() Logged funnel activity (applications, responses, interviews) Optional AI deeper dive on where the search is stalling and what to change

7. Product 2, The Render Dashboard + Career Agent

7.1 Overview

Product 2 is the persistent career dashboard students keep and continue to update after graduation, plus the capstone output of the PLE: the career agent and personal learning plan. Generated from data accumulated in Product 1. Students can no longer access Canvas after graduation, Product 2 is what they own and control going forward. Like Cultivate (the faculty version), it functions as a personal learning environment that grows with the student, not a static export.

Includes: goals, search strings, links hub, job search log with cover letters and resume edits, active resume, skills map with gaps and learning resources, PD activity log, network contacts, interview Q&As with AI feedback, 90-day PD plan, weekly schedule, and semester stats.

7.1.1 Career Agent & Personal Learning Plan, the capstone export

The final layer of the PLE. At capstone, Render runs a gap analysis between everything the student built across the semester and the requirements of the reach job they anchored on day one, then generates a portable career agent and personal learning plan as a Markdown file aligned to those day-one goals. The student carries it into any AI tool (Claude, ChatGPT, and others) and keeps iterating it as their career develops. This is the heart of the model: Render does not get replaced by the agent, Render builds the agent. The PLE is the launchpad, the agent is what it launches. Privacy is preserved, the agent is built from the student’s own anonymous data, and no student PII enters AI.

Pedagogically, this is the summative synthesis of a semester of formative gap-finding, and it stays formative afterward. The Training Plan Agent sequences the collected gaps into a 90-day plan and runs a weekly check on the student’s progress, promoting each skill onto their resume once it is demonstrated well enough, so learning continues alongside the live job search rather than stopping at graduation.

7.2 Theme Options

Product 2 includes 4 customizable color and typography palette options:

# Theme Colors Typography 1 Floral (default) Plum, sage, rose, gold on warm paper, matches AVC 248 site Lora + DM Sans 2 Studio Dark Near-black, warm white, electric accent, editorial/agency feel Playfair Display + DM Sans 3 Clean Minimal White background, charcoal type, single accent, corporate/tech Inter + Inter 4 Bold Editorial High contrast, large type, strong blocks, motion/entertainment Bebas Neue + DM Sans

Sample dashboard with realistic fake data: singletrackmom.github.io/render/sample-dashboard.html

8. Testing Status

The full tool is built. Prototype being tested with a group of 4 students for usability. Career Services feedback ongoing with Mollie. Tool is integrated into AVC 248 course competencies. Pilot deployment planned for Fall 2026.

9. Open Questions

Question Priority Notes How should authentication work long-term? First-name-only approach is ideal for privacy but limits personalization. High Personal email + password on a real server is the most likely path. Must preserve the no-institutional-ID principle. Where does student data live after pilot? localStorage is device-specific and not durable. High Server-side storage needed. Current workaround: JSON export/import via Google Drive. Should the tool be shared across MCCCD or remain GCC-specific? Medium Architecture is already abstracted. Course-specific references are minimal. District-wide deployment viable after pilot. Does Career Services want to actively manage the Google Sheet, or just receive a report? Medium Determines how the pipeline is structured and whether a notification system is needed. Should there be an instructor view showing class-wide progress? Low Useful for grading and engagement tracking. Requires explicit student consent for FERPA compliance.

10. Roadmap

Milestone Target Notes Full tool built June 2026 ✓ Profile, Goals, Links Hub, Search Strings, Job/Client Log, Resume Vault with base cover letter, Skills & PD, Networking, Interview Prep with thank-you / follow-up notes, Launch Plan with weekly schedule and 90-day PD plan. Plus the Tailor This Application flow, Base Materials rule, Critical AI Review checklist, references sheet, online presence audit, salary research, the Job Search Loop home view, and the Diagnose Your Search panel. Product 2 export with 4 themes. Usability testing March–April 2026 4 students in usability testing group. Career Services feedback ongoing with Mollie. Pilot, AVC 248 Fall 2026 First full semester deployment with live students. Tool integrated into AVC 248 course competencies. Feedback collection and iteration. Google Drive auto-sync Post-pilot Cross-device data transfer without manual export/import. Canvas LTI integration Post-pilot Embed Render inside Canvas rather than as a separate link. Industry news feed Post-pilot Curated RSS sources tailored to each student’s program track (~8–12 sources per track). MCCCD district-wide adaptation Post-pilot Deployment for other DMA programs across the Maricopa district.

11. Future Enhancements

Appendix: Key References