OCMD AI Explorers Summer Camp - Grades 6-8

OC Music & Dance (OCMD), in partnership with Pacific Solutions

501(c)(3) community arts and technology education center

Irvine, Orange County, Southern California, USA

Lead Master Coach supported by trained Assistant Coaches under a two-deep adult staffing model

• On-site nonprofit community program
• Summer day camp

Seven-day intensive; morning cohort from 9:00 AM to 12:00 PM

August 1-8, 2026; approximately 19.5 contact hours

20 enrolled students

One program-provided Mac laptop per learner on a password-protected network

• No individual student vendor accounts
• No direct minor access to third-party AI APIs
• All prompt runs required coach review
• Twenty parallel prompt iterations created queue-throughput pressure

Grades 6-8, approximately ages 11-14

No prior AI experience required

No programming prerequisite reported

15 of 20 had perfect attendance; 19 of 20 attended at least five days; 18 of 20 attended the Day 7 showcase; 16 matched pre/post survey pairs

• Direct AI systems rather than consume outputs passively
• Use the 4 Rs prompting framework: Role, Rules, Realness, Reliability
• Evaluate AI outputs for logic, bias, hallucinations, and reliability
• Apply ethical norms, copyright awareness, and transparent AI-use disclosure

• Create text, images, video, custom assistants, decision trees, and a small web tool
• Use human checkpoints in automated workflows
• Present a capstone explaining human decisions and AI contributions

• Not unsupervised access to commercial AI services
• Not a controlled efficacy trial
• Not a programming or machine-learning theory course

Coach-operated text, image, video, automation, and AI-assisted coding tools

• Claude
• ChatGPT
• Gemini and Veo
• HTML and JavaScript vibe-coding templates

• Generative partner
• Object of critical evaluation
• Support for multimodal creation and prototype building

• Students composed prompts in a de-identified workspace
• Coaches reviewed prompts with a Sideline Check before execution
• Coaches ran approved prompts and returned outputs for student iteration

• Coach Proxy Model
• Fictional Character Default
• Personal-data redaction
• Parent or guardian acceptable-use consent
• Human review before output display
• Scheduled 180-day data purge

• Day 1 foundations and orientation
• Day 2 structured prompting
• Day 3 image generation and art direction
• Day 4 video and custom assistants
• Day 5 automation and AI-assisted building
• Day 6 ethics, trust, and critical thinking
• Day 7 learning-partner reflection and capstone showcase

• Students set goals, composed prompts, evaluated outputs, and made creative decisions
• Coaches approved and executed prompts, checked outputs, and documented incidents
• AI systems generated drafts and media within human-defined constraints

• Video-debrief-practice rhythm
• Worked examples and pre-filled templates
• Four-step Compose, Review and Run, Return, Iterate loop
• Success criteria and 4D competency tags

• Managing 20 parallel prompt iterations without stalling classroom momentum
• Sustaining attention during technical debriefs
• Moving students beyond vague two-word prompts
• Late arrivals, pacing issues, and generation lag
• Students sometimes reached quizzes before assigned videos

• Split prompt approval and execution duties across coaches
• Added worked examples and structured prompt templates
• Disabled unnecessary communication features
• Corrected lesson sequencing on the course website
• Recommended a longer orientation, better audiovisual support, reference images, and quick student-work showcases

• 19 of 20 learners attended at least five of seven days
• 18 of 20 attended the Day 7 showcase
• 16 learners completed matched pre/post evaluations

• Average accuracy across objective AI scenarios rose from 69% to 80%
• Admissions and tutoring model-bias accuracy rose from 31% to 69%
• Self-efficacy for writing effective prompts rose from 3.20 to 4.22
• Self-efficacy for improving prompts strategically rose from 3.25 to 4.35

• Habitual output verification remained approximately flat
• Results are descriptive and based on matched participants, not a randomized comparison
• Parent pre/post samples differed in size

• Learners used de-identified seat codes rather than names
• No learner held a personal commercial AI account
• Real-person likeness or voice generation required separate signed consent
• Raw creative outputs, media, and school records remain withheld from public release
• Student workspaces are scheduled for deletion 180 days after camp

• Two-key student pledge and parent consent
• Fictional Default guardrail
• Human-in-the-loop review
• Incident and hallucination logging
• Required disclosure statement for final presentations

• De-identified student workspace
• Private coach compliance ledger
• Observer and coach feedback
• UCI interim matched pre/post evaluation dataset
• Daily physical attendance records
• Capstone showcase presentations

• Coach-mediated generative AI instruction for learners near commercial tool age floors
• Comparison of physical attendance and survey retention
• Operational use of the 4D AI Fluency Framework
• Human-review throughput in multi-learner classrooms

• AI literacy
• Learning sciences
• Educational technology
• Child privacy and online safety
• Human-in-the-loop AI governance

• Completed
• Approved for public registry publication
• Aggregate and de-identified disclosure only

• AAB-PILOT-2026-AI_Explorer_Program-001
• AAB-PILOT-2026-OCMD-001

Grades 6-8

Community-based summer camp

Generative AI, multimodal generation, automation, and AI-assisted coding

Coach-mediated guided practice and project-based capstone

Moderate with documented controls

Low to moderate; de-identified learner work and evaluation data