AI Smart Seasoning Machine
A student prototype exploring repeatable dispensing, guided cooking, taste preferences and responsible kitchen interaction.
- GROWTH TREE
- 4 stages · 6 learning nodes
- SUMMER COMPETITION
- Award information pending
Start with what the project must do. BIAA then maps the system, prerequisites, team roles, learning modules, hands-on outputs and evidence needed to move from an idea to an integrated prototype.
Bring the project goal, learner starting point and team size; BIAA can then assess what a responsible learning map would require. No data is submitted from the demo above.Active recruitment means learners may register interest; it is not acceptance. Roles, timing and mentor arrangements remain subject to project confirmation.
A student prototype exploring repeatable dispensing, guided cooking, taste preferences and responsible kitchen interaction.
A research-stage desktop haptic system for studying guided writing, sensing and progressively reduced assistance.
A consent-led biography, archive and traceable memory-agent project that preserves sources without claiming digital resurrection.
A controlled-environment robotics project exploring collision tolerance, sensing, communications, recovery and auditable inspection evidence.
A service-design and learning-platform project about healthy ageing literacy, lifelong learning and non-diagnostic support.
A whole-room learning robot concept combining mobility, environment sensing, document capture and privacy-bounded learning support.
An upcoming agriculture-robotics study of pollination biology, perception, gentle manipulation and controlled flight.
An upcoming indoor-robotics project about safe navigation, scheduled care, animal welfare and household privacy.
An upcoming controlled-environment project combining fungal biology, sterile practice, sensing, automation and cautious image analysis.
Stage one prioritises verifiable public information and low-risk participation routes. Accounts, uploads and AI generation require identity, permissions, retention and child-safeguarding controls before stage two can be enabled.
Project library, mentor framework, pitches, competition archive, news and local project briefs.
Accounts, material uploads, AI slide and business-plan generation, and mentor review workspaces. The current version does not collect, upload or store user materials.
Design a small inspection-robot prototype that moves in a controlled test environment, records sensor data and flags possible anomalies for human review.
Filtering changes the learning view only. At integration, every role still hands off evidence through defined interfaces.
What are we really building?
What must each role understand first?
Can each part work and be explained?
Does the whole system meet the evidence bar?
Create a one-page system boundary and acceptance table.
Keep the prototype inside a controlled learning environment.
Copy a structured study prompt into OpenAI, Metaso or another learning assistant. It asks the AI to diagnose foundations, teach in steps and require artefact evidence instead of completing the whole project for the learner.
Contains no name, contact detail or learning record.BIAA project-node study prompt Project: Pipe Guardian learning-system demo Node: SYS–01 — Problem, user and system boundary Role: Systems & product Prerequisite nodes: None Learning goals: - Separate needs, assumptions and constraints - Write observable success criteria Hands-on task: Create a one-page system boundary and acceptance table. Evidence required: - Every criterion can be tested - Out-of-scope conditions are explicit Safety boundary: Keep the prototype inside a controlled learning environment. Act as a patient engineering learning coach. First ask 3–5 short questions to diagnose my starting point. Then teach one concept at a time using questions, a small example and a mini-check. Do not complete the entire project or fabricate results for me. Keep hardware, data, AI and minor-safety boundaries explicit. Before moving on, ask me to show the required artefact or evidence, explain it in my own words and identify one limitation. End each exchange with exactly one next action.
System boundary, interface table and integration checklist.
Mechanical envelope, wiring map and measured sensor ranges.
Control states, tested functions and readable source notes.
Data dictionary, baseline method and error analysis.
Risk register, test records and evidence-based review.
A project brief sets the user, purpose, constraints, test environment and responsible-use boundary. Only then is it decomposed into mechanics, electronics, software, control, data, AI, integration, safety and communication. This keeps each course node connected to a real technical decision rather than an isolated topic.
A node states the concept to master, the earlier knowledge it depends on, a small build or investigation, the evidence required for review and the safety boundary. A structured prompt can then be copied into OpenAI, Metaso or another learning assistant. The assistant supports questioning and explanation; the learner still makes, tests and documents the work.
The Pipe Guardian example is labelled as an Academy prototype and learning-system demonstration. It does not represent a field-ready inspection product, a completed learner outcome or a promise of performance. Project details, tool access and assessment arrangements must be confirmed before any formal programme is offered.
Bring the project goal, learner starting point and team size; BIAA can then assess what a responsible learning map would require. No data is submitted from the demo above.