Small apps built with AI
Generate a small request-and-approval app with explicit permissions and automatic checks.
Technical
Bachelor’s · applied project
Final result
A working app, access tests and handover documentation.
Material to create
12 approval-app specs × 2 versions
Choose one leave, equipment or expense specification from the proposed set. Define employee/manager/admin permissions and 10 checks: 5 workflow and 5 authorization checks.
Qwen2.5-Coder-7B-Instruct ↗ · Transformers generation settings ↗
What to do
- Build one administrative app from the fixed specification using an existing authentication helper.
How it is tested
Verify workflow and permission requirements with scripted tests and administrator walkthroughs. Plan 4 participant sessions.
Before you start
Example tools · Qwen2.5-Coder-7B-Instruct, Flask, SQLite, pytest These are suggestions; equivalent tools are fine.
Access or people · administrative users, a requirements reviewer, isolated execution and inference compute.
Research method · Build and test · 6 steps
- Read the starting sources and choose one established implementation method.
- Write the requirements, data fields, system diagram and test cases.
- Prepare 12 approval-app specs × 2 versions. Make the answer key and pass criteria before testing.
- Build a working version of a working app, access tests and handover documentation.
- Run function, integration and failure-case tests. Record each result.
- Run the practical evaluation and list the changes the system still needs.
Download the complete bachelor plan
Download bachelor instructionsMaster’s · research project
Final result
App generator, 12 specs and a 24-app comparison.
Material to create
12 approval-app specs × 2 versions
4 leave, 4 equipment, 4 expense workflows; employee/manager/admin roles. Define 10 checks per spec before generation: 5 workflow and 5 authorization checks.
Qwen2.5-Coder-7B-Instruct ↗ · Transformers generation settings ↗
What to do
- Generate paired Flask/SQLite apps under identical model, prompt and token budget, comparing centralized versioned RBAC scaffolding with generated inline authorization.
- Run parameterized direct-request tests across three roles, own/other records and workflow states; keep failed builds and prohibit selective repair.
- Report build and workflow pass rates, horizontal/vertical authorization failures, response leakage and handover decisions; separate security from functional correctness.
How it is tested
Use fixed Qwen Coder revisions and greedy settings; run direct-request checks in isolation. Count workflow passes, prohibited actions and failed builds separately. Four administrative users inspect sampled workflows and explain handover requirements.
Before you start
Example tools · Qwen2.5-Coder-7B-Instruct, Flask, SQLite, pytest These are suggestions; equivalent tools are fine.
Access or people · 4 administrative users, a requirements reviewer, isolated execution and inference compute.
Start with these three actions
- Write one equipment-request specification and its 10 acceptance checks before generating an app. Confirm access to inference compute and record model, software and hardware versions.
- finalise the same Flask/SQLite template, model and decoding settings for both conditions.
- Generate both versions in isolation and validate the permission tests before expanding to 12 specifications.
Files, questions and sources
Pilot question: Do explicit schemas and access rules improve the handover quality of AI-generated approval apps?
Literature search: end user development AI generated applications governance maintenance
Empty CSV templates: data-plan.csv · evaluation.csv · literature-matrix.csv
Download starter instructionsResearch method · Design, build and test (DSR) · 7 steps
- Read the newest papers and list the closest existing systems.
- Write down the versions, fields, data split, case assignment, random seeds and correct answers for 12 approval-app specs × 2 versions.
- Draw the user workflow, data model and system architecture. List the requirements and pass criteria.
- Build a working version of app generator, 12 specs and a 24-app comparison.
- Test every function, connection and failure case. Save the failed tests as well as the passed tests.
- Compare the system with the named alternative. Then run the user task or decision task in the assignment.
- Report the measured result, the failed cases and the design lessons another team can reuse.
Research question and sources
Research question: Investigate whether a fixed authorization scaffold changes the kinds of defects in AI-built apps. Hold model/specification/budget constant; compare scaffolded and generated authorization, then connect test failures to administrator handover decisions.
Research result: Measured security, correctness and ownership results for constrained AI app development.
Current project literature
- A systematic literature review on the impact of AI models on the security of code generation (2024) systematic review
Synthesizes current security risks and review needs for AI-generated code. - Balancing Security and Correctness in Code Generation: An Empirical Study on Commercial Large Language Models (2025) peer-reviewed
Separates functional correctness from vulnerability outcomes in generated code.
IS theory starting points
- Liu et al. (2023) — Is Your Code Generated by ChatGPT Really Correct? — Distinguish passing a public test suite from independently assessed correctness.
- Nissenbaum (2004) — Privacy as Contextual Integrity — Analyse recipient, purpose and information flow rather than treating privacy as a role label.
Search Scopus or Web of Science and ACM Digital Library using the topic query, then follow citations to the thesis start date. Record searches and compare methods, data, findings and limitations in literature-matrix.csv. Use that review to confirm or revise the gap and choose a current comparator. The linked papers are starting points.
Search terms: end user development AI generated applications governance maintenance
Non-technical
Bachelor’s · applied project
Final result
A practical acceptance checklist and handover template.
Material to create
3 fictional apps
Leave, equipment and expenses; recruit 4 administrative users and 4 IT staff. Each packet names data fields, roles and support tasks.
What to do
- Assess whether an AI-built administrative app can be handed over to its owner.
How it is tested
Use the fictional handover packs and task scenarios; list missing ownership, support and access information. Plan 4 participant sessions.
Before you start
Example tools · LibreOffice Writer/Calc, audio recorder with consent; no programming required. These are suggestions; equivalent tools are fine.
Access or people · Recruit both roles; use document examples only.
Research method · Study and improve · 6 steps
- Read the starting sources and write the exact information problem.
- Prepare 3 fictional apps and a separate answer sheet or coding sheet.
- Run one pilot and fix unclear questions.
- Collect the named evidence with consent.
- Group the findings with the stated categories and check the answer sheet.
- Produce a practical acceptance checklist and handover template. List the three most useful changes.
Download the complete bachelor plan
Download bachelor instructionsMaster’s · research project
Final result
Ownership matrix and a handover checklist.
Material to create
3 fictional apps + 8 interviews
Leave, equipment and expenses; recruit 4 administrative users and 4 IT staff. Each packet names data fields, roles and support tasks.
What to do
- Prepare request forms, approval rules and handover documents for three small apps.
- Interview staff about who should own, approve and maintain each app.
How it is tested
Interview 4 administrative users and 4 IT staff using non-overlapping packs with clear or missing ownership. Compare deployment conditions and responsibility gaps; code access, testing and maintenance disagreements.
Before you start
Example tools · LibreOffice Writer/Calc, audio recorder with consent; no programming required. These are suggestions; equivalent tools are fine.
Access or people · Recruit both roles; use document examples only.
Start with these three actions
- Prepare a pilot with 2 examples from: 3 fictional apps + 8 interviews. Write the task questions and a reference answer sheet.
- Write a recruitment message, information sheet and consent form for the participants named above. Agree privacy handling with the supervisor before contact.
- Pilot one session after approval; revise unclear questions, finalise the task sets and coding categories, then recruit the planned sample.
Files, questions and sources
Pilot question: Where do administrative users and IT staff disagree about ownership of a small app?
Literature search: end user development AI generated applications governance maintenance qualitative scenario study
Interview prompts
- Who owns this app after delivery?
- Who approves access changes and tests releases?
- What must be documented before a colleague can maintain it?
Empty CSV templates: study-plan.csv · coding-sheet.csv · literature-matrix.csv
Download starter instructionsResearch method · Study, compare and explain · 7 steps
- Read the newest papers and write one exact research question.
- State which people, cases or documents you will study and what you will compare.
- Write the selection rules, questions and analysis steps for 3 fictional apps + 8 interviews.
- Run one pilot. Fix unclear questions or categories, then keep the guide unchanged.
- Collect the named interviews, cases or documents with consent.
- Analyse them with the stated comparison or coding method. Keep disagreements and missing data.
- Report the answer, the evidence and the practical output named in the assignment.
Research question and sources
Research question: Explain why a working demonstration may still be unacceptable to its future owner. Compare developer and administrator expectations about support, permissions and responsibility across fixed handover packs.
Research result: A theory-based model of acceptance and ownership gaps in AI-built apps.
Current project literature
- A systematic literature review on the impact of AI models on the security of code generation (2024) systematic review
Synthesizes current security risks and review needs for AI-generated code. - Balancing Security and Correctness in Code Generation: An Empirical Study on Commercial Large Language Models (2025) peer-reviewed
Separates functional correctness from vulnerability outcomes in generated code.
IS theory starting points
- Orlikowski & Gash (1994) — Technological Frames — Compare how roles interpret the purpose, operation and use of the same system.
- Nissenbaum (2004) — Privacy as Contextual Integrity — Analyse recipient, purpose and information flow rather than treating privacy as a role label.
Search Scopus or Web of Science and ACM Digital Library using the topic query, then follow citations to the thesis start date. Record searches and compare methods, data, findings and limitations in literature-matrix.csv. Use that review to confirm or revise the gap and choose a current comparator. The linked papers are starting points.
Search terms: end user development AI generated applications governance maintenance qualitative scenario study
Your degree, track and shortlist are saved in this browser.