← All proposals
Illustration: Software-development information-system concept: An assistant that knows its boundaries

Permissions for coding-assistant search

Prevent a coding assistant from retrieving documents the current user is not allowed to read.

Download brief

Technical

Bachelor’s · applied project

Final result

A permission-aware search demo and exhaustive policy tests.

01

Material to create

30 fictional documents, 3 roles, 60 queries

Ten documents per project. Define membership and copied-content rules; label authorized relevant IDs for all 180 role/query pairs, including empty-access cases.

02

What to do

  • Build document search that filters results using a fixed role-permission matrix.
03

How it is tested

Use the fictional repository documents and role-labelled queries; test allowed retrieval and prohibited content/identifier leakage. Plan 4 participant sessions.

04

Before you start

Example tools · Python, BM25 library, Streamlit, pytest These are suggestions; equivalent tools are fine.

Access or people · IT participants and one independent policy reviewer.

Research method · Build and test · 6 steps
  1. Read the starting sources and choose one established implementation method.
  2. Write the requirements, data fields, system diagram and test cases.
  3. Prepare 30 fictional documents, 3 roles, 60 queries. Make the answer key and pass criteria before testing.
  4. Build a working version of a permission-aware search demo and exhaustive policy tests.
  5. Run function, integration and failure-case tests. Record each result.
  6. Run the practical evaluation and list the changes the system still needs.
Download the complete bachelor planDownload bachelor instructions

Master’s · research project

Final result

Access-controlled search, permission fixtures and leakage report.

01

Material to create

30 fictional documents, 3 roles, 60 queries

Ten documents per project. Define membership and copied-content rules; label authorized relevant IDs for all 180 role/query pairs, including empty-access cases.

02

What to do

  • Implement BM25 with a versioned RBAC matrix and deny-by-default pre-filtering; compare with global top-5 then filter/no-refill on the identical index.
  • finalise tokenizer/BM25 parameters and exhaustively test all 180 role-query pairs, including empty-access cases; keep no-filter and project-only modes as negative controls.
  • Require zero unauthorized text, IDs, titles and citations; report authorized recall@5, nDCG@5, false denial, policy latency and denial comprehension.
03

How it is tested

Measure unauthorized text/IDs/citations and authorized-document recall. Project-only filtering is an additional negative control. Four IT users interpret denials and escalation options; score comprehension against the written policy.

04

Before you start

Example tools · Python, BM25 library, Streamlit, pytest These are suggestions; equivalent tools are fine.

Access or people · 4 IT participants and one independent policy reviewer.

01—03

Start with these three actions

  1. Write 3 fictional documents with intentionally different document-level permissions.
  2. Create the full role/document policy matrix and expected permitted results before implementing retrieval.
  3. Test filtering before ranking on the pilot documents; separate denied retrievals from answer-generation claims.
Files, questions and sources

Pilot question: Can permission-aware retrieval enforce a shared policy while making permitted sources understandable?

Literature search: AI assistant access control information disclosure user understanding

Download starter instructions
Research method · Design, build and test (DSR) · 7 steps
  1. Read the newest papers and list the closest existing systems.
  2. Write down the versions, fields, data split, case assignment, random seeds and correct answers for 30 fictional documents, 3 roles, 60 queries.
  3. Draw the user workflow, data model and system architecture. List the requirements and pass criteria.
  4. Build a working version of access-controlled search, permission fixtures and leakage report.
  5. Test every function, connection and failure case. Save the failed tests as well as the passed tests.
  6. Compare the system with the named alternative. Then run the user task or decision task in the assignment.
  7. Report the measured result, the failed cases and the design lessons another team can reuse.
Research question and sources

Research question: Investigate where permission filtering should occur in a retrieval pipeline. Compare pre-filtering and post-filtering with the same role policy; jointly evaluate authorized recall, leakage and whether users understand denials.

Research result: Evidence about security–retrieval trade-offs and usable denial explanations.

Current project literature

IS theory starting points

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: AI assistant access control information disclosure user understanding

Non-technical

Bachelor’s · applied project

Final result

A permission matrix and an escalation path for unclear requests.

01

Material to create

12 paper access scenarios

8 determinate and 4 ambiguous cases covering roles, copied information and cross-project answers. Prepare equivalent prose policies and permission tables.

02

What to do

  • Document who should access each kind of coding-assistant document.
03

How it is tested

Use the paper role/document scenarios; record determinate decisions separately from policy ambiguities. Plan 4 participant sessions.

04

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 software/IT staff; no assistant implementation.

Research method · Study and improve · 6 steps
  1. Read the starting sources and write the exact information problem.
  2. Prepare 12 paper access scenarios and a separate answer sheet or coding sheet.
  3. Run one pilot and fix unclear questions.
  4. Collect the named evidence with consent.
  5. Group the findings with the stated categories and check the answer sheet.
  6. Produce a permission matrix and an escalation path for unclear requests. List the three most useful changes.
Download the complete bachelor planDownload bachelor instructions

Master’s · research project

Final result

Policy clarification table and source-display recommendations.

01

Material to create

12 paper access scenarios + 8 IT interviews

8 determinate and 4 ambiguous cases covering roles, copied information and cross-project answers. Prepare equivalent prose policies and permission tables.

02

What to do

  • Prepare assistant answers showing sources drawn from three fictional projects.
  • Ask users which sources each role should be allowed to see.
03

How it is tested

Compare policy comprehension for clear cases with balanced, non-overlapping versions. Score clear cases against the policy key. Analyse ambiguous ownership cases and escalation reasons separately.

04

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 software/IT staff; no assistant implementation.

01—03

Start with these three actions

  1. Prepare a pilot with 2 examples from: 12 access scenarios + 8 interviews. Write the task questions and a reference answer sheet.
  2. Write a recruitment message, information sheet and consent form for the participants named above. Agree privacy handling with the supervisor before contact.
  3. 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: Which access-policy rules do users misunderstand when answers combine multiple sources?

Literature search: AI assistant access control information disclosure user understanding qualitative scenario study

Interview prompts

  • Which sources may this role read under the policy?
  • Does combining two permitted facts change your decision?
  • Which wording in the policy or answer is unclear?
Download starter instructions
Research method · Study, compare and explain · 7 steps
  1. Read the newest papers and write one exact research question.
  2. State which people, cases or documents you will study and what you will compare.
  3. Write the selection rules, questions and analysis steps for 12 paper access scenarios + 8 IT interviews.
  4. Run one pilot. Fix unclear questions or categories, then keep the guide unchanged.
  5. Collect the named interviews, cases or documents with consent.
  6. Analyse them with the stated comparison or coding method. Keep disagreements and missing data.
  7. Report the answer, the evidence and the practical output named in the assignment.
Research question and sources

Research question: Explain mismatches between permission policy and users’ expectations of assistant access. Contrast prose and permission-table cases using contextual integrity; separate ambiguous policy from incorrect interpretation.

Research result: A theory-based account of access expectations and unresolved governance decisions.

Current project literature

IS theory starting points

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: AI assistant access control information disclosure user understanding qualitative scenario study

Your degree, track and shortlist are saved in this browser.