Permissions for coding-assistant search — Technical https://thesis.uya.no/proposals/an-assistant-that-knows-its-boundaries/#technical-track BACHELOR Final result: A permission-aware search demo and exhaustive policy tests. Task: Build document search that filters results using a fixed role-permission matrix. Data: 30 fictional documents, 3 roles, 60 queries (planned) Ten documents per project. Define membership and copied-content rules; label authorized relevant IDs for all 180 role/query pairs, including empty-access cases. Requires: IT participants and one independent policy reviewer. Method: Use the fictional repository documents and role-labelled queries; test allowed retrieval and prohibited content/identifier leakage. Plan 4 participant sessions. STEPS Build and test 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. MASTER Final result: Access-controlled search, permission fixtures and leakage report. 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. STEPS Design, build and test (DSR) 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. CURRENT PROJECT LITERATURE Retrieval-Augmented Generation Classification and Access Control (2024, technical publication): https://www.tdcommons.org/dpubs_series/7382/ Describes current permission, classification and monitoring controls for RAG data. Integrating Access Control with Retrieval-Augmented Generation (2025, peer-reviewed): https://doi.org/10.1145/3672608.3707848 Implements and evaluates fine-grained access control for sensitive RAG content. IS THEORY STARTING POINTS Gao et al. (2024 revision) — Retrieval-Augmented Generation: A Survey: https://arxiv.org/abs/2312.10997 Separate retrieval, evidence use and output evaluation; trace newer retrieval work. Nissenbaum (2004) — Privacy as Contextual Integrity: https://digitalcommons.law.uw.edu/wlr/vol79/iss1/10/ 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. PILOT QUESTION Can permission-aware retrieval enforce a shared policy while making permitted sources understandable? EXAMPLE TOOLS Python, BM25 library, Streamlit, pytest Equivalent tools are fine. FIRST 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. LITERATURE SEARCH AI assistant access control information disclosure user understanding DATA 30 fictional documents, 3 roles, 60 queries (planned) Ten documents per project. Define membership and copied-content rules; label authorized relevant IDs for all 180 role/query pairs, including empty-access cases. HOW TO TEST IT 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. FINAL RESULT Access-controlled search, permission fixtures and leakage report. ACCESS OR PEOPLE 4 IT participants and one independent policy reviewer. TEMPLATES https://thesis.uya.no/starters/an-assistant-that-knows-its-boundaries/technical/data-plan.csv https://thesis.uya.no/starters/an-assistant-that-knows-its-boundaries/technical/evaluation.csv https://thesis.uya.no/starters/an-assistant-that-knows-its-boundaries/technical/literature-matrix.csv Use participant codes instead of names or email addresses.