Analysis
Cited project questions
Answer project questions from confirmed evidence with quotes and source locations.
Implemented task
Public task
Ask one question about the open project.
Expected outcome: The answer cites only confirmed evidence and returns to exact source lines.
Declared product contract
Inputs and task boundary
Inputs
- A question about one project with confirmed evidence
Input constraints
- The corpus is the current project and only confirmed, citable evidence may support an answer.
User actions
- Open Ask for a project.
- Enter one question and submit it.
- Inspect each citation or return to its exact transcript line.
Outputs
- A grounded answer with zero or more exact project citations.
Decision boundary
Where it fits
- Questions that can be answered from confirmed evidence in one project.
Outside the boundary
Where it does not fit
- Cross-project questions, saved comparisons, or unsupported claims without confirmed evidence.
Current scope
Limitations
- Cross-project scope, saved comparisons, and complete export are not implemented.
Verification
Product proof
journey
proof.m2-analysis-kernel
- Verified
- Review due
- Expires
- All five locator kinds, overlap, multiple codes, and exact evidence return are covered.
- Codebook, memo, history, research connections, and withdrawal child journeys pass.
- Every child artifact is hashed and rerun from a fresh database.
Failure boundary: The proof covers the completed M2 kernel, not M3 cases, matrices, or later collaboration rounds.
OpenVerbatim is an open-source (Apache-2.0) qualitative data analysis platform for coding and analyzing interview transcripts. AI-suggested codes stay marked as suggestions until a human reviewer confirms or rejects them, and every decision is kept in an audit trail. The full feature set is available when self-hosted; there is no paid feature wall.