# AI-augmented cases

> How to write a report on one real project run with the AI-augmented method, by what the review of case reports found: the shape of a case, six principles with their grades, and the checks that hold a case to them.

Each page's markdown source is served at the same path with a .md extension.

## Standard

- [Standard](https://tewf.github.io/ai-augmented-cases/standard.md): the one-page card to follow, with every principle and its grade
- [Contributing](https://tewf.github.io/ai-augmented-cases/AGENTS.md): rules for changing this repository

## Counting: what a program takes from a history, and how it is printed

- [Print the caution beside the count](https://tewf.github.io/ai-augmented-cases/principles/counting/caution-beside-the-count.md): a count taken from a repository's history is printed by a program, with the program's cautions in columns beside it.
- [Distinct work over raw commits](https://tewf.github.io/ai-augmented-cases/principles/counting/distinct-work-over-commits.md): a case states the distinct work behind its commit total, counted as distinct pairs of author time and subject, because a commit may recur under another hash.
- [A hand count is marked](https://tewf.github.io/ai-augmented-cases/principles/counting/hand-counts-are-marked.md): a count taken by hand is marked as such in the page, listed row by row in a file, and equal to the tally the results record.

## Reporting: how a report by its participants is made trustworthy

- [Answer the reader's checklist](https://tewf.github.io/ai-augmented-cases/principles/reporting/answer-the-readers-checklist.md): a case holds a part for each of the 12 items of the reader's checklist of Runeson 2009, in a fixed order.
- [No model analyses the data](https://tewf.github.io/ai-augmented-cases/principles/reporting/no-model-analyses-the-data.md): a case states that no language model analysed its data; a model may draft the prose, which a person reads before it counts.
- [A participant's report is an experience report](https://tewf.github.io/ai-augmented-cases/principles/reporting/participants-write-experience-reports.md): a case written by those who took part names its genre, an experience report with repository measures, and the baseline it meets.

## Optional

- [Evidence](https://tewf.github.io/ai-augmented-cases/evidence/README.md): one literature review per topic, with the evidence against
- [Bibliography](https://tewf.github.io/ai-augmented-cases/evidence/bibliography.md): every cited work, once
- [Shapes](https://tewf.github.io/ai-augmented-cases/shapes/README.md): skeletons for kinds of documents
- [Decisions](https://tewf.github.io/ai-augmented-cases/decisions/README.md): the choices this repository made, one record each