Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion docs/ai-usage.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,4 +7,17 @@ This file documents how we use AI tools in the project.
| Tool | Used for | How we checked the output |
| --- | --- | --- |
| Claude (Anthropic) / Opus 5.5 (medium)| Refactoring our written specification into a structured README format. | The group wrote the content and made all decisions: app idea, dataset, data model, functionality and tech stack. We reviewed the result against our own notes and the project requirements, and corrected inconsistencies before committing. |
| Claude (Anthropic) / Sonnet 5 | Scaffolding the backend (`server/`): project setup, Mongoose schema/index design, the `averageScore`/`reviewCount` recompute strategy for ratings, the CSV ingestion script, GraphQL resolvers, and integration tests. Database choice (MongoDB) was decided by the group. | We reviewed the generated code against the README's data model and functionality requirements, checked proposed package versions for compatibility, and verified behavior by running the backend locally against Apollo Sandbox and the automated test suite before committing. |
| Claude (Anthropic) / Sonnet 5 | Scaffolding the backend (`server/`): project setup, Mongoose schema/index design, the `averageScore`/`reviewCount` recompute strategy for ratings, the CSV ingestion script, GraphQL resolvers, and integration tests. Database choice (MongoDB) was decided by the group. | We reviewed the generated code against the README's data model and functionality requirements, checked proposed package versions for compatibility, and verified behavior by running the backend locally against Apollo Sandbox and the automated test suite before committing. |

## Delivery 2

| Tool | Used for | How we checked the output |
| --- | --- | --- |
| Claude (Anthropic) / Sonnet 5 | Writing tests, keeping documentation in sync with new features and decisions, and assisting with debugging and error handling. | We reviewed and ran the tests locally, read through the documentation changes for accuracy, and verified fixes by reproducing the original issues before committing. |

## Delivery 3

| Tool | Used for | How we checked the output |
| --- | --- | --- |
| Claude (Anthropic) / Sonnet 5 | Same as Delivery 2: writing tests, keeping documentation in sync with new features and decisions, and assisting with debugging and error handling. | We reviewed and ran the tests locally, read through the documentation changes for accuracy, and verified fixes by reproducing the original issues before committing. |
| Claude (Anthropic) / Opus 5.5 | Assisting with error handling during deployment to the VM. | We tested the deployment on the VM and confirmed the errors were resolved before committing. |
2 changes: 1 addition & 1 deletion frontend/src/components/StarRating.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,7 @@ export default function StarRating({
)}
</div>
<p className={`m-0 text-muted fst-italic ${scorePosition === 'right' ? 'ms-1' : ''}`} style={{ fontSize: "0.875rem" }}>
{score == null ? "Not yet rated" : `${score/2}/5 stars`}
{score == null ? "Not yet rated" : `${Math.round((score / 2) * 100) / 100}/5 stars`}
</p>
</div>
);
Expand Down