Kodaii Generated a 20k-Line Fastapi Back End From One Prompt
Mood
excited
Sentiment
positive
Category
startup_launch
Key topics
To get a sense of how well the engine handles a real project, we asked it to build a Calendly-style booking system from a single prompt. It ran the whole process — planning, code generation, tests, infra, and deployment — in about 8 hours.
What it generated: - ~20K lines of Python (FastAPI, async) - Postgres schema (6 tables) - Services, background tasks, booking logic - Email notifications - 40 unit tests + 22 integration tests - Docker Compose (API + Postgres) - GitHub Actions pipeline - A running deployment tied to Postgres - Code & live endpoints
Everything is open: Repo: https://github.com/OlivierKodaii/calendarKodaii
API docs: https://calendar.kodaii.dev/docs
OpenAPI schema: https://calendar.kodaii.dev/openapi.json
Admin interface: https://calendar.kodaii.dev/admin
Why we’re sharing this
We think this line of work may be of interest to peers on HN who care about backend architecture, tooling, and large-scale code generation and your feedback would be very much appreciate.
If you inspect the repo, we’d appreciate any comments on:
- structure, - code clarity, - decisions that look odd, - failure points, - or anything that feels promising or problematic.
For those who want to follow the project or join the upcoming alpha: https://kodaii.dev
Happy to discuss details or answer questions.
Discussion Activity
Light discussionFirst comment
7h
Peak period
3
Day 1
Avg / period
2
Key moments
- 01Story posted
Nov 25, 2025 at 6:05 PM EST
1d ago
Step 01 - 02First comment
Nov 26, 2025 at 1:16 AM EST
7h after posting
Step 02 - 03Peak activity
3 comments in Day 1
Hottest window of the conversation
Step 03 - 04Latest activity
Nov 26, 2025 at 7:39 PM EST
1h ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
Discussion hasn't started yet.
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.