HAhandfuloflight·Jan 7, 2026Submission
Simboba: Evals for your AI product in under 5 mins
1 points · Open discussionteamkili
simboba
Python2026–2026
teamkili / simboba
simboba
Evals for your AI product in under 5 mins
2Distinct people
2Mentions
0Explicit recommenders
8GitHub stars
What to know before exploring
What it is
Evals for your AI product in under 5 mins
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by 3-hour interval2 dated mentions
Observed mentions: 2026-01-06 15:10:21 UTC to 2026-01-07 23:48:40 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 6, 15:00 | 2026-01-06 15:00:00 UTC | 2026-01-06 18:00:00 UTC | 1 | 1 | 0 |
| Jan 6, 18:00 | 2026-01-06 18:00:00 UTC | 2026-01-06 21:00:00 UTC | 0 | 0 | 0 |
| Jan 6, 21:00 | 2026-01-06 21:00:00 UTC | 2026-01-07 00:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 00:00 | 2026-01-07 00:00:00 UTC | 2026-01-07 03:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 03:00 | 2026-01-07 03:00:00 UTC | 2026-01-07 06:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 06:00 | 2026-01-07 06:00:00 UTC | 2026-01-07 09:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 09:00 | 2026-01-07 09:00:00 UTC | 2026-01-07 12:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 12:00 | 2026-01-07 12:00:00 UTC | 2026-01-07 15:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 15:00 | 2026-01-07 15:00:00 UTC | 2026-01-07 18:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 18:00 | 2026-01-07 18:00:00 UTC | 2026-01-07 21:00:00 UTC | 0 | 0 | 0 |
| Jan 7, 21:00 | 2026-01-07 21:00:00 UTC | 2026-01-08 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
2 sourcesShow HN: Simboba – Evals in under 5 mins
Hi HN,
I built Simboba because we needed something for our own product, and I wanted to explore how dev tools change with AI coding assistants.
The hardest part of evals is creating good annotated test cases. So I focused on getting users there with the power of AI coding assistants.
How it works:
- AI drafts datasets from your codebase
- Web UI to review and refine cases
- Everything tracked in git
- Multi-turn conversation support
- LLM-as-judge + deterministic checks (e.g. was tool xyz called)
- Evals run as simple Python scripts
The AI coding assistant angle: I wanted users running customised evals in 5 minutes, not just a generic example. Started with a CLI command that generates a prompt for Claude Code / Cursor. That felt like too much friction. Then tried a separate markdown file with instructions, but AI tools didn't find this ea
Read the rest
sily.
What worked: clear instructions in the README plus structured schemas (Pydantic). The AI reads the README, understands your codebase, the structure required for the package and drafts a real dataset for your product. Then writes the eval script.
I'd love to know what you think, and happy to answer questions!