ai agent evaluation pipeline
๐งช
1
Evaluate AI agents at Session, Trace & Span levels
PaulPham157
paulpham157
AI & ML interests
DevOps Engineer | Harness Engineering enthusiast
Recent Activity
updated a Space 2 days ago
build-small-hackathon/AI-agent-Evaluation-pipeline updated a collection 3 days ago
Paul's Agent Eval updated a collection 3 days ago
Paul's Agent EvalOrganizations
updated a
Space 2 days ago
updated a
collection 3 days ago
liked a
Space 3 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
published a
bucket 7 days ago
published a
Space 7 days ago
liked a
model 4 months ago
posted an update 5 months ago
Post
1272
Two things to know right before starting:
- Learn Git. Git is a great versioning tool, even when working alone. It's also essential when working in a team. Don't make excuses that you only do DL and can't do software development.
๐ Don't create files like:
main_backup_1.py
main_backup_2.py
main_backup_3.py
anymore...
(It sounds ridiculous, but I've actually seen some people do that... weren't students.)
- Try to keep everything stable. Imagine encountering errors during a demo. Keep the code clean so it runs smoothly and is maintainable. Always minimize DevOps steps to ensure quick reboot (this can be covered by some platforms; thanks to Hugging Face for making it easy and providing a basic infrastructure that most people can access almost for free). ๐คค
- Learn Git. Git is a great versioning tool, even when working alone. It's also essential when working in a team. Don't make excuses that you only do DL and can't do software development.
๐ Don't create files like:
main_backup_1.py
main_backup_2.py
main_backup_3.py
anymore...
(It sounds ridiculous, but I've actually seen some people do that... weren't students.)
- Try to keep everything stable. Imagine encountering errors during a demo. Keep the code clean so it runs smoothly and is maintainable. Always minimize DevOps steps to ensure quick reboot (this can be covered by some platforms; thanks to Hugging Face for making it easy and providing a basic infrastructure that most people can access almost for free). ๐คค
replied to their post 5 months ago
Yes, I completely agree. When writing on paper, I still prefer white paper. But screens are different; they have LEDs underneath, and it creates an effect similar to looking directly at the sun.
replied to their post 5 months ago
I have nearsightedness in one eye and astigmatism in the other. Do you understand the feeling of going out at night and the headlights being so blinding and blurry? That's exactly what I feel when looking at a white screen of light themes.
replied to their post 5 months ago
The huggingface theme ๐คค
posted an update 5 months ago
Post
1287
This isn't really related, but... do people generally prefer dark themes or light themes?
- 8 replies
posted an update 5 months ago
Post
1654
I am building a control panel that converts the Markdown format of spec-kit specification document into a visual kanban board
https://specboard.vercel.app/
https://specboard.vercel.app/
replied to their post 6 months ago
When you use an agent (chatbot, coding IDE, automation workflows...) you don't just pass in your prompt. The agent also passes in other things, which increases the total context, and the input context length is limited.
posted an update 6 months ago
Post
287
Total context = user message + system instruction (system prompt) + tools, MCP instruction + subagent instruction + skill instruction. Can you control your input token?
- 2 replies
published a
Space 6 months ago
upvoted a collection 10 months ago