The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
My AI agent was working… but I had no idea why it worked sometimes and completely fell apart other times. That’s when I plugged in LangSmith , and realized I’d been flying blind.
Suddenly, my “agentic AI” wasn’t a black box anymore, I could see everything:
Every tool call, LLM invocation and retry the agent made, also token burned & cached, state transition across agent steps
What surprised me most wasn’t the bugs , it was the waste. One trace showed my system prompt alone was 6.5k tokens. Not because it needed to be… but because I never saw it before.
So I fixed it.
Refactored prompts -> 1.5k tokens, same output quality
Switched to dynamic system prompts, injected only when complexity demanded it
Lesson learned: If you’re building agentic systems without observability
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
maxearnings
The next frontier of payments is live on Contra. How are you maximizing revenue?
micrographics
Micrographics started as utility - barcodes, packaging, instruction labels. How would you use them?
aidesignflow
AI tools are redefining how designer work. What does your workflow look like?
aivideo
AI video tools are moving at warp speed. What tools are you using?
whennotai
As AI accelerates, creative judgment matters more. What part of your work stays human?