The use case: how Snorkel AI deploys Portkey
Snorkel AI uses Portkey to trace and debug its multi-agent evaluation workflows, viewing every agent, sub-agent and tool call as a nested tree. This lets the team inspect individual prompts and responses and compare good and bad traces side by side.
More reported results
Figures published in Portkey’s case study. They are not independently measured by usedby.
20% accuracy boost in agent evaluations by catching and fixing edge cases that were previously invisible in aggregate metrics.
In the customer’s words
Prior to Portkey, Snorkel debugged LLM applications with a fragmented patchwork of logs in s3, DB queries, and manual visualization. The clean Portkey UI allows us to identify, debug, and rebuild agents with confidence.Other AI tools used by Snorkel AI
Other public relationships recorded on usedby.
Explore Snorkel AI’s AI stackPortkey users in Artificial Intelligence
Companies in the same sector, with public evidence.
See all Portkey customersGo straight to the source
Based on Portkey’s published case study. We check the public evidence; the results are reported by the vendor.
portkey.ai- Last checked
- Nov 7, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 2xChecked
Printed word for word on the page, near the name of Snorkel AI.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Snorkel AI.
- Snorkel AI uses PortkeyChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
With Portkey, the team could finally see what was happening inside their agents. Every call, every sub-agent, every tool invocation appeared as a nested tree, no more reconstructing execution paths from scattered logs.









