Restack Refocuses Product To Test AI Agent Behavior
Restack co-founder and CEO Andrés Tapia says the company pivoted in 2022 after ChatGPT drove almost 90% of users to request AI features, refocusing the platform on AI agent deployment and testing. Restack now offers behavioral metrics and an LLM-as-judge to evaluate subjective agent actions, enabling product teams to iterate prompts and tools without engineering intervention to reduce hallucinations in customer-support deployments.
Key Points
- 1Pivoted core product after 90% of users requested AI features following ChatGPT's 2022 surge
- 2Introduced behavioral metrics and LLM 'judge' to evaluate subjective agent actions beyond outputs
- 3Enables product teams to iterate prompts and tools without engineering, reducing live-hallucination risk
Scoring Rationale
Practical product shift and testing approach increases deployability; limited broader validation beyond company claims and independent evidence.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
