Vikash Shakya (VARTETA)·Oct 4Smarter AI Evaluation: Two Simple Ways to Cut Token Costs Without Cutting QualityThe problem: AI agents are expensive to build and to test
Bulandundonnelly·Sep 3Can an LLM Learn Creative Judgement?Entry 3: Designing the Judging RubricIn the previous entry, I redefined the system around three roles: a generator that proposes strategically distinct directions, a judge that…
Manish Sharma·Jul 16AI Evals for Agentic SystemsQuality, safety, and reliability are critical to the success of enterprise agentic systems. If AI systems are not reliable, it cannot be…
