# Best practices | Date | Title | Tags | |-----------------------|-----------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------| | 10 July 2026 | [Evaluating the GPT-5.6 family](/content/blog/gpt56-decision-map/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 9 July 2026 | [Evaluating speech-to-text models](/content/blog/voice-evals-stt/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 6 July 2026 | [Evaluating the USA vs Belgium World Cup matchup](/content/blog/us-belgium-eval/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 2 July 2026 | [From World Cup matchups to research maps: evaluating Parallel's web research agents](/content/blog/world-cup-knowledge-graphs/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 26 June 2026 | [How to eval stateful agents](/content/blog/stateful-agent-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 24 June 2026 | [Using Braintrust to eval agentic setups from large-scale Hugging Face data](/content/blog/hf-agent-traces/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 17 June 2026 | [How to test agent cost-efficiency with Braintrust](/content/blog/test-agent-cost-efficiency/index.html) | [Best practices](/content/blog/best-practices/index.html) [Product](/content/blog/product/index.html) | | 16 June 2026 | [How to use Braintrust with any framework or provider](/content/blog/any-framework-any-provider/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 21 May 2026 | [How to improve your golden datasets with human review](/content/blog/human-review-golden-datasets/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 21 May 2026 | [The six generations of AI agents and how to eval them](/content/blog/six-generations-ai-agents/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 14 May 2026 | [How to evaluate multi-turn conversations](/content/blog/multi-turn-scoring/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 11 May 2026 | [Why your traces and evals belong in the same place](/content/blog/traces-and-evals-same-place/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 28 April 2026 | [How to earn stakeholder trust with evals and observability](/content/blog/stakeholder-trust-evals-observability/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 13 April 2026 | [How to prepare for AI compliance and governance](/content/blog/ai-compliance-governance/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 27 March 2026 | [Evals are the new PRD](/content/blog/evals-are-the-new-prd/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 19 March 2026 | [What is AI observability?](/content/blog/what-is-ai-observability/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 17 March 2026 | [Evals for PMs: A practical guide to AI product quality](/content/blog/evals-for-pms/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 10 March 2026 | [How to build your first offline eval](/content/blog/offline-eval-guide/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 12 February 2026 | [The 5 pillars of AI model performance](/content/blog/model-measurement/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 25 November 2025 | [Evals are a team sport: How we built Loop](/content/blog/collaborative-evals-loop/index.html) | [Product](/content/blog/product/index.html) [Best practices](/content/blog/best-practices/index.html) | | 18 November 2025 | [The three pillars of AI observability](/content/blog/three-pillars-ai-observability/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 23 October 2025 | [Braintrust Java SDK: AI observability and evals for the JVM](/content/blog/java-sdk/index.html) | [Product](/content/blog/product/index.html) [Engineering](/content/blog/engineering/index.html) [Best practices](/content/blog/best-practices/index.html) | | 10 October 2025 | [Measuring what matters: An intro to AI evals](/content/blog/measuring-what-matters/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 29 September 2025 | [Claude Sonnet 4.5 analysis](/content/blog/claude-sonnet-4-5-aspirational-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 3 September 2025 | [A/B testing can't keep up with AI](/content/blog/ab-testing-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 19 August 2025 | [The rise of async programming](/content/blog/async-programming/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 17 July 2025 | [Five hard-learned lessons about AI evals](/content/blog/five-lessons-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 22 April 2025 | [Webinar recap: Eval best practices](/content/blog/webinar-best-practices/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 22 January 2025 | [Evaluating agents](/content/blog/evaluating-agents/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 4 December 2024 | [What to do when a new AI model comes out](/content/blog/new-model/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 18 November 2024 | [Building a RAG app with MongoDB Atlas](/content/blog/rag-mongodb/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 17 October 2024 | [I ran an eval. Now what?](/content/blog/after-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 20 June 2024 | [How to improve your evaluations](/content/blog/improve-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 6 May 2024 | [AI development loops](/content/blog/ai-development-loops/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 24 April 2024 | [Getting started with automated evaluations](/content/blog/getting-started-evals/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 17 April 2024 | [Eval feedback loops](/content/blog/eval-feedback-loops/index.html) | [Best practices](/content/blog/best-practices/index.html) | | 13 November 2023 | [The AI product development journey](/content/blog/journey/index.html) | [Best practices](/content/blog/best-practices/index.html) |