https://fin.ai/research 2026-09-25 https://fin.ai/research/how-fin-scales-customer-defined-behaviour 2026-09-25 https://fin.ai/research/what-does-it-mean-for-a-model-to-think-reasoning-recursion-and-the-operator-design-space 2026-05-21 https://fin.ai/research/structured-agentic-rag-for-e-commerce 2026-05-07 https://fin.ai/research/low-rank-key-value-attention-reducing-kv-cache-memory-and-maintaining-head-diversity 2026-04-09 https://fin.ai/research/unsupervised-learning-meets-generative-ai-topic-modelling-for-real-world-dialogue 2026-03-30 https://fin.ai/research/podcast-ep2-shipping-reliable-ai-actions 2025-09-19 https://fin.ai/research/podcast-ep1-closing-the-loop 2025-09-19 https://fin.ai/research/building-a-better-language-detection-model-for-fin 2025-09-12 https://fin.ai/research/using-llms-as-a-reranker-for-rag-a-practical-guide 2025-09-12 https://fin.ai/research/building-out-intercoms-ai-infra 2025-09-12 https://fin.ai/research/was-that-helpful-understanding-user-feedback-in-customer-support-ai-agents 2025-09-12 https://fin.ai/research/david-vs-goliath-are-small-llms-any-good 2025-09-12 https://fin.ai/research/to-escalate-or-not-to-escalate-that-is-the-question 2025-09-12 https://fin.ai/research/how-we-built-a-world-class-reranker-for-fin 2025-09-12 https://fin.ai/research/finetuning-retrieval-for-fin 2025-09-12 https://fin.ai/research/cost-of-serving-llms 2025-09-12 https://fin.ai/research/we-dont-need-higher-peak-intelligence-only-more-intelligence-density 2025-08-20 https://fin.ai/research/fin-running-a-reliable-service-over-unreliable-parts 2025-08-08 https://fin.ai/research/think-fast-reasoning-at-3ms-a-token 2025-07-18 https://fin.ai/research/a-causal-inference-approach-to-measuring-the-impact-of-improved-rag-content 2025-07-08 https://fin.ai/research/generating-knowledge-center-content-from-customer-service-conversations 2025-07-08 https://fin.ai/research/do-you-really-need-a-vector-search-database 2025-04-30 https://fin.ai/research/agency-control-reliability-the-tradeoffs-in-customer-support-agents 2025-07-08 https://fin.ai/research/does-slower-seem-smarter-rethinking-latency-in-ai-agents 2025-04-11 https://fin.ai/research/an-actor-critic-approach-to-squash-hallucinations 2025-04-11 https://fin.ai/research/category/benchmarking-testing https://fin.ai/research/category/human-perception-of-ai https://fin.ai/research/category/llm-evaluation https://fin.ai/research/category/text-classification https://fin.ai/research/category/rag https://fin.ai/research/category/podcast https://fin.ai/research/author/afonso-marques https://fin.ai/research/author/alihan-zihna https://fin.ai/research/author/ashwini-shukla https://fin.ai/research/author/damian-kelly https://fin.ai/research/author/dhruv-patel https://fin.ai/research/author/eamon-phelan https://fin.ai/research/author/ekansh-verma https://fin.ai/research/author/fedorparfenov https://fin.ai/research/author/fergalreid https://fin.ai/research/author/james-oneill https://fin.ai/research/author/ketan-bhatt https://fin.ai/research/author/mariia-matskevichus https://fin.ai/research/author/mario-kostelac https://fin.ai/research/author/pedro-tabacof https://fin.ai/research/author/ramil-yarullin https://fin.ai/research/author/sagarjoglekar https://fin.ai/research/author/stefan-ivanovici https://fin.ai/research/author/vinicius-ribeiro https://fin.ai/research/author/wenlong-wang