Blog

Dive into the anatomy of Chain-of-Thought (CoT) prompting — how it works, why it improves LLM reasoning, and tips for writing effective CoT prompts.

Contrastive Chain-Of-Thought Prompting Contrastive Chain-of-Thought Prompting (CCoT) uses both positive & negative demonstrations to improve LLM reasoning.

OpenAI Structured JSON Output With Adherence In the past, when using OpenAI’s JSON mode there was no guarantee that the model output will match the specified and predefined JSON schema. In my view this really made this feature unreliable in a production environment, where consistency is important…

Explore the ‘Chain-of-X’ phenomenon in LLM prompting, how CoT-style decomposition has evolved across reasoning, retrieval, verification, empathy & more.

Chain-Of-Note (CoN) Retrieval For LLMs Chain-of-Note (CoN) is aimed at improving RAG implementations by solving for noisy data, irrelevant documents and out of domain scenarios.

Discover how Southeast Asia's digital banks are outpacing traditional banks with Generative AI, transforming speed, personalization, and efficiency.