We introduce a comprehensive yet simple and novel technical language processing (TLP) framework for digital battery passport (DBP) and other battery predictions, which combines the capabilities of artificial intelligence (AI) agents, large language models (LLMs), and optimized hard and soft prompts. Accurately estimating battery state in extreme temperatures is one of the challenges in the field and this framework aims to address that. The DBP proposed by the EU will provide information on material origin, composition, chemical substances, carbon footprint and more. This electronic record of the entire life cycle of various features of a battery, provided by the DBP, or battery management system (BMS) is useful within the framework for data-driven solutions. It involves a battery-agnostic model context protocol (MCP) AI agent that can connect to external tools that have information of the DBP or BMS and provides soft prompts (continuous feature vectors learned by prompt-tuning) combined with optimized hard prompts (plain text inputs enhanced with gradient-based optimization) (Wen et al., 2023). The combination will then be supplied as input to a capable multimodal LLM for relevant TLP task predictions, e.g. state-of-charge (SoC) estimation or information retrieval (IR).