This topic covers the design, deployment, and governance of AI agents applied to financial services — including retail and corporate banking, insurance claims and underwriting, and trading automation. It examines how agent frameworks, marketplaces, automation platforms, trading chatbots and regulatory‑compliance tools combine to automate customer journeys, claims triage, KYC/AML checks, risk monitoring, trade signal generation and execution, and regulatory reporting. Recent capabilities in multimodal LLMs and agent orchestration have moved use cases from scripted chatbots to goal‑oriented, multi‑step agents. Enterprise platforms such as IBM watsonx Assistant and Yellow.ai enable no‑code and developer workflows plus multi‑agent orchestrations for CX/EX scenarios. No‑code/low‑code builders like Lindy and Nelly let domain teams author and run specialist agent teams and integrate data and tool connectors. Foundational models and API services (Anthropic’s Claude family and Google Gemini) provide the reasoning, retrieval and multimodal inputs that power agent behavior, while developer tools such as GitHub Copilot accelerate building, testing and automating agent workflows. Key market trends include: a shift toward curated agent marketplaces and frameworks that package connectors, policies and audit trails; stronger emphasis on explainability, access controls and provenance to satisfy regulators; and blending of no‑code business configuration with developer extensibility for production-grade automation. For financial institutions, practical evaluation focuses on integration with core systems, latency and execution risk for trading bots, data governance, and compliance controls. Understanding these tradeoffs — platform type, model choice, orchestration and governance — is essential to adopt AI agents safely and effectively in financial services.