Training course · AI Agents · Banking

AI Agents for Banks

Agentic AI for business teams: understand AI agents, automate workflows safely and keep control with human-in-the-loop and governance.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects AI Agents with the everyday processes of Banking. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

AI agents go a step beyond conventional chat assistants: they plan sub-tasks, use tools such as search, files or business applications and complete multi-step work largely on their own. Over two days you will learn how agents are built, how they differ from chatbots and traditional automation, and which tasks genuinely justify their use. Widely used platforms serve as practical examples, including Microsoft Copilot Studio, custom GPTs and Claude with projects and tool connections.

In the hands-on sessions you design agent workflows for tasks from your own area of work, from triaging requests through research and drafting to handing results over to business systems. You decide where a person reviews and approves, which permissions an agent receives and how errors are detected. A dedicated block covers governance, data protection and accountability, so that your agents not only work but remain controllable, traceable and defensible within your organisation.

Banks operate between rising cost pressure, digital competitors and dense regulation. Generative AI offers tangible efficiency gains: AI assistants analyse credit files and financial statements, summarise regulatory publications, help relationship managers prepare client meetings and answer internal questions about policies and procedures. AI agents and automation speed up processes in credit operations, KYC and complaints handling. At the same time, specific requirements apply: outsourcing and ICT risk management, traceable decisions and protection of customer data. Banks using AI must assess use cases carefully, integrate models and providers into risk management and assign clear responsibilities. Then AI becomes a tool for better advice and leaner processes.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Corporate and retail relationship managers
  • Credit analysts and credit operations staff
  • Compliance, AML and risk management teams
  • Organisation and process owners
  • Internal audit

Typical challenges we address

  • Analysing extensive credit files and financial reports efficiently
  • Tracking and implementing regulatory changes from the EBA, ECB and national supervisors
  • Meeting documentation duties in advisory and lending processes
  • Reducing manual checks in KYC and AML without compromising quality

What you will be able to do

  • You can explain how AI agents are structured and clearly distinguish them from chatbots and classic automation.
  • You can select a suitable agent platform for your requirements using transparent criteria.
  • You can design an agent workflow for a real process in your area and build a working prototype.
  • You can define human-in-the-loop checkpoints, test cases and escalation rules.
  • Identify and assess AI use cases across front office, credit operations and compliance.
  • Use AI for credit analysis, regulatory research and client communication with clear review steps.
  • Take supervisory requirements on risk management, DORA and outsourcing into account when using AI tools.

Course outline

Day 1

Module 1 What makes an AI agent
  • Agent building blocks: language model, instructions, knowledge, tools and memory
  • How agents differ from chatbots, macros and classic workflow automation
  • Levels of autonomy: from suggestion-making assistants to agents that act independently
  • Realistically judging which tasks suit agents and which do not
Module 2 Platform overview: Copilot Studio, GPTs and Claude
  • Microsoft Copilot Studio: agents grounded in company data and connected to Microsoft 365
  • Custom GPTs: configuring instructions, knowledge files and actions
  • Claude with projects, knowledge bases and tool access via the Model Context Protocol
  • Selection criteria: data access, integrations, administration and licensing
Module 3 Designing and building agent workflows
  • Breaking tasks into steps and defining hand-offs between agent and human
  • Writing system instructions, examples and knowledge sources for consistent output
  • Connecting tools: search, documents, email, spreadsheets and business applications
  • Building a prototype agent for a real process from your own area
Module 4 Human-in-the-loop, quality and error handling
  • Setting approval steps, escalation rules and thresholds for human review
  • Test cases, evaluation criteria and spot checks for quality assurance
  • Common failure modes: wrong tool choice, endless loops and fabricated facts
  • Using structured user feedback to improve the agent over time

Day 2

Module 5 Governance, security and roll-out
  • Roles and responsibilities across business units, IT, data protection and works council
  • Least-privilege permissions, logging and protection against prompt injection
  • Positioning under the EU AI Act and GDPR: transparency, documentation and data flows
  • From pilot agent to production: operation, maintenance and measuring success
Module 6 Practice lab: Banking
  • Credit file analysis
  • Regulatory monitoring
  • Client meeting preparation
  • KYC research support
  • Complaint classification
  • Internal knowledge assistant
Module 7 Data protection, quality & transfer to daily work
  • AI use in banks is subject to supervisory requirements such as the German MaRisk, DORA for ICT risk and third-party providers, banking secrecy and the GDPR. Creditworthiness assessments of natural persons are classified as high-risk under the EU AI Act, with additional obligations.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Credit file analysis

An AI assistant summarises annual accounts, management accounts and business plans, calculates ratios via transparent formulas and drafts the credit memo, which analysts review before making their recommendation.

Regulatory monitoring

New circulars, guidelines and consultations are collected and summarised automatically; AI maps them to affected departments and produces an initial gap list against existing policies.

Client meeting preparation

Relationship managers receive a concise briefing from approved data sources covering product holdings, open topics and suggested questions, without AI making investment or credit recommendations on its own.

KYC research support

AI structures company register extracts, ownership structures and adverse media, proposes likely beneficial owners and documents sources so that staff can complete reviews faster.

Complaint classification

Incoming complaints are categorised by topic, urgency and product, deadlines are flagged and draft responses prepared for the complaints team to review and approve.

Internal knowledge assistant

An AI assistant answers questions about procedures, product terms and processes based on the bank's written rules and always cites the source for verification.

Prerequisites

You should already use an AI assistant such as ChatGPT, Copilot or Claude on a regular basis. No programming skills are required. You work at a bank or financial services provider and know the core processes of your area.

Technical requirements

You will need a laptop with an up-to-date browser. Ideally you have access to at least one agent platform such as Copilot Studio, ChatGPT with GPTs or Claude; practice accounts can be provided if needed.

Data protection & compliance

AI use in banks is subject to supervisory requirements such as the German MaRisk, DORA for ICT risk and third-party providers, banking secrecy and the GDPR. Creditworthiness assessments of natural persons are classified as high-risk under the EU AI Act, with additional obligations.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Mon, 7 December 2026 – Tue, 8 December 2026 Bremen Request
  • Thu, 7 January 2027 – Fri, 8 January 2027 Augsburg Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Online Request
  • Mon, 1 February 2027 – Tue, 2 February 2027 Salzburg Request
  • Mon, 15 February 2027 – Tue, 16 February 2027 Online Request

Frequently asked questions

Do I need programming skills to build AI agents?

No. The platforms used on the course rely on visual interfaces, plain-language instructions and ready-made connectors. You learn to specify agents precisely from a business perspective, connect tools and test workflows. Where deeper technical integration would be needed, you will know which requirements to put to your IT team.

Which platform will we use during the course?

The course is vendor-neutral and uses Microsoft Copilot Studio, custom GPTs and Claude as examples. You build your prototype on the platform that is available or planned in your organisation. The principles of workflow design, control and governance you learn carry over to other agent solutions as well.

How do I stop an agent from acting without control?

Through deliberate design: agents receive only the minimum permissions they need, critical actions such as sending, booking or deleting require human approval, and every step is logged. In addition, you define test cases and escalation rules. These are exactly the control mechanisms you develop for your own use case during the course.

Does using an external AI service count as outsourcing?

It depends on the use case. Many AI services must at least be assessed as ICT third-party services under DORA, and some as outsourcing under national supervisory rules. We show which questions to clarify with information security, outsourcing management and compliance before a tool goes into production.

May AI decide on loans?

Credit decisions remain the responsibility of authorised staff. AI can prepare documents and analyses. If AI systems are used to assess the creditworthiness of natural persons, the high-risk obligations of the EU AI Act apply, together with transparency and explanation duties towards customers.

How much does “AI Agents for Banks” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Banks

More AI Agents courses

All 45 AI Agents courses

AI Agents · MunichAI Agents · SalzburgAI Agents · BerlinAI Agents · AugsburgAI Agents · HanoverAI Agents · BremenAI Agents · StuttgartAI Agents · KaiserslauternAI Agents · Online