Training course · Prompt Engineering · Banking

Prompt Engineering for Banks

Vendor-neutral prompt engineering: roles, context, few-shot examples, prompt chains, prompt libraries and systematic quality checks.

Duration
1 day (7 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 Prompt Engineering with the everyday processes of Banking. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Whether you use ChatGPT, Claude, Copilot, Gemini or Le Chat, the quality of the output depends largely on how the task is framed. Prompt engineering is the skill of conveying goal, context, constraints and desired format to a language model so that it reliably produces usable results. In this vendor-neutral practical day you learn proven techniques that work across all mainstream AI assistants: defining roles and audiences, selecting relevant context, working with examples and breaking complex tasks down into traceable steps. You try out every technique directly on tasks from your own working day.

The second part focuses on repeatability and quality across the team. You develop prompt templates with placeholders, build multi-step prompt chains for analysis, writing and review processes, and set up a shared prompt library. You learn to evaluate output systematically – with review criteria, test cases and targeted self-checks by the model – and to avoid typical pitfalls such as hallucinations, ambiguity and missing context. By the end you have a structured approach that works regardless of the tool you use and continues to pay off as new models arrive.

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 understand how language models process prompts and derive effective wording from this.
  • You structure prompts with role, context, task, constraints and output format.
  • You use few-shot examples and prompt chains for complex, multi-step tasks.
  • You create reusable templates and build a shared prompt library.
  • 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

Module 1 How language models process prompts
  • Core principles of language models: probabilities, context window, limitations
  • Why wording, order and examples change the result
  • What causes hallucinations and how prompts reduce them
  • Differences and common ground between mainstream AI assistants
Module 2 Building blocks of an effective prompt
  • Defining role, audience, task, context and output format
  • Stating constraints, exclusions and quality criteria
  • Structured input with sections, delimiters and tags
  • Asking the model to raise questions instead of making assumptions
Module 3 Advanced techniques
  • Zero-shot, one-shot and few-shot: setting style and structure with examples
  • Requesting step-by-step reasoning for complex tasks
  • Prompt chains: separating research, drafting, review and revision
  • Using change of perspective, counter-arguments and model self-critique
Module 4 Templates and prompt libraries
  • Creating reusable templates with placeholders and variables
  • Storing persistent instructions in projects, custom assistants and agents
  • Building, naming, maintaining and sharing a team prompt library
  • Documenting templates: purpose, inputs, expected output, owner
Module 5 Quality assurance and responsible use
  • Defining review criteria and scoring rubrics for AI output
  • Setting up test cases and systematically comparing and improving prompts
  • Verifying facts, figures and sources; establishing the four-eyes principle
  • Data protection, confidential content and transparency under GDPR and the EU AI Act
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

Some initial experience with at least one AI assistant such as ChatGPT, Claude, Copilot or Gemini is helpful; no technical background is required. You work at a bank or financial services provider and know the core processes of your area.

Technical requirements

A laptop with an up-to-date browser and access to at least one AI assistant, ideally the tool approved within your organisation.

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 Online Request
  • Tue, 8 December 2026 Salzburg Request
  • Mon, 14 December 2026 Online Request
  • Fri, 8 January 2027 Online Request
  • Thu, 21 January 2027 Bremen Request
  • Wed, 3 February 2027 Online Request

Frequently asked questions

Do these techniques work with every AI assistant?

Yes, the course is deliberately vendor-neutral. The principles – a clear task, relevant context, examples, structured output and review steps – work equally well in ChatGPT, Claude, Copilot, Gemini, Le Chat and other tools. Where assistants differ in detail, for example with projects or custom assistants, we show the corresponding features in each.

Won't better models soon make prompt engineering obsolete?

Models are getting better at interpreting vague requests, but they still cannot know what you do not tell them: audience, quality standards, internal requirements or relevant background. Good prompts are therefore mainly good task descriptions. Templates, prompt chains and quality checks also keep their value for teams as new models arrive.

What is a prompt library and how do we maintain it as a team?

A prompt library is an organised collection of proven templates for recurring tasks, each with its purpose, required inputs, a sample result and an owner. It can live in a shared document, a wiki or directly in the AI tool's projects. In the course you set up a first library and agree simple rules for maintenance and approval.

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 “Prompt Engineering for Banks” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 1 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 Prompt Engineering courses

All 45 Prompt Engineering courses

Prompt Engineering · MunichPrompt Engineering · SalzburgPrompt Engineering · BerlinPrompt Engineering · AugsburgPrompt Engineering · HanoverPrompt Engineering · BremenPrompt Engineering · StuttgartPrompt Engineering · KaiserslauternPrompt Engineering · Online