New

Future Lab: AI Coding

Use coding agents to design, develop, and systematically test your own web applications

training

Focus AI

Favorite Share Open as PDF (German) PDF FILE

From your idea to a prototype in 6 weeks.

This training is held in German.

Take your B2B use case from the initial draft to a testable web prototype. Learn how to formulate requirements precisely, establish context for coding agents, and validate results through testing and reviews. By the end, you’ll walk away with a documented prototype, complete with a context package, test documentation, a learning log, and a development plan.

It starts in January—sign up to be notified

The first Future Lab will begin in January 2027. Additional sessions will follow in March and June. We’ll announce the specific dates shortly. Simply sign up to be notified as soon as the Future Lab is available for booking.

Module 1: Webinar

4 h

Lab Session 1: Experience Vibe Coding

See how a small web application is created using an AI coding tool.
Start by creating your own learning log for your use case.

Module 2: Self-study phase

6–8 hours

Hands-On Phase 1: Experience Vibe Coding for Yourself & Identify Your Own Use Case

Continue to develop your learning log on your own
Compare how differently agents respond to a general request and a specific work assignment

Module 3: Webinar

4 h

Lab Session 2: Refine and Validate Your Use Case

You will methodically select a manageable B2B use case and refine your idea, including, among other things,

by selecting and describing your user group
Definition of Triggers and Outcomes
Analysis of Three Comparable Solutions
Validating Your Idea Through Peer Discussion

Module 4: Self-study phase

6–8 hours

Hands-On Phase 2: Setting Up the Context for Your Use Case

You will continue to develop your use case idea—which was refined and validated during the second lab session—on your own.

These include:

Your one-pager
The Mood Board (Designs)
Wireframes or mockups, if applicable
the architectural sketch/md.

A structured interview with a language model helps you identify unstated assumptions.

The hands-on phase concludes with you

specify your product context
export your current prototype
check the technical status using “Document 0.”

The complete technical context package (Agents.md, architecture plan.md, etc.) will be developed during the next, third hands-on phase.

Module 5: Webinar

4 h

Lab Session 3: Context Engineering—From Product Idea to Actionable Plan

You'll learn the process for your project:

Migrate to the work environment where coding agents work with your repository
Back up the project status using Git and continue developing it in a structured manner
Organize work packages in a PLAN.md file; describe individual features with clear boundaries and acceptance criteria
AGENTS.md or CLAUDE.md: Define specific working rules for your coding agent
Use skills, hooks, and MCP where they simplify a specific task

In addition, you'll learn the basics of controlled loops and tests.

Module 6: Self-study phase

6–8 hours

Hands-On Phase 3: Develop the Context Package for Your Use Case & Prepare for Challenge I

You create the work packages (context package) for your own use case:

PLAN.md
Individual features with clear boundaries and acceptance criteria
AGENTS.md or CLAUDE.md: Work Guidelines for Your Agent
Skills, Hooks, and MCP: How They Simplify a Specific Task

In doing so, you'll apply the fundamentals of controlled loops and tests.

Module 7: Self-study phase

6–8 hours

Challenge I: Context Engineering for Your Use Case & Iteration

In Challenge 1, you'll submit your context package (from Hands-On Phase 3) and receive written feedback on your understanding of the problem, scope, assumptions, and testability.

Only after this feedback is received does the implementation begin using the newly generated repository code.

Before the next lab session:

Loop and Graph Engineering: Making Coding Agents Work in a Controlled Manner

Within an implementation window of approximately three days, you'll build the first working version of your project—your MVP.
In doing so, you'll apply the fundamentals of controlled loops and tests.

Module 8: Webinar

4 h

Lab Session 4: Loop and Graph Engineering—Controlling the Behavior of Coding Agents

Iterating on Your MVP: Specify requirements, delegate tasks, review results, and learn from them.
Link acceptance criteria to appropriate tests
Test-Driven Development as the foundation for verifiable delegation.
Builds, Linting, and Tests: Check changes and behavior before you accept them.
Recognize when to stop a loop and first correct requirements, context, or agent rules.
Peer Review: Demonstrate the core workflow, describe the associated requirements and a failed loop, identify pitfalls, and define useful working patterns for the next project phase.

Module 9: Self-study phase

6–8 hours

Hands-On Session 5: Further Developing Your Prototype & Preparing for Operation

Continue to develop the MVP based on small requirements and systematically review changes.
An overview of hosting, deployment, and the separation of development, test, and production environments.
Implementing HTTPS, Authentication, Roles, and Secure Management of Access Credentials
Assess the importance of backups, logging, CI/CD, and monitoring for your own project.
Describe your application's data processing, develop a data deletion strategy, and test its implementation using synthetic or approved, non-sensitive data.
Cost Control: Set token limits, monitor costs, and review which content is transmitted to model providers.
Record open tasks in the prioritized production readiness plan.

Document and present results, and determine next steps

Developing Your Product Evidence Package

It contains your working prototype
the repository or a complete export
clear instructions for getting started
Implemented Requirements
Test Results
a security and cost review

Submit this package as Challenge II.

Module 10: Self-Study Phase

6–8 hours

Challenge II: Product Evidence Package for Your Use Case & Preparing Your Pitch

In the second challenge, you'll put together your Product Evidence Package and submit it.

It contains your working prototype
the repository or a complete export
clear instructions for getting started
Implemented Requirements
Test Results
Security and Cost Review

After receiving written feedback from the instructors and before the final lab session:

Targeted revision of the points that provide the greatest benefit.
Preparing for your structured use case pitch in the final lab session:
- Pitch and a reproducible demo
- Explain Important Decisions
- Explain a corrected loop and known limitations
- Identify the most sensible next step for your project—for example, a user test, an integration, or technical hardening

Module 11: Webinar

4 h

Lab Session 5: Use Case Pitch & Investing Game

Use Case Pitch:

Structured Project Presentation
Reproducible Demo
Explain key decisions, a corrected loop, and known limitations
Identify the most sensible next step for your project—for example, a user test, an integration, or technical hardening.

Investing Game:

In the Investing Game, you allocate fictional budgets to the other players' projects. The focus is on demonstrable benefits, solid evidence, and a plausible plan for future development.

1. Experience Vibe Coding and refine your use case

Select your own editable B2B use case, including a description of the user group, trigger, and outcome.
Research: Analysis of three comparable solutions and peer discussion to reflect on the idea.
Create deliverables: one-pager, mood board, initial wireframes, architectural sketch. Conduct a structured interview with a language model to clarify unresolved assumptions.

2. Context Engineering: From Product Idea to Actionable Plan

Transfer your project to the work environment where coding agents work with the repository. Back up the project status using Git.
PLAN.md: Structure work packages; describe features with clear boundaries and acceptance criteria.
AGENTS.md/CLAUDE.md: Establish rules and guidelines for the agent; targeted use of skills, hooks, and MCP.
Challenge I: Submit a context package and receive personalized feedback on your understanding of the problem, scope, assumptions, and testability.
Implementation will not begin until after feedback has been received and the repository code has been regenerated.

3. Loop and Graph Engineering: Enabling Coding Agents to Work in a Controlled Manner

Build a functional MVP using short, controlled iterations (define requirements, delegate tasks, review results, and learn from them).
Linking Acceptance Criteria to Appropriate Tests: Test-Driven Development as the Foundation for Verifiable Delegation.
Automated feedback through builds, linting, and tests. Verify changes and behavior before merging.
Peer Review: Examining core processes, requirements, and a failed loop to identify pitfalls and patterns.

4. Further develop your prototype and prepare for operation

Iterative refinement of the MVP based on small requirements, systematic review of changes.
Operations: Prepare for hosting, deployment, and the separation of the development, test, and production environments.
Security: Implement HTTPS, authentication, roles, and secure secret management.
Operational Readiness: Check the relevance of backups, logging, CI/CD, and monitoring; document data processing; and develop and test a data deletion strategy.
Resource Management: Set token limits, monitor costs, review content submitted to model providers, and prioritize pending tasks in the production readiness plan.

5. Document and present the results, and decide on next steps

Challenge II: Compile the Product Evidence Package (working prototype, repository/export, getting started guide, implemented requirements, test results, security and cost review).
Based on individual feedback from the instructor: targeted revision of the most important points.
Preparation for the final session: Present your own use case and a reproducible demo; explain key decisions, the revised loop, and known limitations. Identify the next logical step (e.g., user testing, integration, technical hardening).
Investing Game: Allocate fictional budgets to peers' use cases based on benefits, evidence, and plausible future development.

In your online learning environment, you will find useful information, downloads and extra services for this training course once you have registered.

Translating business ideas into clear requirements: You define the scope of your use case, clarify your target audience and the benefits, and describe what your application is intended to do—and what it is intentionally not designed to do.
Create context rather than just stating requirements: You organize information, project rules, and acceptance criteria so that coding agents can work on specific, verifiable tasks.
Targeted control of coding agents using Loop and Graph Engineering: You’ll learn to break down development tasks into small steps, delegate them to agents, and decide on the next steps based on tests and reviews. You retain responsibility for the process and the outcome.
Assessing quality and limitations in a transparent way: You don't just check whether your application displays something, but also whether its behavior, requirements, and evidence align.
Plan the next steps carefully: Take data protection, security, and token costs into account , and identify the steps your prototype still needs to take to be ready for production.

What you'll bring to the table:

Initial experience with AI coding tools such as Claude Code or Codex or with "Prompt-to-App" tools such as Lovable or Bolt
- Often, you're still missing the workflow that turns a quick prototype into an application that can be planned and tested.
An interest in technology, a willingness to work in the terminal, and your own use case that is sufficiently small
A desire to work on your use case independently
The willingness and time to design and develop your own use case during the hands-on phases.
Tools & Licenses (see below) to implement your use case from a technical standpoint.
Synthetic or released, non-sensitive data for your use case
Responsibility for use cases, data, the repository, and tool and license costs.

Out of Scope:

Use Cases for Desktop Applications and Projects Involving Sensitive Production Data
Use cases that are too large to be implemented within the timeframe of the Future Lab
Anything that requires company-specific follow-up work after the pilot phase, such as hosting and deployment

Disclaimer

The finalized use case from Future Labs, which has undergone feedback, does not constitute production approval.

Required tools and access:

The choice of tool is open
Your work environment must be up and running before you start; the first lab session is not an installation workshop.
Recommended technical setup:
- Lovable Pro or Bolt Pro, currently starting at $25 per month each.
- For further work in the repository:
  - At least Claude Pro, including Claude Code, or ChatGPT Plus, including Codex; currently about $20 per month each
  - Recommended: Claude Max (includes Claude Code) or ChatGPT Pro (includes Codex); currently about $100 per month each
  - That takes care of access to the respective chat.
- Cloud Accounts and Admin Rights:
  - A tested work environment with repository access is essential. An account alone is not enough.
  - For the local setup, Git, a coding tool (IDE), and the required runtime must be set up, or a cloud IDE.
  - Broad administrative rights are not strictly required. Participants or their IT departments must facilitate the installation and use. A preconfigured cloud workstation may also be suitable.
  - To help you prepare, an optional Course 0 is available, featuring a checklist and learning resources on Git, GitHub, Supabase, Vercel, local setup, and coding environments. If you already have the necessary prior knowledge, you can skip this preparation.
- Budget for 1–2 billing months: approximately 100–150 €, including a reserve for additional usage.
  - This is a planned value
  - The actual costs depend on existing subscriptions, usage intensity, and, if applicable, additional API or hosting usage.

The following third-party tool can be used in the event:

AI tools

The Future Lab AI Coding is designed for:

Technically savvy professionals, as well as project and product managers who want to implement their own B2B use case using AI Coding.
Software developers are welcome to participate. They will gain valuable experience in loop and graph engineering, as well as in systematic testing and reviews (Test-Driven Development).

Open Badges are recognized, digital certificates of participation. These verifiable credentials are the current standard for integration in career networks such as LinkedIn.

With them, you digitally demonstrate the competences you possess. After successful completion, you will receive an Open Badge from us.

Joint online training

Booking number
43278

€2,750 plus VAT

Details

approx. 65 hours

Online

currently no events

German

Get notified by email when event dates available again.

Make a note

Train several employees

Price upon request

Details

approx. 65 hours

In Person or Online

Appointment scheduled on an individual basis

Customized training courses
Direct application in practice
Efficient use of time and resources

100% non-binding inquiry

Feedback within 24 hours

Start request

Or schedule an appointment and get personalized advice

Personal consultation

Do you have any questions? We'd be happy to help you during a personal consultation.

Select a consultation date

Please note: We use third-party tools for selected events. Personal data of the participant will be passed on to them for the implementation of the training offer. You can find more information in our privacy policy.

About us - The Haufe Akademie

Your optimizer, innovator and companion since 1978 -
Your professional partner for professional development and seminars, training courses and topical conferences.

Whether on site, live online or in-house - our customised solutions, our claim to the highest level of consulting expertise and training tailored to your needs simplify the acquisition of skills for the working world of the future and sustainably facilitate professional development.

A wide range of seminars, individual coaching and our flexible formats support HR managers and decision-makers in shaping the future and developing employees, in-house teams and companies.

Experience the benefits of online training from the comfort of your own home. Our online formats meet the highest quality standards and are in no way inferior to face-to-face events in terms of practical relevance. Learn together live online in interactive groups or digitally at a time of your choice.

3,600+ continuing education courses

690,000+ apprentices per year

Over 95% positive reviews

2,600+ trainers and coaches

19,000+ training courses held per year

Call us or send an email