Artificial intelligence
Cross-tool programme

Create internal apps with vibe coding

Learn to explore an internal application with AI, describe its behaviour and review a prototype before deciding how to proceed. Practice is adapted to the AI-assisted creation tool the client uses.

Introductory8 h · 4 × 2 hSpanish & English
Contact

Find your starting point

A good fit when you want to turn an internal need into an AI-assisted prototype and learn to check its changes and limits.

Another option to consider

Claude for developmentIf your team uses Claude, already reads and modifies code and wants to work in a repository, you can choose its specific technical programme.
Hours and sessions
8 hours live · 4 sessions of 2 h.
Group size
Up to 12 participants per trainer as a reference, adjusted to the practice and feedback.

What you will learn

  1. 01

    Write a short specification covering users, tasks and limits.

  2. 02

    Guide changes to a prototype and check its expected behaviour.

  3. 03

    Identify data, permission and maintenance questions before any possible implementation.

A proposed programme

Build an internal resource catalogue with the client's AI-assisted creation tool: describe the journey, request changes and check how people find a guide or template. Work with fictional data, topic search and a detail view, adapting the build to the agreed environment's features. The eight hours include practice and review; the handover explains what works and what needs a further phase.

We adapt the selection and depth of the modules to the group's starting point and goals.

01

Define the prototype

Problem, users, screens and acceptance criteria for a small scope.

You will work on

  • Choose the resources a team needs to find and define who looks them up, what information they need and what is outside scope.
  • Prepare fictional titles, topics, descriptions and links with clear screens.
  • Write testable criteria for finding a resource, viewing its details and understanding whether a link is available.
Practice
Prepare a short specification for a guide and template catalogue with a topic, description and reference link.
How you will check it
A scope with fields, screens and criteria for checking the journey.
02

Build and iterate with AI

Instructions, reviewing changes and testing the journey with the agreed tool.

You will work on

  • Give the chosen tool the objective, data and criteria before requesting the first version.
  • Request one change at a time and compare the preview with the specification.
  • Try a normal search, a resource without a link and a query with no results; correct the behaviours observed.
Practice
Build the journey and adjust search, details and messages for resources without an available link.
How you will check it
A classroom prototype reviewed with normal and error cases, checking behaviour beyond its appearance.
03

Evaluate what is missing

Prototype limits, data handling and technical reviews for a subsequent phase.

You will work on

  • Distinguish prototype session data from a shared database and access for individual users.
  • Record checks, outstanding errors and reviews needed for data, permissions and maintenance.
  • Exchange prototypes with another person and check whether they understand the journey and its limits.
Practice
Review the prototype with feedback and leave instructions for repeating the checks.
How you will check it
A handover explaining what was checked and what is needed before considering real use.

Find the right guide and know whether it is available

Teaching example

You will build a prototype with fictional data, check a main user journey and document what works and what needs review before use.

Fictional classroom case. A team wants its guides and templates in a catalogue that is easy to browse. We work in an independent teaching project with ten invented resources, without connecting company documents. The build is adapted to the client's tool; the test dataset is prepared afresh for each practice.

Starting point
We need to search by title or topic and understand what each resource is for. Some links are not available yet and must say so. We use a test dataset prepared for the exercise.
First attempt
The example’s first proposal shows an “Open resource” button on every card, including those with no link. Search finds matches only when the category is typed exactly, and a query with no results leaves a blank area.
What we review
The trainer asks participants to check the journey against the specification. They add understandable title or topic search, replace a button with no destination with “Link pending”, and prepare a message that lets people return to all resources. They repeat the queries and document the results.
Result
The revised example helps people find a guide or template and distinguishes available links from pending ones. The handover collects the specification, checks and practice-environment limits; sharing real documents and managing permissions require a further phase.

Request a change and check its effect

  1. Define

    • Guides and templates

      List, search and details

    • Invented data

      Title, topic, description and link

  2. Test

    • Find a resource

      Search by title or topic

    • Link pending

      A clear message instead of an empty button

  3. Review

    • A visible limit

      Test data and checked features

    • The next phase

      Data, permissions and maintenance

Product-independent teaching illustration of a fictional case. It shows review criteria, not a tool screenshot or an operational application.

Before calling it complete

  • Resources communicate their topic, description and link availability clearly.
  • Title or topic search, a resource without a link and a query with no results have expected, checked behaviours.
  • The handover distinguishes test data from a shared workspace with real documents and permissions, and documents which features were checked in the chosen environment.

Four sessions to put it into practice.

Reference edition · 8 h live

Reference edition: 8 live hours across 4 two-hour sessions, including practice and feedback. We use the client's tool and fictional data; the environment's features are checked beforehand. The result is a classroom prototype with documented limits.

  1. Session 12 h

    Define the app and its criteria

    Define the resources, prepare fictional data and sketch the search, list and detail journey.

    By the end

    A short specification and examples for checking it.

  2. Session 22 h

    Build the first version

    Guide changes within the agreed scope and explore the prototype to identify specific improvements in the chosen environment.

    By the end

    An initial prototype and a justified list of adjustments.

  3. Session 32 h

    Iterate and check errors

    Adjust search and details; test a missing link, queries with no results and a small screen.

    By the end

    A reviewed journey and a table of expected and observed results.

  4. Session 42 h

    Review and prepare the handover

    Exchange apps, apply feedback and explain session data, permission questions and the next phase.

    By the end

    A prototype others can check, with instructions and documented limits.

If your team needs to go further

  • Adding persistence, authentication or permissions for individual users requires extending the case and its checks.
  • Implementing the app, integrating systems or managing its security and maintenance requires a separate scope.

Learn with someone who develops projects for companies.

Borja Martínez

Borja Martínez

The Optimal Flow consultant

Over two years of experience developing projects for companies across industries and sizes.

Borja is the planned trainer for this programme. Dates, language and his availability are confirmed when the edition is agreed.

With guidance, practice and support.

Each delivery includes working materials, feedback on practical work and assessment against the agreed objectives.

See materials, support and terms

Materials you can keep

Downloadable, versioned guides, exercises and review criteria for internal use.

To prepare and complete the delivery

A short recommendation, an editable communications kit and a group learning report.

TOF’s own certificate

A certificate of achievement after the agreed assessment. It is not a vendor certification.

A month of email support

On the content covered, up to two accumulated hours for the whole group.

What does your
team need to learn?

Tell us what you want to work on, how many people would take part and where you are based. We will prepare a proposal with scope, sessions and a budget.

Would you like to ask about FUNDAE?

We check eligibility for each company and edition, subject to requirements and available training credit in Spain. Funding is neither automatic nor guaranteed. Official FUNDAE information ↗

Discuss eligibility
The Optimal FlowlearnCross-tool programme

Create internal apps with vibe coding

Learn to explore an internal application with AI, describe its behaviour and review a prototype before deciding how to proceed. Practice is adapted to the AI-assisted creation tool the client uses.

8 live hours4 sessions of 2 hoursIn Spanish or English

Reference edition: 8 live hours across 4 two-hour sessions, including practice and feedback. We use the client's tool and fictional data; the environment's features are checked beforehand. The result is a classroom prototype with documented limits.

Who it is for

Business, operations and technical professionals who want to learn AI-assisted prototyping. The learning path is adapted to your experience with code.

By the end you will be able to

  • Write a short specification covering users, tasks and limits.
  • Guide changes to a prototype and check its expected behaviour.
  • Identify data, permission and maintenance questions before any possible implementation.

Four sessions to put it into practice

  1. Session 1 · 2 h

    Define the app and its criteria

    Result: A short specification and examples for checking it.

  2. Session 2 · 2 h

    Build the first version

    Result: An initial prototype and a justified list of adjustments.

  3. Session 3 · 2 h

    Iterate and check errors

    Result: A reviewed journey and a table of expected and observed results.

  4. Session 4 · 2 h

    Review and prepare the handover

    Result: A prototype others can check, with instructions and documented limits.

Before we begin

We agree the client's AI-assisted creation tool, prototype scope and the group's experience. Features, accounts, permissions and usage limits are checked before the edition. The result is a classroom prototype; security, deployment and maintenance require their own assessment and scope.

We will prepare an independent project and fictional data in the client's AI-assisted creation tool. Before the edition, we agree the environment and check the features needed for the list, search and detail view, accounts, access and any usage limits or costs. Work is adapted to the group's experience. Practice ends with a reviewed prototype; authentication, shared storage and company connections are outside scope. How test data is retained or reset is confirmed for the chosen environment.

Your trainer

Borja Martínez
The Optimal Flow consultant

Over two years of experience developing projects for companies across industries and sizes.

Borja is the planned trainer for this programme. Dates, language and his availability are confirmed when the edition is agreed.

The Optimal FlowlearnCreate internal apps with vibe coding

What we will work on

Define the prototype

  • Choose the resources a team needs to find and define who looks them up, what information they need and what is outside scope.
  • Prepare fictional titles, topics, descriptions and links with clear screens.
  • Write testable criteria for finding a resource, viewing its details and understanding whether a link is available.

Practice: Prepare a short specification for a guide and template catalogue with a topic, description and reference link.

Build and iterate with AI

  • Give the chosen tool the objective, data and criteria before requesting the first version.
  • Request one change at a time and compare the preview with the specification.
  • Try a normal search, a resource without a link and a query with no results; correct the behaviours observed.

Practice: Build the journey and adjust search, details and messages for resources without an available link.

Evaluate what is missing

  • Distinguish prototype session data from a shared database and access for individual users.
  • Record checks, outstanding errors and reviews needed for data, permissions and maintenance.
  • Exchange prototypes with another person and check whether they understand the journey and its limits.

Practice: Review the prototype with feedback and leave instructions for repeating the checks.

A fictional classroom case

Find the right guide and know whether it is available

Fictional classroom case. A team wants its guides and templates in a catalogue that is easy to browse. We work in an independent teaching project with ten invented resources, without connecting company documents. The build is adapted to the client's tool; the test dataset is prepared afresh for each practice.

By the end of the exercise: The revised example helps people find a guide or template and distinguishes available links from pending ones. The handover collects the specification, checks and practice-environment limits; sharing real documents and managing permissions require a further phase.

Extensions agreed separately. Adding persistence, authentication or permissions for individual users requires extending the case and its checks. Implementing the app, integrating systems or managing its security and maintenance requires a separate scope.

What accompanies the programme

  • A downloadable, versioned guide, exercises and review criteria; keep a copy for internal use.
  • A short recommendation, editable kit and group learning report. Responsibilities, a prior access check, handover and recipients are agreed for each delivery.
  • TOF’s own certificate of achievement after passing the agreed assessment. It is not a vendor certification.
  • Email support on the content covered for one calendar month after the last session. A maximum of two accumulated hours for the whole group, with a response time of up to two working days.

Clients provide licences unless expressly agreed otherwise. Recordings are agreed in advance. Implementation, work carried out independently by TOF, production deployment and ongoing maintenance are quoted separately. Delivery link access is agreed per delivery. Later updates and specific support require agreement. Structured documents and text alternatives; participation needs reviewed before starting.

Full format and terms → theoptimalflow.com/en/learn/how-we-teach