The Optimal Flowlearn
Artificial intelligence
Cross-tool programme

Prompting for generative AI

Learn to give instructions with context, criteria and examples, compare responses and prepare reusable prompts for your team's tasks. Practice uses the client's AI tool.

Introductory6 h · 3 × 2 hSpanish & English
Contact

Find your starting point

A good fit when you have tried AI and want to improve instructions, compare responses and retain a reusable approach.

Another option to consider

Generative AI fundamentalsIf you first need to understand AI uses, limits and basic checks, choose foundations.
Hours and sessions
6 hours live · 3 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 an instruction with an objective, context and response format.

  2. 02

    Compare prompt variants using defined criteria.

  3. 03

    Document a reusable prompt with its limits and usage examples.

A proposed programme

You will prepare a template for replying by email to internal work requests. You will test it with three inputs: one complete, one without a date and one with conflicting priorities. You will compare two instruction versions using the same criteria and leave with a reusable prompt, its examples and the checks needed before using the draft.

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

01

Instructions that guide

Objective, context, constraints, examples and format for a specific task.

You will work on

  • Define what the reply should achieve, who it is for and which request details and agreements it may use.
  • Separate instructions from variable data and request a subject, draft and outstanding questions; provide a short example of the desired tone.
  • Specify how to handle missing dates or conflicting priorities, without authorising AI to commit to deliveries or choose the order of work.
Practice
Write the first version of a template for replying to an internal request and test it with an input containing a deliverable, audience and an agreed date.
How you will check it
A prompt with an objective, context, format and tone example, together with an initial email checked against the input.
02

Iterate with judgement

Clarifying questions, result comparisons and adjustments based on observed errors.

You will work on

  • Set criteria before comparing: fidelity to agreements, clarity, format and handling of missing or conflicting information.
  • Test the same version with three classroom inputs: complete, missing a date and two incompatible priorities; keep the inputs and responses.
  • Adjust the instruction based on an observed issue and retest all three inputs to compare the initial and revised versions.
Practice
Compare v1 and v2 using the same requests; check whether the change keeps a confirmed date, asks for a missing date and leaves an unresolved priority for the responsible person to decide.
How you will check it
A comparison of two versions and three inputs, with observations against each criterion and reasons to keep or change the prompt.
03

Build a useful library

Templates, test cases and guidance for sharing and maintaining instructions.

You will work on

  • Save the template with its variable fields, purpose, audience, limits and usage examples.
  • Document the version, date, tool or model where shown, test inputs, responses and outstanding issues.
  • Exchange the template with another person and check whether they can adapt it to a new request without losing agreements or omitting human review.
Practice
Hand over the revised template with its three tests and usage checklist; another person applies it to a new fictional request and identifies any necessary adjustments.
How you will check it
A reusable library entry with versions and tests, a checking checklist and clear limits for the next person using it.

A template for replying to internal requests

Teaching example

You will prepare a template for a regular task, test it with several inputs and record which changes improve results against the agreed criteria.

Fictional classroom case. The team receives requests to prepare welcome material. We test three inputs: a guide with a confirmed delivery on 18 November; a request without a date; and a guide and presentation both requested as the first priority, when only one can be prepared this week.

Starting point
Every reply is written from scratch. We want to acknowledge the request, retain existing agreements and ask for the missing information needed to proceed, using a clear tone and an easy-to-review format.
First attempt
Version 1 asks 'write a friendly reply to this request'. Reviewing the three tests checks whether it preserves agreements or fills gaps: the draft must not invent a date or choose between priorities. Each input and response is retained for comparison.
What we review
Version 2 adds: 'Using {request} and {agreements}, return a subject, short draft and outstanding questions. Keep confirmed dates; if information is missing or priorities conflict, ask. Do not add commitments or decide priorities.' A tone example is supplied and all three tests are repeated against the same criteria.
Result
The handover contains the revised prompt and checked replies: confirming 18 November when agreed, asking for a date when missing and asking the responsible person to order the priorities. Issues and limits are documented; three classroom tests do not guarantee that every future input will work the same way.

The same prompt, three everyday situations

Complete request

  • Welcome guide

    Agreed delivery: 18 November

  • Keep the agreement

    Confirm the scope and date in the draft

Missing date

  • Material requested

    No indication of when it is needed

  • Ask for clarification

    Ask for a date without inventing a delivery

Conflicting priorities

  • Guide or presentation

    Both requested first · time for one this week

  • Prepare the decision

    Ask the responsible person to confirm the order

Fictional cases and our own teaching criteria. These are separate tests, not automatic steps or guaranteed results from a tool.

Before calling it complete

  • Both versions are compared with the same three inputs and criteria for fidelity, clarity, format and handling of outstanding questions.
  • The reply keeps the confirmed date, asks for the missing one and leaves conflicting priorities open without assuming commitments.
  • Another person can find the fields, versions, examples and limits, and reviews the draft before using it; emails are not sent automatically.

Sessions to put it into practice.

Reference edition · 6 h live

Confirmed reference edition: 6 live hours across 3 sessions of 2 hours. We compare two versions using three inputs during the course in the client's tool, then prepare a template with examples, review criteria and guidance for reuse.

  1. Session 12 h

    Design the instruction for a useful reply

    Define the objective, context, format and tone; separate confirmed agreements from outstanding information.

    By the end

    An initial template and an email based on a complete request.

  2. Session 22 h

    Compare two versions with three inputs

    Apply common criteria, introduce missing details and conflicts, and repeat the tests after adjusting the prompt.

    By the end

    A documented comparison and a revised version with its limits.

  3. Session 32 h

    Prepare the template for another person to use

    Save fields, examples and versions; exchange the template and review a new request.

    By the end

    A reusable prompt with three tests and a review checklist before using the draft.

If your team needs to go further

  • Developing a company-wide library with ownership, controls and evaluation across many tasks requires additional scope.
  • Integrating prompts into applications, connecting email or automating sending is outside these 6 hours of manual practice and review.

Learn to give instructions and review their results.

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 AI programme. Dates, language and availability are confirmed when arranging the course.

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.

Your team carries out the practice. Implementation services are agreed separately. See the scope →

Keep learning

Other options for the task you want to work on. Each link explains what that programme adds.

Artificial intelligence

ChatGPT for everyday work

If you use ChatGPT, apply the instructions to documents and recurring tasks with a defined review.

View course
Artificial intelligence

Claude for everyday work

If you use Claude, practise providing documents, identifying omissions and repeating a task with different examples.

View course

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.

Contact

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

Prompting for generative AI

Learn to give instructions with context, criteria and examples, compare responses and prepare reusable prompts for your team's tasks. Practice uses the client's AI tool.

6 live hours3 sessions of 2 hoursIn Spanish or English

Confirmed reference edition: 6 live hours across 3 sessions of 2 hours. We compare two versions using three inputs during the course in the client's tool, then prepare a template with examples, review criteria and guidance for reuse.

Who it is for

People who have tried generative AI and want to improve how they frame requests and review results. Applicable to different professional roles.

By the end you will be able to

  • Write an instruction with an objective, context and response format.
  • Compare prompt variants using defined criteria.
  • Document a reusable prompt with its limits and usage examples.

Programme sessions

  1. Session 1 · 2 h

    Design the instruction for a useful reply

    Result: An initial template and an email based on a complete request.

  2. Session 2 · 2 h

    Compare two versions with three inputs

    Result: A documented comparison and a revised version with its limits.

  3. Session 3 · 2 h

    Prepare the template for another person to use

    Result: A reusable prompt with three tests and a review checklist before using the draft.

Before we begin

Basic familiarity with generative AI. Practice is adapted to the client's tool; the necessary features, accounts and permissions are checked before the edition. No programming is required, and examples are adapted to the group's experience.

We will prepare three fictional requests, a tone example and a comparison table. Text is entered manually in the client's AI tool after checking features, authorised access and usage limits. Comparison criteria and the template are general; their use is adapted to the agreed environment. No email connection, API or specific paid features are needed.

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 AI programme. Dates, language and availability are confirmed when arranging the course.

Course online · theoptimalflow.com/en/learn/courses/generative-ai-promptinginfo@theoptimalflow.comVersion 1 · Document reviewed: 13 October 2026
The Optimal FlowlearnPrompting for generative AI

What we will work on

Instructions that guide

  • Define what the reply should achieve, who it is for and which request details and agreements it may use.
  • Separate instructions from variable data and request a subject, draft and outstanding questions; provide a short example of the desired tone.
  • Specify how to handle missing dates or conflicting priorities, without authorising AI to commit to deliveries or choose the order of work.

Practice: Write the first version of a template for replying to an internal request and test it with an input containing a deliverable, audience and an agreed date.

Iterate with judgement

  • Set criteria before comparing: fidelity to agreements, clarity, format and handling of missing or conflicting information.
  • Test the same version with three classroom inputs: complete, missing a date and two incompatible priorities; keep the inputs and responses.
  • Adjust the instruction based on an observed issue and retest all three inputs to compare the initial and revised versions.

Practice: Compare v1 and v2 using the same requests; check whether the change keeps a confirmed date, asks for a missing date and leaves an unresolved priority for the responsible person to decide.

Build a useful library

  • Save the template with its variable fields, purpose, audience, limits and usage examples.
  • Document the version, date, tool or model where shown, test inputs, responses and outstanding issues.
  • Exchange the template with another person and check whether they can adapt it to a new request without losing agreements or omitting human review.

Practice: Hand over the revised template with its three tests and usage checklist; another person applies it to a new fictional request and identifies any necessary adjustments.

A fictional classroom case

A template for replying to internal requests

Fictional classroom case. The team receives requests to prepare welcome material. We test three inputs: a guide with a confirmed delivery on 18 November; a request without a date; and a guide and presentation both requested as the first priority, when only one can be prepared this week.

By the end of the exercise: The handover contains the revised prompt and checked replies: confirming 18 November when agreed, asking for a date when missing and asking the responsible person to order the priorities. Issues and limits are documented; three classroom tests do not guarantee that every future input will work the same way.

Extensions agreed separately. Developing a company-wide library with ownership, controls and evaluation across many tasks requires additional scope. Integrating prompts into applications, connecting email or automating sending is outside these 6 hours of manual practice and review.

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
Course online · theoptimalflow.com/en/learn/courses/generative-ai-promptinginfo@theoptimalflow.comVersion 1 · Document reviewed: 13 October 2026