That’s where the OCEAN prompting process comes in: it’s a straightforward framework designed to work with any LLM, helping you reliably get the results you want. 

The great thing about the OCEAN process is that it takes the guesswork out of using LLMs. It helps you move past that ‘blank page syndrome’ — that moment when you can ask the model anything but aren’t sure where to start. By focusing on clear objectives and guiding the model with the right context, you can generate content that is spot on for your needs, every single time.

5 ways to make LLMs work for you using the OCEAN prompting process

OCEAN’s name is an acronym: objective, context, examples, assess, negotiate — so let’s begin at the top.

1. Define your objective

Think of this as setting a clear goal for your interaction with the LLM. A well-defined objective ensures that the responses you get are focused and relevant.

Maybe you need to:

• Draft an email to parents about an upcoming school event
• Create a beginner’s guide for a new Scratch project
• Come up with engaging quiz questions for your next science lesson

By knowing exactly what you want, you can give the LLM clear directions to follow, turning a broad idea into a focused task.

2. Provide some context 

This is where you give the LLM the background information it needs to deliver the right kind of response. Think of it as setting the scene and providing some of the important information about why, and for whom, you are making the document.

You might include:

• The length of the document you need
• Who your audience is — their age, profession, or interests
• The tone and style you’re after, whether that’s formal, informal, or somewhere in between

All of this helps the LLM include the bigger picture in its analysis and tailor its responses to suit your needs.

3. Include examples

By showing the LLM what you’re aiming for, you make it easier for the model to deliver the kind of output you want. This is called one-shot, few-shot, or many-shot prompting, depending on how many examples you provide.

You can:

• Include URL links 
• Upload documents and images (some LLMs don’t have this feature)
• Copy and paste other text examples into your prompt

Without any examples at all (zero-shot prompting), you’ll still get a response, but it might not be exactly what you had in mind. Providing examples is like giving a recipe to follow that includes pictures of the desired result, rather than just vague instructions — it helps to ensure the final product comes out the way you want it.

4. Assess the LLM’s response

This is where you check whether what you’ve got aligns with your original goal and meets your standards.

Keep an eye out for:

• Hallucinations: incorrect information that’s presented as fact
• Misunderstandings: did the LLM interpret your request correctly?
• Bias: make sure the output is fair and aligned with diversity and inclusion principles

A good assessment ensures that the LLM’s response is accurate and useful. Remember, LLMs don’t make decisions — they just follow instructions, so it’s up to you to guide them. This brings us neatly to the next step: negotiate the results.

5. Negotiate the results

If the first response isn’t quite right, don’t worry — that’s where negotiation comes in. You should give the LLM frank and clear feedback and tweak the output until it’s just right. (Don’t worry, it doesn’t have any feelings to be hurt!) 

When you negotiate, tell the LLM if it made any mistakes, and what you did and didn’t like in the output. Tell it to ‘Add a bit at the end about …’ or ‘Stop using the word “delve” all the time!’ 

How to get the tone of the document just right

Another excellent tip is to use descriptors for the desired tone of the document in your negotiations with the LLM, such as, ‘Make that output slightly more casual.’

In this way, you can guide the LLM to be:

• Approachable: the language will be warm and friendly, making the content welcoming and easy to understand
• Casual: expect laid-back, informal language that feels more like a chat than a formal document
• Concise: the response will be brief and straight to the point, cutting out any fluff and focusing on the essentials
• Conversational: the tone will be natural and relaxed, as if you’re having a friendly conversation
• Educational: the language will be clear and instructive, with step-by-step explanations and helpful details
• Formal: the response will be polished and professional, using structured language and avoiding slang
• Professional: the tone will be business-like and precise, with industry-specific terms and a focus on clarity

Remember: LLMs have no idea what their output says or means; they are literally just very powerful autocomplete tools, just like those in text messaging apps. It’s up to you, the human, to make sure they are on the right track. 

Don’t forget the human edit 

Even after you’ve refined the LLM’s response, it’s important to do a final human edit. This is your chance to make sure everything’s perfect, checking for accuracy, clarity, and anything the LLM might have missed. LLMs are great tools, but they don’t catch everything, so your final touch ensures the content is just right.

At a certain point it’s also simpler and less time-consuming for you to alter individual words in the output, or use your unique expertise to massage the language for just the right tone and clarity, than going back to the LLM for a further iteration. 

Ready to dive in? 

Now it’s time to put the OCEAN process into action! Log in to your preferred LLM platform, take a simple prompt you’ve used before, and see how the process improves the output. Then share your findings with your colleagues. This hands-on approach will help you see the difference the OCEAN method can make!

Sign up for a free account at one of these platforms:

• ChatGPT (chat.openai.com)
• Gemini (gemini.google.com)

By embracing the OCEAN prompting process, you can quickly and easily make LLMs a valuable part of your teaching toolkit. The process helps you get the most out of these powerful tools, while keeping things ethical, fair, and effective.

If you’re excited about using AI in your classroom preparation, and want to build more confidence in integrating it responsibly, we’ve got great news for you. You can sign up for our totally free online course on edX called ‘Teach Teens Computing: Understanding AI for Educators’ (helloworld.cc/ai-for-educators). In this course, you’ll learn all about the OCEAN process and how to better integrate generative AI into your teaching practice. It’s a fantastic way to ensure you’re using these technologies responsibly and ethically while making the most of what they have to offer. Join us and take your AI skills to the next level!

A version of this article also appears in Hello World issue 25.

The post Ocean Prompting Process: How to get the results you want from an LLM appeared first on Raspberry Pi Foundation.

Back in person, with new ways to create with code

The Raspberry Pi Build HAT allows learners to build and program projects with Raspberry Pi computers and LEGO® Technic™ motors and sensors from the LEGO® Education SPIKE™ Portfolio.

What better way could there be to get the more experienced coders among our Dojo’s young people (Ninjas) properly excited to be back? We knew they were fond of building things with LEGO bricks, as so many young people are, so we were sure they would have great fun with this activity!

For our beginners, we set up Raspberry Pi workstations and got them coding the projects on the Home island on our brand-new Code Club World platform, which they absolutely loved, so their jealousy was mitigated somewhat. 

Being able to rely on your learners’ existing skills in making the physical build leaves you a lot more time to support them with what they’re actually here to learn: the coding and digital making skills.

We wanted to keep our first Dojo back small, so for the ‘LEGO bricks and Raspberry Pi’ activity, we set up just four workstations, each with a Raspberry Pi 4, with 4GB RAM and a Raspberry Pi Build HAT on top, and a LEGO Education SPIKE Prime set. We put eight participants into teams of two, and made sure that all of them brought a little experience with text-based coding, because we wanted them to be able to focus on making projects in their own style, rather than first learning the basics of coding in Python. Then we offered our Ninjas the choice of the first two projects in the Introduction to the Raspberry Pi Build HAT and LEGO path: make Pong game controllers, or make a remote-controlled robot buggy. As I had predicted, all the teams chose to make a robot buggy!

Teamwork and design

The teams of Ninjas were immediately off and making — in fact, they couldn’t wait to get the lids off the boxes of brightly coloured bricks and beams!

Our project instructions focus primarily on supporting learners through coding and testing the mechanics of their creations, leaving the design and build totally up to them. This was evidenced by the variety of buggy designs we saw at the project showcase at the end of the two-hour Dojo session!

One of the amazing things Raspberry Pi makes possible when you use it with the Raspberry Pi Build HAT and SPIKE™ Prime set: it’s simple to make the Raspberry Pi at the heart of the creation talk to a mobile device via Bluetooth, and off you go controlling what you’ve created via a phone or tablet.

While beginner-friendly, the projects in the Introduction path involve a mix of coding, testing, designing, and building. So it required focus and solid teamwork for the Ninjas to finish their buggies in time for the project showcase. And this is where building with LEGO pieces was really helpful.

Coding front and centre, thanks to the Raspberry Pi Build HAT

Having LEGO bricks and the Build HAT available to create their Raspberry Pi–powered robot buggies made it easy for our Ninjas to focus on writing the code to get their buggies to work. They weren’t relying on crafting skills or duct tape and glue guns to make a chassis in the relatively short time they had, and the coding could be front and centre for them.

The most exciting part for the Ninjas was that they were building remote-controlled robot buggies. This is one of the amazing things Raspberry Pi makes possible when you use it with the Build HAT and SPIKE™ Prime set: it’s simple to make the Raspberry Pi at the heart of the creation talk to a mobile device via Bluetooth, and off you go controlling what you’ve created via a phone or tablet.

The LEGO Technic motors that are part of the LEGO Education SPIKE Prime set are of really high quality, and they’re super easy to program with the Build HAT and its Python library! You can change the motors’ speed by setting a single parameter in your code. You can also easily write code to set or read the motors’ exact angle (their absolute position). That allows you to finely control the motors’ movements, or to use them as sensors.

Some of our teams, inspired by everything the SPIKE Prime set has to offer, tried out programming the set’s sensors, to switch their robot buggy on or help it avoid obstacles. Because we only had about 90 minutes of digital making, not all teams managed to finish adding the extra features they wanted — but next time for sure!

With a little more time (or another Dojo session), it would have been possible for the Ninjas to make some very advanced remote-controlled buggies indeed, complete with headlights, brake lights, sensors, and sound.

Learning with LEGO® elements and Raspberry Pi computers

If you have access to LEGO Education SPIKE Prime sets for your learners, then the Raspberry Pi Build HAT is a great addition that allows them to build complex robotics projects with very simple code — but I think that’s not its main benefit.

Because the Build HAT allows your learners to work with LEGO elements, you know that many of them already understand one aspect of the creation process: they’ve got experience of using LEGO bricks to solve a problem. In a coding or STEM club session, or in a classroom lesson, you can only give your learners limited amount of time to complete a project, or get their project prototype to a stable point. So being able to rely on your learners’ existing skills in making the physical build leaves you a lot more time to support them with what they’re actually here to learn: the coding and digital making skills.

You and your young people next!

The projects using the Raspberry Pi Build HATs were such a hit, we’ll be getting them and the LEGO Education SPIKE Prime sets out at every Dojo session from now on! We’re excited to see what young people around the world will be creating thanks to our new collaboration with LEGO Education.

Have you used the Raspberry Pi Build HAT with your learners or young people at home yet? Share their stories and creations in the comments here, or on social media using #BuildHAT.

The post The Raspberry Pi Build HAT and LEGO® components at our CoderDojo appeared first on Raspberry Pi Foundation.

On 9 and 10 November, a large group of Scouts converged on their global headquarters at Gilwell Park in Surrey to attend a Social Action Hackathon hosted by a great team of digital making educators from the Raspberry Pi Foundation.

The event was to celebrate internet service provider Plusnet’s partnership with the Scout Association, through which Scout groups throughout the UK will be given free WiFi access. This will allow them to work towards tech-based badges, including the Raspberry Pi Foundation’s Digital Maker Staged Activity Badge.

The Social Action Hackathon

Over two days, the Scouts participated in our cutting-edge hackathon, where they were taught authentic agile development techniques; handed a crate of Raspberry Pi computers, electronic components, and construction materials; and given free rein to create something awesome.

The Social Action Hackathon was designed to directly support the Scout Association’s A Million Hands project, which aims to encourage Scouts to ‘leave the world a little better than they found it’ by engaging with their UK-based charity partners. During the Hackathon, the Scout Association asked the young people to create a technological solution that might benefit one of these important charities, or the people and communities that they support.

Creating with tech

First, participants were shown the capabilities of the technology available to them during the Hackathon by undertaking some short, confidence-boosting programming activities, which got them thinking about what assistive technologies they could create with the resources available. Then, they chose a call-to-action video by one of the A Million Hands charity partners as the basis of their design brief.

The event was designed to feel like a role-playing game in which teams of Scouts assumed the part of a fledgling technology start-up, who were designing a product for a client which they would bring to market. The teams designed and prototyped their assistive technology through a process used all over the world in technology and software companies, known as agile development methodology.

The fundamental principles of agile development are:

• Only work on the most important things at any given point in time
• Break those things into bite-sized tasks for individuals to work on autonomously
• Catch up regularly on progress to work out what is important now, and change your plan to adapt if you need to
• Start by making something simple that works, then add to it or change it into something better in several steps

The ‘creation’ phase of the Hackathon consisted of several 90-minute rounds called sprints, each of which began with a team meeting (or stand-up) just as they would in a real agile workplace. Teams broke their project idea down into individual tasks, which were then put into an organisational tool known as a kanban board, which is designed to allow teams to get an instant snapshot of their current progress, and to help them to problem-solve, and adapt or change their current focus and plans at each stand-up meeting.

The final pitch

As their final task, teams had to present their work to a panel of experts. The four-person panel included the Raspberry Pi Foundation’s Head of Youth Partnerships, Olympia Brown, and television presenter, Reggie Yates, an advocate for Mind, one of the A Million Hands charity partners.

By completing the Social Action Hackathon, the young people also completed the fifth and most complex stage of the Digital Maker Staged Activity Badge in just two days — a real accomplishment!

Get involved!

If you think your Scout group might like to take their Digital Maker Badge, you can find free curriculum resources for all ages of Scout group, from Beavers to Explorers, on the Raspberry Pi Foundation partner page.

The post Social Action Hackathon with the Scouts appeared first on Raspberry Pi Foundation.