Recording Science Experiments for YouTube: Why Clarity Matters More Than Spectacle

Science experiments can be visually impressive.

A Van de Graaff generator can make someone’s hair stand on end. A chemical reaction can produce a sudden colour change. A magnet can apparently pull a cornflake across the surface of some water. A balloon can burst, a rocket can accelerate along a wire, or a microscopic specimen can reveal an unexpected living world.

These moments are excellent for attracting attention, but spectacle alone does not make a good science video.

A successful experiment video should help the viewer understand:

• what is being investigated;

• how the experiment has been arranged;

• which measurements are being taken;

• what they should watch carefully;

• why the result occurs;

• what could affect the reliability of the conclusion.

The best science videos do not merely show that something happened. They make the science visible, understandable and memorable.

At Philip M Russell Ltd, recording an experiment is therefore not just a matter of putting a camera in front of a laboratory bench and pressing record. It requires many of the same skills as designing the experiment itself: planning, observation, control, measurement and careful communication.

Start With the Learning Objective

Before choosing the camera position, lighting the bench or setting up a microphone, it is worth asking one simple question:

What should the viewer understand by the end of the video?

That question determines everything else.

For example, a video about surface tension might have the objective:

To show that the surface of water behaves as though it has an elastic skin, and that detergent reduces this effect.

The video might include a paperclip floating on water, pepper moving away from a drop of detergent or water forming a dome on the surface of a coin.

However, without a clear explanation, the viewer might simply see an entertaining trick.

The recording needs to direct attention towards the scientific idea:

• the paperclip is denser than water but remains supported;

• the water surface bends beneath it;

• detergent disrupts the forces between water molecules;

• the surface can no longer support the object in the same way.

A good experiment video begins with the science, not the special effect.

Plan the Video Before Starting the Experiment

Some experiments are difficult to repeat.

A reaction may use expensive chemicals. A specimen may change during observation. A model may break. A combustion experiment may leave smoke or residue. A carefully prepared apparatus may take an hour to reset.

It is therefore useful to plan the recording as a sequence of shots.

A simple structure might be:

1. Introduce the scientific question.

2. Show the complete apparatus.

3. Identify the important components.

4. Explain the method.

5. Show any starting measurements.

6. Record the experiment.

7. replay the most important moment.

8. Examine the results.

9. Explain the science.

10. Discuss errors, limitations and improvements.

This does not mean every video must feel rigid or overly scripted. It means the important evidence is less likely to be missed.

A shot list can be as simple as:

• wide view of the laboratory bench;

• close-up of the measuring cylinder;

• overhead view of the apparatus;

• close-up of the reaction;

• view of the thermometer;

• screen recording of the data;

• final shot comparing the results.

Planning these shots in advance makes the final edit clearer and usually saves time.

Use More Than One Camera Angle

A single camera rarely shows everything the viewer needs to see.

A wide shot is useful for showing the complete experiment and the position of the presenter. However, it may not reveal a small colour change, the reading on a meter or the movement of a tiny object.

A close-up can show the detail, but it may leave the viewer unsure how that detail relates to the rest of the apparatus.

Combining different views solves this problem.

The wide establishing shot

The wide shot shows the entire experiment. It allows the viewer to see how the equipment is arranged and how the presenter interacts with it.

This is particularly useful for:

• mechanics demonstrations;

• electrical circuits;

• large chemical apparatus;

• Van de Graaff experiments;

• projectile motion;

• wave demonstrations;

• practical safety explanations.

The wide shot provides context.

The close-up

The close-up shows the evidence.

It might focus on:

• the meniscus in a burette;

• the pointer on a force meter;

• the display on a digital balance;

• bubbles forming on an electrode;

• the movement of a cornflake towards a magnet;

• the colour of an indicator;

• a scale on a ruler;

• an insect or specimen under a microscope.

The close-up is often the shot that turns an experiment from a demonstration into useful scientific evidence.

The overhead view

An overhead camera is particularly effective when objects move across a flat surface.

It can be used for:

• magnetic field patterns;

• chromatography;

• circuit construction;

• dissections;

• surface tension demonstrations;

• arranging samples;

• drawing diagrams beside the apparatus;

• comparing several test results.

It also allows the presenter’s hands to be seen without their body blocking the experiment.

The instrument or data view

Some experiments produce their most important results on a screen.

A force sensor, oscilloscope, thermal camera, microscope, graphing system or data logger may display information that cannot be seen in the main camera view.

Recording that display directly, rather than simply pointing a camera towards it, usually produces a much clearer result.

For example, a video of simple harmonic motion might show:

• the moving mass in the main camera view;

• a close-up of the spring;

• a graph of displacement against time;

• a slow-motion replay of one complete oscillation.

Together, these views reveal far more than any one angle could provide.

Close-Ups Should Reveal Evidence, Not Just Add Drama

Close-ups are sometimes used simply because they look impressive.

In science filming, they should have a more precise purpose.

Consider an experiment in which fortified cornflakes are floated on water and attracted towards a strong magnet.

A wide shot can establish that the magnet is not touching the cornflake. A close-up can then show the flake moving across the water. Later, the cornflakes can be crushed and the iron separated using the magnet.

A microscope view can finally show the small iron particles.

Each view answers a different question:

• Is the magnet touching the cornflake?

• Is the cornflake genuinely moving?

• Can magnetic material be separated from the cereal?

• What does that material look like under magnification?

The sequence changes the experiment from an amusing observation into a chain of evidence.

That is what a useful close-up should achieve.

Make Measurements Easy to Read

Science depends upon measurement.

Unfortunately, instrument displays are often too small, too reflective or too briefly shown for viewers to read properly.

A camera may record a thermometer, ruler or balance perfectly well, but the viewer may still struggle to identify the actual value.

Measurements should therefore be deliberately presented.

Useful techniques include:

• holding the shot for several seconds;

• using a close-up camera;

• placing the scale square to the lens;

• reducing reflections from glass;

• adding the measurement as on-screen text;

• showing both the instrument and the recorded value;

• using a pointer or graphic to identify the reading;

• displaying a results table during the explanation.

Suppose an experiment investigates cooling.

It is not enough to show a thermometer occasionally. The video should make clear:

• the starting temperature;

• the time intervals;

• the temperature at each interval;

• the units;

• the trend in the data;

• any anomalous result.

A graph may then be added during editing so the viewer can see the pattern.

This is particularly important for students. They need to learn that the conclusion comes from the evidence, not from the presenter simply announcing the answer.

Lighting Must Help the Viewer See the Science

Laboratory lighting is often designed to illuminate a room, not to produce good video.

Overhead lights can create shadows, reflections and patches of excessive brightness. Glassware can disappear against a pale background. Digital displays may flicker or become unreadable. Dark equipment can lose all visible detail.

Good lighting does not need to be dramatic. It needs to reveal the important features of the experiment.

Light the subject, not just the room

A soft light placed in front of the apparatus can make a substantial difference.

Additional side lighting may help reveal:

• the shape of transparent glassware;

• bubbles in a liquid;

• texture on a specimen;

• movement of smoke;

• surface detail;

• small changes in colour.

Choose the background carefully

The background should contrast with the subject.

A colourless liquid may be difficult to see against a pale bench. A dark background can make it clearer. Smoke or vapour may show better against black or blue. A dark specimen may need a light background.

For some demonstrations, changing the background is more effective than adding more lighting.

Control reflections

Glass vessels, polished metal and instrument screens can reflect lights, cameras and the presenter.

Moving the light slightly to one side may remove a distracting reflection. A camera positioned directly in front of a glass container may need to be shifted a few degrees. Sometimes a simple black card beside the apparatus can reduce unwanted glare.

These details may appear minor, but they can determine whether the viewer sees the actual result.

Sound Is Part of the Explanation

Viewers will tolerate an imperfect picture more readily than unclear sound.

A laboratory can be acoustically difficult. Extractor fans, pumps, computers, power supplies and air conditioning may all create background noise. Hard walls and benches can produce echoes.

The presenter may also turn away from the camera while handling equipment, causing their voice level to change.

A dedicated microphone is usually better than relying on the microphone built into the camera.

Depending on the experiment, this might be:

• a lapel microphone;

• a small directional microphone;

• an overhead microphone;

• a separate audio recorder;

• a studio microphone used for narration afterwards.

Recording narration separately can be particularly useful. It allows the experiment to be performed safely and carefully without the presenter trying to operate equipment and deliver a perfect explanation at the same time.

Natural experiment sounds can also be valuable.

The click of a relay, the bubbling of gas, the snap of a spark or the change in pitch of a moving sound source may all be part of the evidence. These sounds should be recorded clearly, but never at the expense of an understandable explanation.

Safety Must Be Visible as Well as Practised

Science videos influence how other people attempt experiments.

It is therefore important not only to work safely, but also to show the relevant precautions.

This might include:

• wearing eye protection;

• tying back long hair;

• using gloves where appropriate;

• keeping ignition sources away from flammable materials;

• using safety screens;

• securing heavy apparatus;

• working with small quantities;

• using tongs or heatproof mats;

• checking electrical equipment;

• explaining why an experiment should not be attempted without supervision.

Safety information should be proportionate.

There is no need to turn every video into a lengthy risk-assessment lecture, but the viewer should not be encouraged to copy a potentially hazardous procedure without understanding the risks.

The camera position must also be considered.

A tripod should not block an escape route. Cables should not create trip hazards. Cameras should be protected from chemicals, heat, water and moving equipment. The desire for a dramatic close-up should never place a camera operator in danger.

One of the advantages of using remotely controlled cameras is that they can be positioned close to an experiment while everyone remains at a safe distance.

Explain What the Viewer Should Notice

One of the most important phrases in any science video is:

“Watch what happens to…”

Without guidance, viewers may focus on the wrong part of the screen.

In a displacement reaction, they may watch the liquid when the important change is occurring on the metal surface. In a wave demonstration, they may look at the source rather than the reflected wave. During electrolysis, they may notice the bubbles but not compare the volume of gas at each electrode.

Before the important moment, tell the viewer what to observe.

For example:

“Watch the surface of the copper wire as it enters the silver nitrate solution.”

Or:

“Look carefully at the movement of the pepper immediately after the detergent touches the water.”

Or:

“Notice that the trolley continues moving while the ball rises and falls.”

This short instruction turns passive watching into purposeful observation.

The explanation after the event can then connect the observation to the scientific principle.

Use Captions and Graphics to Reinforce the Science

Captions are useful for far more than accessibility.

They can identify:

• the independent variable;

• the dependent variable;

• control variables;

• measurement units;

• chemical names;

• equations;

• forces;

• key vocabulary;

• equipment;

• stages in the method.

A label placed beside a component can prevent a long verbal explanation. An arrow can show the direction of a force. A timer can reveal the duration of an event. A graph can show a trend that was not obvious during the live experiment.

For example, a video of a projectile launched from a moving trolley might include arrows representing:

• horizontal velocity;

• vertical velocity;

• gravitational acceleration.

The real footage shows what happened. The graphics help explain why.

However, captions should not overcrowd the screen. A science video can quickly become confusing if equations, labels, subtitles and moving images all compete for attention.

Graphics should appear when they are needed and disappear when their purpose has been served.

Slow Motion Can Reveal Hidden Events

Some scientific events happen too quickly for the human eye to analyse.

Slow-motion footage can reveal:

• the deformation of a bouncing ball;

• the moment a droplet hits a surface;

• the movement of a flame;

• a collision between trolleys;

• the oscillation of a spring;

• the release of a projectile;

• the collapse of a soap film;

• the moment a circuit contact is made.

Slow motion is most useful when it answers a scientific question.

It should not be added simply to make a video look dramatic.

A collision, for example, can be replayed frame by frame to identify:

• the point of contact;

• the direction of movement;

• changes in velocity;

• deformation;

• rebound;

• energy transfer.

The replay becomes a measurement tool as well as a visual effect.

Microscopes Need Their Own Recording Strategy

Microscopy presents a special filming challenge because the viewer needs both context and detail.

A useful microscope sequence might include:

1. The specimen being prepared.

2. The slide being placed on the stage.

3. The objective lens being selected.

4. The low-power image.

5. The area of interest being centred.

6. The higher-power image.

7. Labels identifying important structures.

8. A scale bar or magnification.

It is tempting to begin immediately with the impressive microscopic image. However, showing how that image was obtained helps students understand the process.

For example, when examining iron particles separated from fortified cereal, the video could show the cereal being crushed, the magnet collecting the particles, the sample being transferred to a slide and the final microscope image.

The viewer then sees a complete investigation rather than an isolated image.

Preserve the Unexpected Results

Not every experiment works perfectly.

A reading may be inconsistent. A sample may be contaminated. A reaction may be slower than expected. A sensor may lose connection. The apparatus may behave differently from the prediction.

It can be tempting to remove all such moments during editing.

Sometimes that is appropriate. A video should not become a record of every technical problem.

However, an unexpected result can provide excellent teaching material.

It allows discussion of:

• experimental error;

• uncontrolled variables;

• reliability;

• repeat measurements;

• calibration;

• contamination;

• limitations of the method;

• improvements to the apparatus.

Real science is not a sequence of flawless demonstrations. It involves testing, checking and trying again.

Showing a failed attempt followed by an improved method can be more educational than showing only the successful result.

It also encourages students to see practical work as an investigation rather than a performance in which the “correct” result must appear immediately.

Separate the Experiment From the Explanation When Necessary

Trying to perform an experiment, monitor several cameras, watch the measurements, maintain safety and deliver a perfect explanation at the same time is difficult.

There is no requirement for every science video to be recorded in one continuous take.

A more effective process may be:

• record the introduction;

• record the apparatus;

• perform the experiment;

• capture close-ups separately;

• record the measurements;

• film the conclusion;

• add narration during editing.

This provides greater control and usually produces a clearer explanation.

The final video can still feel natural. The aim is not to deceive the viewer, but to present the process in a way that helps them understand it.

Any repeated or reconstructed shots should remain scientifically honest. A close-up recorded separately should accurately represent the experiment being described.

A Practical Recording Workflow

A dependable workflow can prevent many common problems.

Before recording

• Define the learning objective.

• Test the experiment.

• Complete the safety checks.

• Prepare spare materials.

• Write a simple shot list.

• Clean the bench and background.

• Charge cameras and microphones.

• Check storage space.

• Set the correct frame rate and resolution.

• Test the lighting.

• Check every important measurement is readable.

• Record a short sound test.

During recording

• Record several seconds before beginning each action.

• Keep hands away from important details where possible.

• Announce measurements clearly.

• Repeat important readings.

• Capture both wide and close views.

• Check focus before irreversible events.

• Allow time for the viewer to observe the result.

• Record additional detail shots after the main experiment.

After recording

• Check that the critical moment was captured.

• Confirm that measurements can be read.

• Save and back up the footage.

• Organise files by camera and experiment.

• Synchronise the camera angles.

• Remove unnecessary pauses without making the process misleading.

• Add captions, diagrams and units.

• Check scientific terminology.

• Include relevant safety information.

• Add a clear conclusion.

What Students Should Take Away

A strong experiment video should leave students with more than a memorable image.

They should be able to explain:

• what was changed;

• what was measured;

• what was controlled;

• what happened;

• why it happened;

• whether the evidence supports the conclusion;

• how the method could be improved.

That is the difference between a science demonstration and science education.

The demonstration says, “Look at this.”

The educational video says, “Look at this carefully, notice this particular change, connect it to this principle, and consider whether the evidence is reliable.”

Clarity Creates the Real Impact

Spectacle has its place.

A dramatic opening can attract attention. An unusual experiment can stimulate curiosity. Slow motion, microscopic images and multiple camera angles can make science look extraordinary.

But none of these techniques can replace a clear scientific purpose.

The most successful science videos combine visual interest with disciplined explanation. They use camera angles to reveal evidence, lighting to expose detail, sound to communicate clearly, measurements to support conclusions and captions to direct attention.

The aim is not simply to make an experiment look impressive.

It is to give viewers the feeling that they have been brought close enough to the experiment to observe it for themselves.

When a student can see exactly what happened, understand why it happened and recognise how the conclusion was reached, the camera has done far more than record a spectacle.

It has become part of the scientific instrument.

 

Timelapse Photography: Showing Change That Is Too Slow to Notice

Some of the most interesting changes happening around us are almost impossible to see.

A plant turns gradually towards the light. Clouds build above the horizon. A flower opens. Varnish dries across a newly restored piece of wood. A 3D printer slowly builds an object one layer at a time. A laser cutter transforms a blank sheet of material into a finished design.

We know these processes are happening, but they usually take place too slowly for us to observe them directly.

Timelapse photography changes that.

By taking photographs at regular intervals and then playing them back as a video, hours, days or even weeks can be compressed into a few seconds. The gradual becomes immediate. The invisible becomes visible. A process that might otherwise appear uneventful can become fascinating.

For Philip M Russell Ltd, timelapse photography is more than a photographic technique. It can be used to document experiments, explain scientific ideas, record workshop projects, study nature and show the amount of work that goes into creating something.

What Is Timelapse Photography?

Ordinary video records many frames every second. When those frames are played back at the same rate, movement appears at its normal speed.

Timelapse photography works differently.

Instead of recording continuously, the camera takes individual photographs at intervals. These might be:

• one photograph every second;

• one photograph every ten seconds;

• one photograph every minute;

• one photograph every hour;

• or even one photograph every day.

The photographs are then combined and played back as a video.

At 25 frames per second, 250 photographs produce approximately ten seconds of finished footage. If one photograph is taken every minute, those 250 frames represent more than four hours of real time.

A slow process can therefore be compressed into something short enough to watch, study and share.

Revealing the Movement of Plants

Plants often appear stationary, but they are constantly responding to their surroundings.

They turn towards light, open and close flowers, raise and lower leaves, grow around obstacles and react to changes in temperature and moisture.

Most of this movement happens too slowly for us to notice.

A simple timelapse can reveal:

• a seedling emerging from the soil;

• a shoot bending towards a window;

• a sunflower tracking the light;

• a flower opening in the morning;

• leaves moving during the day;

• climbing plants searching for support;

• roots developing against the side of a transparent container.

This can produce attractive nature footage, but it can also become a useful scientific resource.

For example, two similar seedlings could be placed in different conditions. One might receive light from above, while the other receives light from one side. A timelapse would make the difference in their growth patterns much easier to see than a series of written measurements alone.

The result becomes both an experiment and a visual explanation.

Watching Clouds and Weather Develop

Weather is another ideal subject for timelapse photography.

When we look at the sky, clouds may seem to drift slowly and almost randomly. Compress an hour into twenty seconds, however, and the atmosphere suddenly appears dynamic.

Clouds form, merge, rise and disappear. Shadows sweep across the landscape. Rain showers move through. Wind direction becomes visible through the changing movement of the cloud layers.

A weather timelapse might record:

• clouds building before a thunderstorm;

• morning mist clearing from a river;

• changing light across a garden;

• a weather front arriving;

• rain clouds passing over a sailing club;

• the movement of shadows through the day;

• sunset followed by the appearance of stars.

This can be particularly effective when combined with weather-station information. Wind speed, rainfall, temperature and pressure readings can help explain what is happening in the video.

Instead of simply saying that conditions changed during the afternoon, we can show the change taking place.

Timelapse in the Workshop

Many workshop projects involve long periods when very little appears to be happening.

A 3D printer may take several hours to produce a component. A laser cutter may follow hundreds of lines to build up an engraved image. A sewing or embroidery project develops through many repeated stages. A boat repair may require preparation, filling, sanding, priming, painting and finishing.

A viewer does not necessarily need to watch every minute of that process. However, reducing it to a few seconds can create an engaging record of the work.

Possible workshop timelapses include:

• a 3D-printed component growing layer by layer;

• a laser-etched design gradually appearing;

• a sheet of material being cut into a finished shape;

• a machine-embroidery design being stitched;

• a vinyl decal being prepared and applied;

• a model or piece of equipment being assembled;

• a damaged surface being repaired and refinished;

• a workbench changing from a collection of parts into a finished project.

These videos can be especially valuable when showing that a finished object did not simply appear.

The audience sees the stages, the tools, the adjustments and the decision-making involved. Timelapse does not remove the work from the story. It makes the scale of the work easier to understand.

Recording the Restoration of Champagne

The restoration and improvement of Champagne, our Thames A-Rater, provides many possible timelapse subjects.

A camera could record:

• sanding and preparing a wooden component;

• varnish being applied;

• a repaired area progressing through several stages;

• new decals being positioned;

• a pennant being designed and made;

• a cover being measured, cut and assembled;

• the boat being prepared before sailing;

• the mast and rigging being put into place.

Some of these jobs take much longer than they appear to in a short finished video.

A thirty-second timelapse of sanding, varnishing or fitting a component can communicate the patience involved far more effectively than a single photograph of the finished result.

It can also create a useful visual history of the boat. Months or years later, we will still be able to look back at how each part was repaired or improved.

Drying, Curing and Other Almost Invisible Processes

Some processes are difficult to photograph because the change is extremely gradual.

Fresh varnish may look almost identical from one minute to the next. Paint slowly loses its gloss as it dries. Glue cures. Water evaporates. Crystals form. A damp material changes colour. Ice melts.

Timelapse can expose these transitions.

For example, a camera positioned above a varnished test piece might record changes in surface reflection as the varnish dries. A separate clock, temperature display or humidity reading could be placed in the frame to provide context.

This turns what might otherwise be a simple workshop recording into a small investigation.

Questions could include:

• How long does the surface remain visibly wet?

• Does drying occur evenly?

• Does warmer air noticeably reduce the drying time?

• How does humidity affect the result?

• When is the surface safe to handle?

Timelapse can therefore become a tool for observation, not merely presentation.

Making Science Experiments More Visible

Some experiments happen too quickly for the eye to follow. These are often best recorded with slow-motion video.

Other experiments happen too slowly. These are ideal for timelapse.

Examples include:

• crystal growth;

• evaporation;

• rust formation;

• diffusion through a gel;

• plant germination;

• mould growth in a controlled investigation;

• water movement through plant stems;

• the gradual cooling of an object;

• changes in shadows during the day;

• movement caused by convection over a longer period.

A timelapse can help students identify patterns that would be difficult to notice from occasional observations.

It is still important to collect measurements. Timelapse photography should not replace temperature readings, mass measurements, dimensions or written observations where these are required.

Instead, it adds another form of evidence.

A graph might show that a value changed. A timelapse can show how that change appeared.

Documenting Progress Rather Than Only Results

One of the weaknesses of ordinary project photography is that we often remember to photograph the beginning and the end, but not the work in between.

We photograph the uncut material and then the finished product. We photograph the damaged boat and then the repaired boat. We photograph the empty workbench and then the completed experiment.

The most interesting part may be everything that happened between those two images.

Timelapse provides a continuous visual account of progress.

This is useful for:

• company blogs;

• YouTube project videos;

• educational demonstrations;

• social-media posts;

• workshop records;

• design reviews;

• personal reflection;

• troubleshooting when something goes wrong.

It can also help us evaluate our own working methods.

Watching a project back may reveal how often tools were moved, how much time was spent searching for parts, where the workflow slowed down or which stages could have been prepared more efficiently.

The camera becomes an observer of the process.

Choosing the Right Interval

The interval between photographs determines how the finished timelapse will look.

For fast-moving clouds, a photograph every one or two seconds may work well.

For a 3D print, an interval of five to thirty seconds may be more appropriate, depending on the length of the print.

For a flower opening, one photograph every thirty seconds or every few minutes might be suitable.

For plant growth over several days, the interval might be ten minutes, thirty minutes or one hour.

There is no single correct setting. The decision depends on three questions:

1. How long will the process take?

2. How quickly is the subject changing?

3. How long should the finished video be?

Suppose a process lasts four hours and the camera takes one photograph every minute. That produces 240 photographs, or just under ten seconds of video at 25 frames per second.

That may be perfect for a short social-media clip.

However, a detailed educational explanation might benefit from a longer sequence, a slower playback speed or occasional pauses and captions.

Keeping the Camera Stable

Camera movement is one of the most common causes of disappointing timelapse footage.

Even a small change in position can make the finished video appear to jump or shake.

The camera should therefore be mounted securely.

Depending on the project, this might involve:

• a strong tripod;

• a clamp attached to a bench;

• an overhead camera support;

• a suction mount;

• a purpose-built 3D-printed bracket;

• a weather-protected outdoor mount.

The tripod should not be positioned where it will be knocked while people work around it. Cables should be secured. The framing should allow enough room for the project to develop without moving out of shot.

For long projects, it is also worth marking the position of the tripod and subject. This makes it easier to restore the setup if something has to be moved.

Controlling Light and Exposure

Changes in lighting can create flicker.

Automatic exposure may brighten one frame and darken the next. Indoor lights may be switched on and off. Sunlight may move across the scene. Clouds may repeatedly change the brightness.

Where possible, manual settings should be used so the camera does not constantly alter the exposure.

For indoor workshop projects, consistent artificial lighting usually produces the most reliable result.

For outdoor projects, some lighting change is inevitable—and may actually be part of the story. A timelapse of a garden or river should show the changing light.

The important point is to decide whether changing light is a problem or part of the subject.

Power, Storage and Long Recordings

A timelapse lasting several hours can easily be ruined by a flat battery or full memory card.

Before starting, it is sensible to check:

• battery capacity;

• external power options;

• available storage;

• image resolution;

• expected number of frames;

• weather protection;

• whether the camera is likely to overheat;

• whether anyone might accidentally switch it off.

For projects lasting several days, the camera may need a continuous power supply.

The setup should also be tested before the real event begins. A short ten-minute trial can reveal framing, focus or exposure problems that would otherwise spoil an entire day’s recording.

Combining Timelapse with Ordinary Video

A complete project video does not need to use only one filming technique.

Timelapse works best when combined with:

• normal-speed footage;

• close-up detail shots;

• photographs of important stages;

• spoken explanations;

• diagrams;

• measurements;

• captions;

• before-and-after comparisons.

For example, a video about laser etching might begin with a normal-speed explanation of the design. A timelapse could then show the engraving process. Close-up footage could reveal the finished surface, followed by a discussion of the settings used.

The timelapse provides pace and visual interest, while the ordinary video provides detail and explanation.

What Timelapse Teaches Us About Patience

There is something slightly misleading about timelapse photography.

A project that took six hours may appear to have been completed in fifteen seconds.

That can make the process look effortless.

However, when used thoughtfully, timelapse can communicate the opposite. It shows the number of stages involved, the repeated movements, the gradual development and the persistence required to reach the finished result.

This is one reason I find timelapse particularly suitable for the work carried out through Philip M Russell Ltd.

Much of what we do involves experimentation, preparation, adjustment and learning. Whether we are creating teaching equipment, filming a scientific demonstration, repairing a boat, photographing nature or manufacturing a component, the final result is only part of the story.

The process matters.

Final Thoughts: Making the Invisible Visible

Timelapse photography allows us to watch the world at a different speed.

It can reveal a plant moving towards the light, clouds building above a river, a printed object emerging from a machine or a repair developing through many careful stages.

It can support science, improve project documentation and create engaging photographs and videos. More importantly, it encourages us to pay attention to gradual change.

Many worthwhile things do not happen instantly.

Plants grow slowly. Skills develop slowly. Experiments take time. Restoration requires patience. Designs improve through repeated testing.

We may not notice the difference from one minute to the next, but change is still taking place.

Timelapse photography captures that change—and reminds us that progress is often happening even when it is too slow to see.

 

Making the Best Use of AI: Why Plugins, Appsal intelligence is powerful on its own. 

It can generate ideas, analyse information, improve writing, create plans, suggest solutions and help us think through a problem.

However, AI becomes considerably more useful when it is connected to other specialist tools.

What many people still call plugins are increasingly described as apps or connectors. These allow an AI system such as ChatGPT to work alongside services including Canva, cloud storage, calendars, spreadsheets, research tools and business applications. Instead of simply telling us what to do, the AI can help move the work into the application where it will be completed. nges AI from being merely a clever conversational assistant into something closer to a creative director, project coordinator and production assistant.

The difference is not simply speed. Used properly, these connections can improve the quality, consistency and usefulness of the final result.

AI Is Powerful, but It Cannot Do Every Job Equally Well

One of the mistakes people make when using AI is expecting one system to perform every part of a task perfectly.

ChatGPT may be excellent at:

• developing an idea;

• researching a subject;

• organising information;

• writing a detailed creative brief;

• suggesting a visual structure;

• reviewing a draft;

• identifying weaknesses;

• producing revised instructions.

Canva, meanwhile, specialises in:

• creating layouts;

• combining text and graphics;

• applying fonts and colours;

• producing social media graphics;

• preparing presentations;

• resizing designs;

• working with templates;

• producing editable visual content.

The two tools have different strengths.

ChatGPT can decide what the design needs to communicate. Canva can help turn those instructions into an actual visual design.

That is the real value of connecting AI systems to specialist applications.

Think of the AI as the Director

A useful comparison is a film production.

The director does not personally operate every camera, build every set, adjust every light and edit every frame. The director decides what the production is trying to achieve and coordinates the specialists who make it happen.

AI can take a similar role.

It can help determine:

• the audience;

• the objective;

• the central message;

• the visual hierarchy;

• the emotional tone;

• the words that should appear;

• the information that should be omitted;

• the most suitable format.

It can then pass a structured set of instructions to Canva.

This is much more effective than entering a vague instruction such as:

Make me a good social media image about AI.

Canva may still produce something attractive, but “good” is subjective. The tool does not yet know who the image is for, where it will be published, what message matters most or what should receive the viewer’s attention.

The more precise the direction, the more controlled the result.

A Practical Example: Creating a Social Media Image

Suppose I have written a blog called:

Making the Best Use of AI

I want a square image for LinkedIn, Facebook and Instagram.

My first instruction might be:

Create a social media image about using ChatGPT with Canva.

This might generate a reasonable starting point. However, it leaves most of the important creative decisions to the system.

A stronger instruction would be:

Canva, create a 1080 × 1080-pixel social media graphic promoting a business blog called “Making the Best Use of AI”.

Show a professional workspace in which an AI conversation develops into a polished graphic design. Use a clear left-to-right visual journey: an idea or prompt on the left, an AI processing stage in the centre and a finished social media design on the right.

Use a modern, intelligent and practical style rather than science fiction. Avoid robots, glowing humanoid faces, excessive circuitry and meaningless streams of computer code.

Use a dark navy, white and warm gold colour palette. Add subtle blue highlights. Keep the background uncluttered.

The main headline must read: “Making the Best Use of AI”.

Add the smaller supporting line: “Better prompts. Connected tools. Better results.”

Make the headline the strongest visual element. Leave generous margins around all text and keep important content away from the edges.

Add “Philip M Russell Ltd” discreetly at the bottom.

The finished image should look professional, educational and suitable for a business audience.

That instruction controls:

• the dimensions;

• the purpose;

• the audience;

• the composition;

• the style;

• the colours;

• the headline;

• the supporting message;

• the branding;

• the elements to avoid.

The design tool is no longer being asked to guess what I want. It has been given a proper creative brief.

Canva’s ChatGPT app can create, edit and preview designs from within a conversation, with the option to continue customising the result in Canva. irst Result Should Be Treated as a Draft

One of the biggest misunderstandings surrounding AI is the belief that a prompt should produce a perfect result immediately.

Professional creative work rarely operates that way.

A photographer does not expect every frame to be the final photograph. A writer revises a first draft. A designer experiments with layout, spacing and visual hierarchy.

AI-generated work should be approached in the same way.

The first result gives us something concrete to examine.

We can then ask:

• Is the headline easy to read?

• Is the purpose immediately obvious?

• Is the image too busy?

• Does the background compete with the text?

• Does it look like our business?

• Is the supporting text too small?

• Does the image contain unnecessary generic AI imagery?

• Will it still work when viewed on a mobile telephone?

• Is there enough contrast?

• Is the most important element receiving the most attention?

This is where ChatGPT becomes useful again.

Using ChatGPT as an Art Director

After Canva has produced the first design, the result can be reviewed by ChatGPT.

A useful review instruction might be:

Act as an experienced social media art director. Review this design for clarity, visual hierarchy, mobile readability and professional credibility.

Identify the three most important weaknesses. Then write precise editing instructions for Canva. Do not redesign it completely unless necessary. Preserve the central concept and brand colours.

ChatGPT might then recommend changes such as:

Increase the headline size and reduce the amount of decorative background detail.

Move the finished-design panel slightly to the right so that it does not compete with the central AI symbol.

Increase the contrast behind the supporting line and shorten it to improve mobile readability.

Reduce the number of glowing interface elements because they make the design appear too much like a generic technology advertisement.

Those instructions can then be sent back to Canva.

The process becomes a creative loop:

Idea → brief → design → review → correction → final design

This is much more powerful than asking for a single image and accepting whatever appears.

Write Editing Commands, Not Vague Opinions

When improving a design, vague reactions are not particularly useful.

Saying:

I don’t really like it.

does not tell the AI what needs to change.

A controlled editing command should identify:

1. what is wrong;

2. what should change;

3. what must remain unchanged;

4. why the change is needed.

For example:

Keep the existing layout and navy-and-gold colour palette. Remove the robot illustration and replace it with a clean visual showing a written prompt becoming an editable Canva design. Make the image feel practical and businesslike rather than futuristic. Do not change the headline or company name.

Another useful command would be:

Preserve the background image and overall composition. Enlarge the headline by approximately 15 per cent, move it slightly upwards and add a subtle dark overlay behind it. Increase the contrast without covering the main subject.

These are production instructions rather than general comments.

The clearer the correction, the less likely the system is to alter parts of the design that were already working.

A Seven-Part Formula for Better Canva Instructions

When asking ChatGPT to write instructions for Canva, I find it useful to include seven elements.

1. Purpose

What is the image intended to achieve?

Is it promoting a blog, advertising a course, explaining a scientific idea or announcing an event?

2. Format

Specify the required size and destination.

For example:

• 1080 × 1080 pixels for a square social post;

• 1200 × 628 pixels for a blog or link preview;

• 1080 × 1920 pixels for a story;

• A4 portrait for a printable information sheet;

• 16:9 for a presentation slide or YouTube thumbnail.

3. Audience

A design for A-level students should not necessarily look like a design for company directors.

State who needs to understand or respond to the image.

4. Main Message

Decide what the viewer should understand within the first few seconds.

One strong headline is usually better than several competing messages.

5. Visual Direction

Describe the scene, layout, focal point, photographic style or illustration style.

“Professional photograph of a teacher using AI” is still broad.

“Over-the-shoulder photograph of an experienced teacher using an AI assistant to develop a colourful science worksheet, with laboratory equipment softly visible in the background” is far more useful.

6. Brand Controls

Include colours, logo position, company name, preferred style and any fonts or visual conventions that matter.

Where supported, connected design workflows can also apply brand assets and produce editable content rather than leaving the user with an unchangeable flat image. Canva has also introduced technology that can convert generated imagery into layered, editable designs. egative Instructions

Tell the system what must not appear.

For example:

• no robots;

• no distorted hands;

• no meaningless code;

• no excessive neon lighting;

• no tiny text;

• no clutter;

• no American classroom imagery;

• no unrelated icons;

• no invented company logos.

Negative instructions are particularly important when trying to avoid the familiar, generic appearance of AI-generated advertising.

The Importance of Keeping Designs Editable

A completely finished flat image may look impressive, but it can become a problem when something needs to change.

Perhaps the date is wrong. The headline needs shortening. The image needs resizing. A logo must be moved. The same design is required for LinkedIn, Instagram and a website banner.

Editable design elements are therefore extremely valuable.

Text should remain editable. Backgrounds should be replaceable. Logos should be movable. Individual objects should be adjustable. Colours should be changeable.

This allows AI to create the first version without taking control away from the human user.

The objective should not be to remove people from the design process. It should be to remove unnecessary repetitive work while preserving human judgement.

One Design Can Become a Complete Campaign

Once the main image has been approved, ChatGPT can help create instructions for a family of related materials.

For example:

Using the approved square design as the master style, create:

• a 1200 × 628-pixel blog header;

• a 1080 × 1920-pixel story;

• a LinkedIn banner;

• a presentation title slide;

• an A4 promotional poster.

Preserve the navy, white and gold palette, the central visual concept and the company branding. Adjust the layout for each format rather than simply stretching the original. Keep all text editable.

This is where the combination begins to save substantial time.

The AI is no longer creating one isolated graphic. It is helping establish a consistent visual campaign.

The same approach can be used for:

• course advertisements;

• sailing event announcements;

• science experiment videos;

• company blog promotions;

• educational worksheets;

• YouTube thumbnails;

• presentation slides;

• posters;

• photographic exhibitions;

• product information.

AI Can Also Help Before Canva Is Opened

The connection between ChatGPT and Canva is useful, but the preparation can begin even earlier.

ChatGPT can first help decide:

• which words belong on the image;

• which words belong in the accompanying post;

• which visual metaphor would communicate the idea;

• whether a photograph, diagram or illustration would work best;

• which image dimensions are needed;

• how the same campaign should vary between platforms;

• which details are essential;

• which details would create clutter.

For example, I might ask:

Give me five visual concepts for an article about connecting AI to specialist tools. Avoid robots, human brains and glowing circuit boards. Each concept should be understandable without a long explanation.

ChatGPT could suggest:

• an orchestra conductor coordinating specialist instruments;

• a central control desk connected to different creative tools;

• a rough sketch passing through several specialist workstations;

• a workshop in which the AI supplies plans while specialist machines build the result;

• a relay race in which each application completes the stage it performs best.

I can then select the strongest idea before asking Canva to produce anything.

That prevents time being wasted developing the wrong concept.

Connected AI Requires Sensible Judgement

Apps and connectors can make workflows more capable, but they should be used carefully.

Before enabling a connection, it is sensible to understand what information the application may receive and what actions it can perform. OpenAI explains that an enabled app may use relevant conversational context to help fulfil a request. ns we should avoid casually including confidential client information, private student details, passwords, financial data or other sensitive material in a design workflow.

Every final design should also be checked by a person.

AI can:

• misspell words;

• invent details;

• misunderstand branding;

• produce inappropriate imagery;

• create poor contrast;

• position text outside safe areas;

• use an unsuitable visual style;

• alter details that should have remained fixed.

Connection does not remove the need for inspection. It makes informed human supervision more important.

My Own View: The Skill Is Becoming Direction

The more I use AI, the more I realise that the most valuable ability is not simply knowing how to type a prompt.

The real skill is learning how to direct the process.

That means being able to say:

• what the work is for;

• who it is for;

• what success looks like;

• what must remain consistent;

• what needs changing;

• what should be removed;

• when the result is good enough to publish.

A vague prompt transfers nearly every decision to the machine.

A detailed prompt keeps the human in control.

This is particularly important in my own work because I may move between teaching, photography, scientific demonstrations, sailing, video production, music and business administration. The same visual style will not suit every project.

An A-level physics graphic needs clarity and scientific credibility. A sailing photograph needs movement and excitement. A company announcement needs professionalism. A YouTube thumbnail needs immediate impact.

AI can help with all of them, but only when it is given suitable direction.

Conclusion: Connect the Intelligence to the Right Tool

AI is impressive when it can produce an answer.

It becomes far more useful when it can help us complete a process.

Connecting ChatGPT to Canva illustrates the wider opportunity. ChatGPT can develop the idea, write the brief, create the words, suggest the composition and review the result. Canva can produce the layout, manage the visual elements and turn those instructions into an editable design.

Neither tool replaces the other.

More importantly, neither replaces the person directing the project.

The best results come from combining:

human purpose, AI reasoning and specialist applications.

The future of productive AI is not one machine trying to do everything. It is a collection of capable tools, connected intelligently and directed by someone who knows what the finished work needs to achieve.

The first prompt may create something interesting.

The complete, controlled workflow can create something genuinely worth publishing.

 

Which AI Should I Use? Choosing the Right Tool for the Job

Artificial intelligence is no longer a single product or a single website. It is becoming an entire toolbox.

That creates a new problem.

We are constantly being told that we should use AI, but we are not always told which AI we should use for a particular job.

Should we use ChatGPT, Claude, Gemini, Microsoft Copilot or Perplexity? Should we create an image in Canva, Adobe Firefly or ChatGPT? Should we use a specialist system for video, music, coding or voice generation? Should we configure our own AI assistant, or connect several systems together using plugins?

The answer is not to find one AI that supposedly does everything.

The better approach is to understand the job, select the right tool and build a reliable process around it.

There Is No Single “Best AI”

Asking which AI is best is rather like asking:

Which is the best tool in a workshop?

A screwdriver is excellent when you need to turn a screw, but fairly useless when you need to cut a sheet of plywood. A laser cutter is extremely powerful, but it would be ridiculous to use it simply to open a cardboard box.

AI tools work in much the same way.

There is considerable overlap between systems, but they have different strengths, integrations and working methods.

Some are general-purpose assistants. Some specialise in research. Others are built into office software. Some generate images, video, voices or music. Others help programmers write and test code.

At Philip M Russell Ltd, the range of possible AI tasks is already enormous.

On one day, AI might help me:

• turn a set of rough notes into a structured company blog;

• create an X post and a LinkedIn post;

• design a worksheet for an individual student;

• analyse a spreadsheet;

• suggest categories for bank transactions;

• write part of a sailing weather application;

• develop a script for a science video;

• plan an infographic;

• or explore ideas for a piece of music.

Those are all “AI tasks”, but they are not necessarily jobs for the same AI.

Start With the Job, Not the Brand

Before choosing an AI, ask five practical questions.

1. What am I actually trying to produce?

Do you need:

• an idea;

• a polished article;

• a researched answer;

• a spreadsheet;

• an image;

• a video;

• computer code;

• a voiceover;

• a piece of music;

• or an action completed in another system?

The final output often determines which AI is most suitable.

2. Does the answer need current information?

There is a major difference between asking an AI to improve a paragraph you have written and asking it to explain the latest changes to tax rules, examination specifications or energy tariffs.

For current information, you need an AI that can research live sources and show where its information came from.

3. Do I need the AI to use my own material?

An AI may need access to:

• company documents;

• course notes;

• spreadsheets;

• previous articles;

• brand guidelines;

• photographs;

• email messages;

• calendars;

• or technical manuals.

In that case, a Project, knowledge base or connected application may be more useful than an ordinary one-off chat.

4. Does the AI only need to advise me, or must it take action?

There is a substantial difference between:

“Write an email reminding a customer about an invoice.”

and:

“Find the correct customer, create the email, attach the invoice and place the message in my Gmail drafts.”

The first is a writing task.

The second is a connected workflow involving data, permissions and external actions.

5. How sensitive is the information?

Before uploading any document or connecting an account, consider whether it contains:

• personal information;

• student data;

• financial records;

• passwords;

• confidential business material;

• health information;

• or unpublished intellectual property.

Convenience should never replace sensible data handling.

A Practical Guide to Different AI Tools

The following is not a league table. It is a practical guide to where different systems may fit.

Features and subscription arrangements change frequently, so the important lesson is to understand the category of tool rather than memorising a fixed list.

ChatGPT: A Strong General-Purpose Starting Point

ChatGPT is useful for a wide range of tasks, including:

• brainstorming;

• writing and rewriting;

• lesson planning;

• explaining concepts;

• analysing documents;

• working with spreadsheets;

• generating and editing images;

• writing code;

• creating reusable files;

• and building customised assistants.

ChatGPT Projects allow related chats, reference files and custom instructions to be kept together, making them particularly useful for repeated work such as regular content creation, research or planning.

ChatGPT can also analyse common spreadsheet formats, including Excel and CSV files, while its image tools can create or edit images from natural-language instructions.

A good choice for: general business work, teaching resources, planning, writing, data analysis and workflows that combine several different types of task.

Claude: Long-Form Thinking, Documents and Interactive Artifacts

Claude is often useful when working with lengthy documents, detailed analysis, structured writing or substantial pieces of content.

Its Projects can hold their own instructions, documents, knowledge and chat histories. Its Artifacts feature can place substantial content, applications, visualisations and other reusable outputs into a separate working area.

A good choice for: long reports, detailed editing, document analysis, structured thinking and creating interactive prototypes or tools.

Gemini: Google-Connected and Multimodal Work

Gemini is particularly relevant to people who already work extensively with Google services.

Its current feature set includes connected applications, Deep Research, image tools, Canvas, live conversation and custom Gems. Feature access and usage limits vary between subscription levels.

A Gem performs a similar broad role to a customised assistant: it can be configured for a repeatable type of task.

A good choice for: people working heavily with Google services, multimodal questions, web research and Google-centred workflows.

Microsoft 365 Copilot: Working Inside Office Applications

Microsoft 365 Copilot is designed to work within applications such as Word, Excel, PowerPoint, Outlook and Teams.

For example, it can assist with drafting in Word, suggest formulas or analyse data in Excel, summarise email discussions in Outlook and help summarise meetings in Teams.

This can be more convenient than transferring material between an office application and a separate AI chat.

A good choice for: businesses whose documents, spreadsheets, presentations, emails and meetings already live in Microsoft 365.

Perplexity: Current Web Research With Sources

Perplexity describes itself as an AI answer engine that researches the live web and produces concise answers with citations.

It can therefore be useful at the beginning of a project when you need to establish:

• what has recently changed;

• what different sources are saying;

• what research is available;

• or where a particular claim originated.

However, cited research still needs to be checked. A citation proves that a source exists; it does not automatically prove that the source is reliable or that the AI has interpreted it correctly.

A good choice for: initial research, current information and finding sources for further investigation.

Gemini Notebook, Formerly NotebookLM: Learning From Your Own Sources

Gemini Notebook is especially useful when the priority is to work from a defined collection of source material.

You can upload documents and use them to generate summaries, questions, flashcards, quizzes, study materials and audio-style overviews. Its responses are designed to remain grounded in the sources supplied to it.

For a student, this might mean uploading course notes, a specification and several textbook chapters.

For a business, it could mean uploading policies, meeting papers or product documents.

A good choice for: revision, source-based research, document collections and projects where the AI should remain focused on supplied material.

GitHub Copilot: Writing and Maintaining Code

GitHub Copilot is designed specifically for software development.

Its features include code completion, suggestions, code review and agent-style tools that can examine several files, propose changes, run tests and validate results.

A general AI can explain programming and write code, but a dedicated coding assistant may fit more naturally into the development environment.

A good choice for: programmers working regularly with repositories, development environments, testing and code review.

Canva AI: Rapid Social Media and Business Design

Canva AI combines design, writing, image and video tools within the Canva environment.

Its Magic Media tools can generate images, graphics and videos from descriptions, while Magic Design can help turn supplied material into layouts and short videos.

For a small business already creating posters, social graphics, presentations and promotional material in Canva, this can remove several unnecessary stages.

A good choice for: social graphics, posters, presentations, branded content and rapid design work.

Adobe Firefly: Creative Production and Adobe Workflows

Adobe Firefly generates and edits images, video, audio, vectors and designs. It also integrates with the wider Adobe Creative Cloud environment.

This is particularly relevant when AI-generated material needs to move into applications such as Photoshop, Premiere Pro or other professional creative tools.

A good choice for: photographers, designers, editors and video producers already using Adobe software.

Runway: AI-Assisted Video Generation

Runway concentrates heavily on generative video.

It can generate, edit and extend video using text, images and existing footage.

This might be used for:

• concept sequences;

• illustrative B-roll;

• visual experimentation;

• storyboarding;

• background material;

• or creating shots that would otherwise be difficult to film.

A good choice for: dedicated AI video generation and experimentation.

ElevenLabs: Voice Generation and Narration

ElevenLabs specialises in synthetic speech, voice design, voice cloning, transcription and voice-based agents.

Its text-to-speech tools are aimed at uses such as video narration, games, podcasts, audiobooks and accessibility.

Naturally, voice cloning must only be used with proper permission. The fact that technology can imitate a voice does not mean that it is acceptable to imitate anyone without their knowledge.

A good choice for: narration, accessibility, multilingual audio and approved synthetic voices.

Suno: Generating Musical Ideas and Complete Songs

Suno is designed to turn a written idea, recorded sound, rhythm or melody into a more complete musical production.

It can generate lyrics, beats, vocals and full song arrangements.

For a musician, it can provide a useful starting point, but the most interesting results may come from taking those ideas into a digital audio workstation and developing them further.

A good choice for: musical experimentation, song concepts, backing ideas and rapid demonstrations.

You Do Not Have to Accept the AI’s Default Behaviour

One of the most powerful developments is the ability to configure a general AI for a particular job.

Instead of repeatedly explaining your company, preferred tone and required output, you can create a dedicated Project or customised GPT.

A custom GPT can combine instructions, uploaded knowledge, selected capabilities, connected apps or defined API actions.

This turns a general-purpose AI into something much closer to a task-driven assistant.

Example: Creating a Philip M Russell Ltd Content Assistant

Suppose I want an AI whose job is to create the daily Philip M Russell Ltd blog and supporting social content.

Step 1: Create the Workspace

I could create a ChatGPT Project called:

Philip M Russell Ltd Daily Blog and Social Media

Alternatively, I could create a custom GPT called:

PMR Content Assistant

A Project is useful when I want to keep an evolving collection of chats and material together.

A custom GPT is useful when I want a clearly defined assistant that performs the same role whenever it is opened.

Step 2: Add Relevant Knowledge

I might upload:

• a description of Philip M Russell Ltd;

• details of the tuition services;

• examples of previous blogs;

• the preferred UK English writing style;

• company biographies;

• lists of science equipment;

• sailing projects;

• photography and video equipment;

• preferred hashtags;

• and examples of successful social posts.

The assistant would then have a far better understanding of the company than an AI beginning with a blank conversation.

Step 3: Give It Precise Instructions

The following could be placed in the Project instructions or custom GPT configuration:

Role
You are the content assistant for Philip M Russell Ltd, a UK education, science, technology and media company.

Primary task
Turn the owner’s rough notes into a detailed, engaging company blog.

For every topic, produce:

1. A strong title.

2. An engaging introduction.

3. A detailed structured blog using clear section headings.

4. Practical examples.

5. Relevant personal reflections written in the first person.

6. A compelling conclusion.

7. A short curiosity-driven X post.

8. A thoughtful LinkedIn post that builds professional authority.

9. Strong but relevant hashtags.

10. Three detailed Canva image prompts.

Writing rules

• Use UK English spelling.

• Keep the tone knowledgeable, reflective and accessible.

• Do not invent events, qualifications, results or customer claims.

• Clearly distinguish fact from personal opinion.

• Avoid exaggerated marketing language.

• Explain technical ideas in plain English.

• Where current factual information is required, research and cite reliable sources.

Quality check before finishing
Confirm that the article has a clear central argument, practical value, a personal voice and a conclusion that adds something new rather than merely repeating the introduction.

That instruction set is much more reliable than simply saying:

“Write me a blog about AI.”

Step 4: Use a Consistent Input Form

Each day, I could provide:

Topic: Making a pennant for Champagne
What happened: We began planning a traditional pennant for the Thames A-Rater.
Important details: Shape, colours, logo, fabric, stitching, visibility and how it will appear in photographs.
Personal angle: A pennant is a small item, but it gives the boat identity and character.
Audience: Sailing enthusiasts, makers and small-business readers.

The AI now has a clear task, reliable background information and an agreed output format.

This is the real value of a configured AI.

It does not necessarily make the AI more intelligent. It makes the process more disciplined and repeatable.

What Is a Plugin?

A plugin is easiest to understand by separating three things.

The AI Is the Brain

The AI interprets the request, reasons about the information and decides what needs to happen.

The Connected App Provides Eyes and Ears

A connected app might allow the AI to retrieve information from:

• email;

• cloud storage;

• a calendar;

• a customer database;

• a spreadsheet;

• or another approved service.

An Action Provides Hands

An action may allow the AI to:

• create a draft;

• update a record;

• add a calendar event;

• create a task;

• write information into another system;

• or call a company’s own API.

In current ChatGPT terminology, plugins provide a way to discover and enable workflow capabilities. A plugin may contain skills, app connections and templates. The underlying apps connect ChatGPT to external information and actions.

Some connected apps can search information, synchronise content, support research or carry out approved write actions. Availability depends on the plan, application, permissions and workspace settings.

How a Plugin-Based Process Works

A connected workflow usually follows a sequence.

1. The User Connects a Service

The user selects an approved plugin or app and signs into the relevant service.

This should be treated as granting access, not merely installing a decorative extra.

2. Permissions Are Defined

The connection may be allowed to:

• read information;

• search information;

• create new items;

• modify existing items;

• or perform only a limited set of actions.

Good practice is to grant only the access required for the job.

3. The User Gives the AI a Defined Task

For example:

“Find my notes about this week’s science demonstrations, create a blog, prepare two social posts and place the finished email newsletter in my drafts.”

4. The AI Retrieves the Necessary Information

The connected app locates the approved files, messages or records.

5. The AI Processes the Material

The AI might:

• summarise;

• classify;

• compare;

• calculate;

• draft;

• or transform the information.

6. The System Requests Approval Where Necessary

Actions with a meaningful external effect should be checked before they are completed.

Creating an email draft is not the same as sending it.

Suggesting a spreadsheet category is not the same as submitting accounts.

Preparing a calendar event is not the same as inviting fifty people to it.

7. The Action Is Completed

Once approved, the connected system creates or updates the relevant item.

8. A Human Checks the Result

The process should end with verification, particularly where the action affects customers, students, money or public communications.

Practical Plugin Workflow Examples

A Content Production Workflow

A connected content assistant could:

1. Read upcoming events from a calendar.

2. Find associated notes in cloud storage.

3. identify the photographs available for the topic.

4. Draft the blog.

5. Create platform-specific social posts.

6. Produce image instructions.

7. Create an email newsletter draft.

8. Leave everything ready for human review.

The final publication decision remains with the business owner.

A Bookkeeping Workflow

A bookkeeping process could:

1. Retrieve a bank statement.

2. Transfer the transactions into a spreadsheet.

3. Apply known categories to familiar suppliers.

4. Flag uncertain items.

5. identify possible duplicates.

6. Produce a list of missing receipts.

7. Create reminders for unresolved transactions.

The AI should not pretend to know what an ambiguous transaction represents. A good system highlights uncertainty rather than hiding it.

A Tuition Workflow

A tuition assistant could:

1. Read the lesson topic from the calendar.

2. Retrieve the relevant course specification.

3. Find the student’s previous focus sheet.

4. Create a personalised worksheet.

5. Produce easier and harder versions.

6. Draft a parent progress summary.

7. Save the material for review before the lesson.

That is much more useful than producing the same generic worksheet for every student.

A Sailing Information Workflow

A connected sailing assistant could:

1. retrieve wind and weather information;

2. collect river level and flow data;

3. check for relevant warnings;

4. produce a club-focused summary;

5. generate a consistent weather graphic;

6. and prepare the information for publication.

Where a company has its own data service, a custom GPT action can be configured to use an external API. This requires the API’s authentication details and a schema defining the available endpoints and operations.

Plugins Do Not Remove Responsibility

Connecting more systems does not automatically make a process better.

It may simply allow a mistake to travel further and faster.

A poorly designed automated workflow might:

• use the wrong source document;

• send an unfinished message;

• expose private information;

• overwrite a correct record;

• misunderstand a customer request;

• or repeat an error across hundreds of entries.

OpenAI’s own guidance warns that connected agents may encounter prompt-injection attacks or gain access to sensitive information. It recommends enabling only the apps required for a task, avoiding vague instructions and reviewing permissions regularly.

A sensible AI process therefore needs:

• limited permissions;

• clear instructions;

• reliable source data;

• approval points;

• exception handling;

• and human verification.

The Best Solution May Be an AI Team

Sometimes the most effective solution is not one AI but a sequence of specialist tools.

A content workflow might look like this:

1. Use a research-focused AI to locate current sources.

2. Use ChatGPT or Claude to organise the argument.

3. Use a configured assistant to apply the company’s style.

4. Use Canva or Firefly to produce the visual material.

5. Use ElevenLabs for an approved narration.

6. Use a human editor to check the final result.

7. Use a connected app to prepare the content for publication.

Each AI performs the part of the job for which it is most suitable.

The human remains responsible for the complete result.

Do Not Automate a Bad Process

Before adding AI, it is worth asking whether the existing process makes sense.

If a task is disorganised, poorly defined or based on inaccurate information, automation will not repair it automatically.

It may simply perform the bad process more quickly.

The best order is:

1. Understand the task.

2. Remove unnecessary stages.

3. Standardise the information.

4. Decide where human judgement is required.

5. Select the appropriate AI.

6. Add connections or automation carefully.

7. Measure whether the result has genuinely improved.

Conclusion: Build an AI Toolbox, Not an AI Dependence

The question is not:

“Which AI is the best?”

The better question is:

“Which AI is best suited to this particular stage of this particular job?”

A general assistant may help us think and write.

A research AI may help us find current sources.

A specialist image, video, voice or music system may produce the creative asset.

A configured Project or custom GPT may make a repeated task more consistent.

A plugin may connect the AI to the information and applications needed to complete a process.

The important skill is no longer merely knowing how to ask an AI a clever question.

It is understanding how to design the whole workflow:

• choosing the right tool;

• supplying the right information;

• defining the task;

• controlling permissions;

• checking uncertainty;

• and keeping human judgement at the centre.

AI should not become an excuse to stop thinking.

Used properly, it should allow us to spend more time thinking about the parts of the job that genuinely matter.

So How do I produce blogs like this?

I generate the ideas.  AI's simply go off and do their own thing - not related to what I do.

Voice to document - I dictate much of the story. I want this blog to be about me not an AI. Auto spell correct helps here though.

Then I can get an AI to clean up the text - suggest better orders for paragraphs and or ideas.

Then the magic bit for me - the AI can put in headings in the correct places - this really is the AI in action, then either sort through my vast library of photographs - you really don't want to know how many - It's in the many terabyte order - and usual manually adding text or generate my own.

Practice at writing suitable prompts for an Ai graphic engine and many attempts can produce an image I don't have or it can cobble several i do have together.