Day 6 of my daily creative challenge.
Today: Harmattan for aerial capture.
Most drone footage starts with a pilot you have to book, brief, and hope reads your mind. Here you just describe the shot: "slow orbit of the wedding tent at sunset, start wide, end close on the couple's entrance." The agent plans the flight, times it to golden hour, and a Scout flies it autonomously.
It's honest about its limits. It can't fly within 30m of guests, so it tells you upfront that the close-up will use a longer lens from farther out, where the shot looks the same. You book knowing exactly what you'll get. The same tool maps as well as it films. Describe a site, "the new estate off the Kachia road, for the planning application," and it returns an orthomosaic, an elevation model and a 3D model at survey accuracy.
The trust runs through the money too. If the weather stops the flight, you don't pay. Footage arrives colour-graded within the hour, yours outright, with a flight log proving every frame was shot inside the permissions.
This is a fictional product, designed end to end. Screens below.
I design interfaces for AI agents. If you're building one, my inbox is open.
#ProductDesign (https://www.linkedin.com/search/results/all/?keywords=%23productdesign&origin=HASH_TAG_FROM_FEED) #UX (https://www.linkedin.com/search/results/all/?keywords=%23ux&origin=HASH_TAG_FROM_FEED) #AIAgents (https://www.linkedin.com/search/results/all/?keywords=%23aiagents&origin=HASH_TAG_FROM_FEED) #Drones (https://www.linkedin.com/search/results/all/?keywords=%23drones&origin=HASH_TAG_FROM_FEED) #Cinematography (https://www.linkedin.com/search/results/all/?keywords=%23cinematography&origin=HASH_TAG_FROM_FEED)
1
33
Day 5 of my daily creative challenge.
Today: Harmattan for agriculture.
One of the ideas I have been incubating is how drones can be used to monitor farm produce and livestock. Not just to protect them from pest, predators and thieves, but also in detecting diseases and recommending solutions. Harmattan drones can be configured to detect changes in crops and animals, flag them, and provide suggestions on how to resolve them. In addition to this, the drones can be used to survey farmland and predict natural disasters like flooding and erosion using historical environmental data to help farmers observe safety precautions
0
27
Day 4 of my daily creative challenge.
Today: Harmattan for infrastructure inspection. Pipelines, transmission lines, refineries.
A drone flies the corridor and photographs every metre, thousands of frames per kilometre. No human can review all of that, and none should have to.
So a detection agent takes the first pass. It flags a coating loss on a weld joint, scores its confidence, and says why: "this patch grew 40% since the last pass and sits on a weld joint." A certified engineer then confirms or rejects each finding. Nothing reaches the client report unless a person has signed it.
The part I find most interesting as a designer is that the relationship runs both ways. Every confirm and reject is training data with the engineer's name on it. Over six months the agent's precision climbs and its false alarms fall, because it learns from the reviewer, not the other way round. Known test findings are slipped into the queue to keep both sides honest.
What comes out is a report the client can act on, and an asset history that tracks a fault on the weld itself, pass after pass, until a repair closes it.
This is a fictional product, designed end to end. Screens below.
One of the pros of this kind of product is to enable oil refineries, rigs and other infrastructure to detect defects, worn out equipment, leakages before they happen, thus saving them the cost for repairs and loss of valuable resources flowing through those pipes.
I design interfaces for AI agents. If you're building one, my inbox is open.
0
29
Day 3 of my daily creative challenge.
Yesterday I showed Harmattan's health dashboard on desktop. But the person who receives the delivery is rarely at a desk. They're a nurse in a courtyard, a pharmacist between wards.
So today: the responsive, mobile version of the same system.
You sign in by facility code and role, and every action is signed with your name. It works offline, so orders queue until the signal returns, which matters where the network doesn't. You can order by voice: "I need antivenom, snakebite came in 10 minutes ago." The agent knows your stock, assumes an emergency, and confirms the dose with you. Then you track the flight and follow a simple winch-down guide to receive the pod safely on the pad. The trust thread from the desktop carries over. When the system reroutes around a storm, it says so, and a human checks it.
This is a fictional product, designed end to end. Mobile screens below.
I design interfaces for AI agents. If you're building one, my inbox is open.
#ProductDesign (https://www.linkedin.com/search/results/all/?keywords=%23productdesign&origin=HASH_TAG_FROM_FEED) hashtag#UX (https://www.linkedin.com/search/results/all/?keywords=%23ux&origin=HASH_TAG_FROM_FEED) hashtag#MobileDesign (https://www.linkedin.com/search/results/all/?keywords=%23mobiledesign&origin=HASH_TAG_FROM_FEED) hashtag#HealthTech (https://www.linkedin.com/search/results/all/?keywords=%23healthtech&origin=HASH_TAG_FROM_FEED) hashtag#AIAgents (https://www.linkedin.com/search/results/all/?keywords=%23aiagents&origin=HASH_TAG_FROM_FEED)
2
38