We just added this. It is at the top of the maintenance section. While we were at it, we also added MCP support for maintenance log management. If you use an AI tool, point it to http://saillogger.com/mcp, and it should be able to create personalized reports for you.
administrators
Private
Posts
-
Print service log? -
Print service log?You mean the maintenance log? If so not yet, but it is a good idea, we will add it to the list of items in the backlog.
Out of curiosity, what exactly is your use-case?
-
đ¤ Boat Monitoring with AI and SailloggerAs a Saillogger user, you can now put your boatâs data to work with your AI assistant in more ways. Weâve enhanced our existing MCP server and added webhook support. These enhancements let compatible assistants explore your boatâs data, help configure monitoring, and respond to alarms, automatically if you want.
Weâre already using these capabilities to monitor our own boats. In this post, weâll walk through how you can do it too, from connecting an assistant to Saillogger to having it keep watch and notify you when something needs attention.
AI has many uses, but outside of work, the primary way we use it is through AI assistants: Instinct, Grok Bot, Muse, OpenAIâs dots, the newly announced Claude Duet, and others. We use these assistants to help organize our daily lives, from booking concert tickets to helping with travel arrangements.
The most natural next step for us was to give those assistants the ability to monitor our boats. We now have a boat specialist agent that keeps an eye on our boats 24/7, even correlating boat data with events from our cameras, weather reports sent by Chris Parker (our weather router for the Caribbean), news about local events, hurricane reports for the Caribbean, and so on.
How It Works
How Saillogger and AI keep watch over your boat
For the AI integrations, the foundation is the data Saillogger already collects: what your boat reports via NMEA 2000, along with the historical records it keeps automatically.
Our new AI integrations build on that foundation, putting everything Saillogger can monitor and log for you at your AI assistantsâ disposal with a single click. Whatâs more, we let AI assistants selectively configure monitoring settings in response to your prompts. They can help you figure out what additional things you can monitor on your boat and set up that monitoring for you. This is usually one of the trickier parts of setting up a boat monitoring and alarm system, but AI can be very helpful here.
The mechanism that connects AI assistants to Saillogger is called MCP (Model Context Protocol). It essentially allows an AI assistant to use the tools offered by a service provider. In this case, Saillogger offers a very rich set of tools that provide access to your entire trip history, statistics, and places you have anchored or docked, as well as your near real-time monitoring data and its history. All you need to do is tell your assistant to connect to Saillogger.
Connecting Your AI Assistant
Letâs see how it works in practice with Grok Bot. Just tell it to connect to Sailloggerâs MCP server at https://saillogger.com/mcp.
Connecting an AI assistant to Saillogger
This brings up an authorization window where you can approve the connection:
Choosing what your AI assistant can access and change
You can choose read-only access or allow the AI assistant to change your sensor settings and create alarms too. Weâll cover alarms further below. The choice depends on how comfortable you are letting AI tweak your configuration, but in this example, weâll allow it.
Exploring Your Boatâs Data
Once connected, Grok Bot will be able to retrieve near real-time data from your boat. Saillogger reports at one-minute intervals while your boat is online.
This gives a quick overview of the boatâs status, summarizing everything it can retrieve. The screenshot also happens to reveal that weâre taking a break from the boats and spending some time on land
Grok Bot can now also access historical data and create visualizations or perform other analyses for you. Here is a simple example that gives you a sense of what is possible:
Analyses and visualizations from Grok Bot, on demand
You can also let your AI assistant help you figure out which sensors you have and enable tracking for them in Saillogger.
Here is an actual example. We werenât remotely monitoring solar output or the battery status of our RuuviTag Bluetooth sensors, which are placed in different parts of the boat. Grok Bot discovered these data sources and suggested monitoring them, as weâd already lost contact with one of the sensors in the port hull, likely because of a dead battery.
Letting Grok Bot enable monitoring for additional sensors
Just to add a bit of fun, letâs ask Grok Bot to summarize our last cruising season:
Grok Botâs summary of our cruising season
These are all excellent ways to use an AI assistant, especially when you use it more broadly and it can draw on your boating history, memories, journal entries, real-time data, and context while helping with your daily routines.
Having Your Assistant Keep Watch
But what matters even more to us boaters is having someone keep an eye on our boats while we enjoy a moment without thinking about them. So letâs ask Grok Bot to keep an eye on our boat:
Grok Bot on watch
With a simple instruction like this, it will start checking on our boat regularly. Whatâs attractive about AI is that it already demonstrates the ability to analyze information in context and even apply judgment. This kind of monitoring can go beyond a basic rule-based alarm system that triggers when certain thresholds are crossed.
You can also provide more details about your boat, the equipment aboard, manuals, and so on, which can make its analyses more useful. To us, this feels close to having someone watch our boat 24/7, applying context and boat-specific know-how to what may be happening.
Here is a great example: Grok Bot noticed that the saloon sensorâs battery was running low and that something was drawing a fair bit of power at night. It spotted these issues without specific instructions or explicit alarm rules. The overnight draw came from our Starlink, backup marina Wi-Fi connection, router, and Raspberry Pi, which together draw close to 100 W.
Grok Bot spotting a low sensor battery and overnight power draw
So far Iâve been demonstrating this with Grok Bot, starting with the initial setup, but you can also use other compatible AI assistants. Here is an example with Muse:
Muse bringing together weather reports, forecasts, and updates on friends
In this screenshot, you can see how it combines multiple sources of information: an email from Chris Parker (our weather router for the Caribbean), forecasts from Windy, and updates on our friends. Our friends on Mimi are on their way to the Bahamas, where we first met them. It was very nice to be automatically informed when they left the dock in the Chesapeake so we could connect with them!
When an Hourly Check Isnât Enough
Taking a step back, what is already available here is amazing. However, one obvious gap in this approach is the frequency of the checks. In the example above, we asked Grok Bot to check things every hour. What if something goes wrong a few minutes after the last check?
First off, we donât think itâs a good idea to rely solely on AI, or any form of remote monitoring for that matter, to detect a problem that could sink a boat at a momentâs notice. Those situations need dedicated protection aboard, such as an additional high-capacity bilge pump triggered by high water or an automatic fire suppression system, with notifications sent in parallel. That deserves some thought of its own, but regardless, a system that checks every hour or so will always have a gap between checks.
Thatâs why we also developed a mechanism that lets AI assistants define alarms for your boat and wakes them up when those alarms are triggered.
Here is how it works: you can already define fixed alarm rules in Saillogger. Now your AI assistant can too, if you let it. These rules trigger when Saillogger detects a threshold being crossed. It could be wind rising above a certain speed, temperature dropping below a set value, or a bilge pump coming on. The AI assistant then gets notified alongside you, or instead of you if you prefer.
These rules normally notify you through email or a phone push notification in Saillogger. Now those alerts can also be delivered directly to your AI assistant through a webhook, allowing it to analyze the situation and take action within the permissions youâve given it. Depending on the assistantâs capabilities, that might mean calling the marina or yard, or capturing video from compatible monitoring cameras. Your imagination and the capabilities of these AI agents set the limits, and those capabilities are growing very rapidly.
Alerts Set by Your AI Assistant
One key requirement for this approach is an AI assistant that can accept incoming webhooks. Not all assistants support this yet. At the time of writing, Muse doesnât, though Iâve submitted several feature requests. Grok Bot does. Letâs see how it works in practice. Go ahead and tell Grok Bot to add a webhook for Saillogger:
Setting up a webhook in Grok Bot
It will provide a URL and a key in the panel on the right. Copy them into Sailloggerâs Notifications settings, under Webhook Notifications:
Configuring the webhook in Saillogger
Saving sends a test notification, which you can immediately see in Grok Bot:
Grok Bot receiving a test notification
Now you can choose which notifications to send directly to Grok Bot. You can turn individual notification categories on or off, or disable them all. For boat monitoring, keep âMonitoring Alertsâ enabled so Grok Bot receives your alarm notifications.
Choosing which notifications to send to Grok Bot
Once webhooks are enabled, tell Grok Bot to set up alarms. You can be creative about how you want it to configure and respond to them. The good thing is that these settings donât have to stay fixed. Grok Bot can adjust them based on where you are, your travel plans, the season, conditions, and so on. Here is an example:
Grok Bot configuring alarms for our boatâs current state
To show this in action, we temporarily set the wind alarm threshold to 5 knots. And unsurprisingly, in less than 30 seconds, Grok Bot responded:
Grok Bot responding to a wind alarm in under 30 seconds
The layer of judgment that AI assistants can bring here is actually pretty impressive. It even guessed this was a test, without being told.
If something really is wrong, they can pull more real-time data, look at historical sensor readings, connect the dots, and put things in context. They can then take additional action, either automatically based on your prior instructions or by helping you diagnose and mitigate the issue. They can also visualize the data for you on demand. For example, my Muse is instructed to include trend charts whenever it flags a potential anomaly, so I can quickly assess whether something looks amiss.
You can also connect compatible assistants to messaging apps like WhatsApp, so you can literally text with your boat wherever you are. Here is how I communicate with Muse over WhatsApp:
Communicating with Muse over WhatsApp
We also have someone looking after our boat, and we communicate primarily over WhatsApp. We havenât needed to do this yet, but we could ask our AI assistant to contact him directly when something needs checking. For example, it could ask him to check the dehumidifier or air conditioning if humidity is rising, or the shore power connection if the boat loses shore power.
For friends or fellow boaters who donât have Saillogger aboard, our companion service, AIS Fleet, also offers an AI integration. AIS Fleet is free to use and has its own MCP server at http://aisfleet.com/mcp, available with its $2.99/month subscription tier.
Feel free to contact us with ideas, suggestions, or examples of how youâre using it on your boats. We look forward to hearing from you!
Adapted from Boat Monitoring with AI, originally published on S/V Renaissance. Feel free to follow us there too
-
đşď¸ No hardware for Saillogger yet? Start with AIS Fleet, a live map of boats at seaYou can start following boats today with AIS Fleet, our companion site, even if your boat does not have the hardware Saillogger needs yet.
AIS Fleet is a live map of boats at sea, built on AIS. All it takes is a free account, and there is nothing to install aboard. We are also working on an easier way to connect a boat to Saillogger.
AIS is a radio system: ships and many recreational boats use it to broadcast their name, position, course and speed. Receivers on shore and aboard boats receive these reports, and AIS Fleet draws them on one live map.
Here is what you can do with AIS Fleet:
-
Follow boats, and know when they leave and arrive
Search by name, MMSI, call sign or IMO number, then follow a boat to be notified when she leaves and when she arrives. -
See the boats around you, directly from an AIS receiver
If there is an AIS receiver on your boat's Wi-Fi network, the AIS Fleet app for iPhone connects to it. While the app is on screen, it draws the boats the receiver hears within seconds. The app also becomes your own station, which no other member sees: what it hears joins the AIS Fleet network, and you can pause that sharing. From its first full month, a station that meets the monthly requirements for boats heard, reception range and uptime earns you the Plus or Pro plan for the following month. The app counts toward uptime only while it is open on screen; a receiver you add under My Stations on aisfleet.com reports on its own, without the app. Share your AIS receiver -
Group boats into lists and fleets
Keep the boats that interest you on a list, and share it if you like. Claiming your boat on AIS Fleet is free and needs one document. After that, a club or rally can add the boat to its fleet, with a shared map and chat. With the Plus or Pro plan, you can also create a fleet of your own. -
Write to other boaters
Write to the owners of the boats you follow, and of the boats in your fleets, if those boats are claimed on AIS Fleet or shared on Saillogger. -
Follow Saillogger boats in more detail
When their owners choose to share, boats that keep their log with Saillogger also show their journal and the voyage they are on, as Saillogger records it. If their owners allow it, these boats also keep moving on the map from their own position reports whenever they have internet aboard, even where no AIS receiver hears them. -
Photograph boats, and earn the Plus or Pro plan
If you enjoy watching or photographing boats, you can add your photos to their galleries; each one is reviewed before it appears. In one calendar month, use AIS Fleet to photograph three boats you have not photographed with it before. Once the photos are published, you have the Plus plan for the following month. Ten boats photographed this way earn you the Pro plan.
Watching the map, following up to five boats and being in a fleet are all free with an AIS Fleet account, and the free plan does not expire. AIS Fleet has its own sign-in: enter your e-mail address and AIS Fleet sends you a code, so there is no password. On iPhone, use the AIS Fleet app; on Android or a computer, use aisfleet.com in the browser.
If your boat broadcasts AIS and a receiver has heard her, family and friends ashore can already follow your boat on AIS Fleet. When your boat logs with Saillogger, they can also read your journal and see your voyage, as far as you choose to share.
Have questions or ideas? Feel free to write to us.
Fair winds and following seas!
The Saillogger Team -
-
Timelapse map disappearsThanks, this was helpful to diagnose the root-cause. We have fixed the issue, please try again.
-
Timelapse map disappearsSorry @jaredko , your timelapse renders perfectly fine when we try. The only thing I can suspect is rendering engine, is it happening on all devices? It is really strange as we cannot observe what you are observing on your timelapse.
-
Fuel and Water volumeHi, thank you for the note.
On tank volume: this was a bug on our side, not in your setup. The Conditions table on trip pages rounded tank readings to the nearest 100 L, and humidity and battery charge to the nearest 10%, so 0.083 mÂł showed as 100 L. The figure on the live dashboard was correct. A fix is deployed, and nothing needs changing on your side.
Motor time is a bit different. The two engines are not added together. Motoring is the time at least one engine is running. As example, if one engine ran for the first leg, the other around midday, and both for the arrival. So the boat can come under engine for close to 4 hours, while the engines logged 1.8 h and 2.4 h each. Each engineâs own hours are under Engine hours on the trip page.
-
Problem displaying custom SignalK data in instruments pane.Thanks, one piece of extra information, when you took this screenshot what was the time exactly? Here is what we suspect is happening. For Saillogger to display data, it needs to be "fresh". Fresh means max 90 seconds of age. I suspect these values are only published by Node Red when the bilge pump runs and probably were older than 90 seconds. So Saillogger will not pick them up, thinking they are stale. A quick test is to check Saillogger within a minute of these fields refreshing or having NodeRed publishing them regularly. Could you try that?
-
Problem displaying custom SignalK data in instruments pane.Hi, how do they show up in Signal K data browser? Can you send those screenshots as well, timestamps there are important so please include them too.
-
Timelapse map disappearsHi @jaredko , we can not reproduce it. Is it happening for all timelapses? Is is it with the new or old UI or both? I am wondering if it has something to do with graphics acceleration on the computer, but multiple laptops eliminate that possibility.
Can you send a link that is broken for you?