How SwarmFarm is scaling its robot fleet without hiring more support engineers
SwarmFarm has close to 300 autonomous robots working on farms across Australia. Alloy lets its support capacity grow with the fleet, not with the engineering team.
Last year at this time, I was spending a day or more investigating issues and support tickets. Now it's usually less than an hour.Mitch Galea, Senior Autonomy Engineer at SwarmFarm
Impact at a glance
- A day or more → under an hour: Mitch's own estimate of his time on support investigations, a year apart
- About a week: from connecting Alloy to SwarmFarm's telemetry to the first results
- 25 people: using Alloy across engineering, support and customer success
- No new support engineers hired yet: even as the fleet keeps growing
SwarmFarm's robots are working farms across Australia
SwarmFarm builds autonomous vehicles for agriculture. Close to 300 of its robots are in commercial work on farms right across Australia. Every farm brings its own conditions, crops and jobs, so the fleet sees an enormous range of situations. In late 2025, SwarmFarm raised a A$30 million Series B to scale its fleet and expand into North America.
Summer is peak season. The number of robots out working climbs from tens to hundreds, and requests from farmers climb with it. Over the past year, SwarmFarm's team handled close to 3,000 support requests, with more than 300 a month through the summer peak.
That growth is the goal, and it brings a challenge every robotics company meets as it scales deployments. More robots in the field means more questions from the field. The hardest ones land with the engineers who know the robots best, and the roadmap starts competing with the ticket queue.
More robots in the field, more questions for engineering
SwarmFarm's support process was thorough. When a farmer needed help:
- The farmer raised a request through the SwarmFarm app.
- Support built a full picture from the robot's telemetry, because farmers are busy running their farms and reports vary in detail.
- Support gathered logs, ROS bags and network data, and often called the farmer back to understand exactly what happened.
- Harder issues went to SwarmFarm's autonomy engineers for deeper analysis.
- The ticket closed once the team had a confirmed answer.
That's careful work, and it takes time. Some investigations took a few hours, others up to a week, and the hardest ones competed with product work for engineers' attention. Field robots also keep limited logs on board, so in peak season, speed matters: older logs roll over to make room for new ones.
Rather than wait for summer to arrive, the team used the quieter months to get ahead of it.
We used this winter to prepare, putting better systems in place to stay on top of issues when far more robots are running.Mitch Galea, Senior Autonomy Engineer at SwarmFarm
Why SwarmFarm bought instead of built
Mitch found Alloy himself. He uploaded a single ROS bag file to try it, liked the plots that came back, and got in touch with the Alloy team shortly after.
SwarmFarm had the skills to build its own tools, and considered it. "But really it's a question of manpower," Tom Brodie, SwarmFarm's Head of Autonomy, said. "Our people already have busy plates."
Mitch saw the same trade-off. "I could set something up and get it working well enough for me," he said. "But to support a whole team, and having to then answer all their questions, that wasn't going to be maintainable long term."
Tom put it simply: "We build robots. We don't want to build diagnostic websites. So why reinvent the wheel?"
Alloy connected first to ClickHouse, where SwarmFarm keeps its robot telemetry. Once the whole team could query that data through Alloy, the value was immediate. "I thought it would take a lot longer," Tom said. "It took about a week." Jira, Confluence, Slack and SwarmFarm's CAN API followed, so Alloy could read tickets, triage guides and decoded robot data in one place.
Every new ticket arrives with a first investigation
When a ticket lands in SwarmFarm's Jira, Alloy builds a triage package before a person picks it up:
- It summarizes the issue and flags any missing context.
- It suggests a priority and a route, based on SwarmFarm's own triage guide.
- It finds related tickets, and searches the robot's telemetry and logs.
- Where logs will help, it requests them from the robot.
- It posts its findings as an internal comment, for a person to review and act on.
Alloy works from SwarmFarm's own triage guides, past tickets and documentation, so it follows the way SwarmFarm's experts already work.
On one ticket about a communication fault between a robot's main and attachment controllers, Alloy found the exact time window and requested the right CAN logs from the robot on its first review.
For the people on the phones, that takes care of the most repetitive part of the job.
I was on the phones last week, and it really helped. It took half my job away: all the silly stuff you have to do.Luke Reid, Robotics Support Specialist at SwarmFarm
SwarmFarm has also been building out its support structure, adding a support engineer role between customer success and the full engineering team. Alloy works at every tier, and goes into more detail as an issue moves up. In one winter week, it ran about 95 triage investigations on tickets and answered 235 questions from the team. Engineers used it most, because that's where the hardest problems land.
Answers that come with evidence
Trust in an AI agent is built in drips and lost in buckets. Tom said Alloy "doesn't just make claims. It backs them up." Its findings point back to the tickets, telemetry and logs behind them.
Alloy doesn't act alone. It posts internal comments for the team to review, and people stay in charge of what goes back to farmers.
SwarmFarm's team keeps it sharp. On one ticket, Alloy suspected a software version regression. A SwarmFarm engineer pointed out that the beta had already gone into production. Alloy withdrew the claim, reviewed related tickets for the same robot, and proposed a better line of investigation into power and brownouts.
It's a lot better than the other AI summarizing agents I've seen. It reinforces my team's knowledge and their confidence in their own calls.Jack Humphrey, Customer Success Team Lead at SwarmFarm
Support solves more before it reaches engineering
Farmers are busy running their farms. When they report an issue, they might say it happened "maybe an hour ago." Alloy finds the exact moment in the robot's data, so support pulls logs for a narrow window instead of a large one. "That really short-circuits the whole process," Mitch said.
When an issue does go to engineering, the evidence is already gathered. Farmers hear back sooner, too. Support can often tell them early that the team has seen something similar and knows where to look.
Every engineer gets the best engineer's context
As SwarmFarm's senior engineers work with Alloy, their know-how stays with it: which signals to check, and where to look when a problem comes back. That puts deep investigation within reach of the whole team.
When a couple of robots had GPS issues, a recent addition to the team used Alloy to compare their settings. Alloy spotted a configuration difference between them, and the team traced it to what appears to be the root cause. Another new software engineer picked Alloy up in their first week, worked through an issue with a release candidate, and wrote it up as a report for a field technician.
"Basically something that we'd have an engineer do a query for, but some bloke could just work that out," Tom said. "It's made accessible what used to sit behind a technical barrier."
Everyone feels like they're upskilling. People are finding insights on topics even I don't know the answer to.Tom Brodie, Head of Autonomy at SwarmFarm
More robots, without more support engineers
"Tickets are stopping before they reach us," Tom said. "People are solving their own problems."
Mitch gets far fewer escalations. "I definitely don't miss writing all the NumPy and Matplotlib Python scripts," he said. That time now goes into big projects and the core problems the team wants to solve.
SwarmFarm's support engineering team is lean, and it hasn't needed to hire anyone yet. "Alloy's given us a lot more breathing room," Tom said. Mitch put the outcome plainly: "We can keep scaling up robots without worrying about growing the team."
Simply put, SwarmFarm's support capacity now grows with its fleet. After the pilot, SwarmFarm moved into an annual partnership with Alloy, and every investigation adds to what Alloy knows about its robots. Mitch now wants to add more telemetry to the robots. "Imagine what we can do now that Alloy has access to this data," he said.
We want to work on robotics, not build integrations to LLMs. Alloy frees up all that time so we can focus on what we want to do.Mitch Galea, Senior Autonomy Engineer at SwarmFarm
Questions teams ask before choosing Alloy
Answered on camera by Tom Brodie, Head of Autonomy, and Mitch Galea, Senior Autonomy Engineer at SwarmFarm. Open a question to watch their answer, or read it.
Can it handle our robot data?0:16
Yes. Alloy connects to the robot data you already have, learns it quickly and turns it into answers you can act on.
Tom: I was definitely concerned initially at its ability to crunch data, or even where it'd get it from. When it did have it, how quickly you could get a viable solution for it. I think over a bit of training and working through the motions, we've been able to get to a pretty good point here.
Why not build it ourselves?0:23
Faster to buy. A robotics data agent needs parsers for every log format, fleet-scale storage and querying, integrations with your tools and constant upkeep. Alloy ships all of it today, so your engineers spend their time on the roadmap that sets your robots apart, not on maintaining internal tools.
Tom: We've considered it, but really it's a question of manpower. We've got enough people with enough busy plates.
Mitch: I could set something up and get it working well enough for me, but to support a whole team and having to then answer all their questions, that wasn't gonna be maintainable long term.
Tom: That's not what we do. We build robots. We wanna go out there, we wanna build robots for farming applications. We don't wanna build diagnostic websites, so why reinvent the wheel?
How long until we see value?0:30
About a week. Customers typically see results within a week of connecting their first data source.
Mitch: Had a few meetings and set up the pilot. The process for the pilot was really seamless. The Alloy team did whatever we asked. Set up a bunch of integrations. ClickHouse was the first one, and that added immediate value the moment the whole team was able to query Alloy for ClickHouse telemetry data. We had huge initial value from that alone.
Tom: I was pretty surprised by how quickly the initial turnaround was to getting initial results. Like a week. I thought it was gonna be a lot longer than that.
Will it work with our stack?0:30
Yes. Alloy integrates with tools like ClickHouse, Jira, Slack and CAN data, so you don't build the plumbing yourself.
Mitch: I think Alloy has a lot of really good integrations. The second major integration was Jira. It's working really well now. Everyone really, really, really likes the initial triage and feedback from Alloy. Building stuff from scratch, like the Jira integration for instance, that would've been a whole lot of work, which we wouldn't have time for.
Tom: And Slack as well. We use Slack a lot. Got integrations with our CAN API, so now we can decode byte data. Going down through all those rabbit holes would've been at least just extra work for somebody.
Will Alloy's team actually support us?0:12
Yes. Every customer gets a dedicated forward-deployed engineer who sets up your integrations and answers requests directly in your Slack.
Mitch: We're able to raise issues promptly and get initial feedback. But even beyond that, the Alloy team were really responsive through Slack to any queries and requests made by our team.
Will it fit how our support team works?0:25
Yes. Alloy works at every tier of your support flow and gives each one the level of detail it needs.
Tom: We've restructured our whole support flow process. We'll get to a support engineer role before it gets to the full-blown engineering team. At each one of those tiers, the level of detail that it goes to as a particular issue gets escalated varies, and I think that's a really cool way to not drown someone with information that they don't need to know. But if you do need to know it, you can get it.
Can non-engineers really use it?0:39
Yes. Alloy is designed to be used by your entire team, and you talk to it in plain language, so it's very accessible.
Tom: It's a lot easier for non-engineers to tackle these problems before it even gets to us, even if they haven't got a solution. It's much easier to give feedback to the customers a lot quicker: "Righto, we think we have an idea of where we're looking. We've seen this before. Let's get back to you shortly." Whereas in the past it's a bit more like, "I don't know. In the dark. We'll get back to you when we do."
I reckon everyone feels like they're upskilling. People are having more insights on even topics I don't even know the answer to. If you can solve it yourself, fantastic. We had a field tech who's just sitting in a pub on a Friday who can just look it up. Basically something that we'd have an engineer do a query for, but some bloke could just work that out. It's really made accessible what was otherwise quite behind a technical barrier.
Will it find what our experts miss?0:18
Often. Alloy indexes every recording, from MCAP and ROS bags to CAN and custom binary logs, into queryable tables and searches your whole fleet's history in one pass, alongside your tickets and docs. An expert checks the few files they remember; Alloy checks all of them.
Tom: I think the first aha moment is where there's some things that I've been doing for years as part of debugging, or you just know the answer to. You have your process, you know your patterns, and you get to the bottom of it. It was just able to find it out in the first question. Sometimes you're like, "Oh, what am I doing with my life?" That's the purpose of it, I suppose.
Can it get to a real root cause?0:19
Yes. Alloy lines up config, logs and telemetry from every affected robot, diffs them against robots that are working, and links each finding back to the exact data behind it.
Tom: We've had a couple of robots that have had some GPS issues, and we've had someone who's a recent addition to our team use Alloy to make a correlation between the settings. And that was able to find a particular configuration that had changed that we weren't aware of between them. From there we're able to pull at that thread and determine that seems to be the root cause of our particular issue.
Will it actually save engineering time?0:25
Yes. Investigations that took engineers a day or more typically come down to under an hour.
Tom: Alloy's definitely helped with the escalation rates of our issues.
Mitch: Last year around this time, I was probably spending at least a day or more investigating issues and support tickets. But at the moment it's usually less than an hour here and there.
Tom: I absolutely reckon the number of tickets that are starting to hit me has dropped significantly from where this would've been the same time last year.
Mitch: We're not worried about keeping on scaling up robots without having to grow the team.
Will we still need to hire as we scale?0:40
Not yet. Customers typically keep scaling their fleet without growing the support team, because fewer issues reach engineering.
Mitch: I've definitely been receiving a lot less escalations coming my way, so I'm happy. I definitely don't miss writing all the NumPy and Matplotlib Python scripts.
Tom: There's been periods in the past where there's been a lot of sunken time in support work. The ticket flows are stopping before us. People are able to solve their own problems.
Mitch: It definitely frees up a lot of time for big project developments and tackling the actual core problems that we need to be solving.
Tom: We've got a smaller support engineering team. Alloy's given them the ability to keep their heads above water. We haven't necessarily needed to hire anyone yet. I think Alloy's given us a lot more breathing room to be able to give them the skills that they need with the time that they have at the moment.
Grow your fleet without hiring more support engineers
Book a demo to see how Alloy can grow your support capacity with your fleet, as it did for SwarmFarm.
book a demo