Finding the Next Gear in Planning: Interview With Canyon’s Paul Tips

For a direct-to-consumer bicycle company, getting demand right at the product-family level is only part of the challenge. A customer does not simply want a particular bike model. They want it in the right size, the right color, and within a delivery window they can trust.

That level of precision was difficult to achieve when Canyon’s planning processes relied on fragmented Excel files and static assumptions. Teams spent significant time exchanging spreadsheets, reconciling information, and making ad hoc decisions across demand and supply.

Canyon has since brought its planning data and processes together on the o9 platform. According to Paul Tips, Product Owner at Canyon, the transformation is helping the company plan at a much more detailed level and strengthening collaboration across the business.

“Instead of having information in fragmented Excel files and people having to look between different files, we have it now all in one platform,” he said. “The information exchange between different teams is much easier.”

Watch

Planning for the bike the customer actually wants

Before implementing o9, Canyon planned demand mainly at the bike level.

The company then applied static ratios to estimate how many bikes it would need in each size and color. That approach provided an overall view of demand, but it could not fully reflect how customer preferences varied across individual product combinations.

Canyon can now plan directly at the size-and-color level.

This gives teams a more accurate view of the stock available in the distribution center, the remaining production capacity, and the combinations most likely to be required by customers.

“We are much better able to balance out demand at a size-and-color level between what we have in the distribution center and how much we can still produce,” Tips explained.

The aim is to increase product availability while reducing excess inventory. Better alignment at this level could also support higher sell-through and fewer markdowns.

The company is still assessing the full financial impact, but Tips said the process improvements are already visible.

“We see much more collaboration between the different teams, a much better flow of information, a much more robust process, and the ability to meet demand at the lowest level of granularity,” he said.

Giving teams a shared view of demand and supply

Canyon’s previous planning process involved frequent exchanges of Excel files, long email chains, and decisions made outside a shared system. These manual handovers created opportunities for delays and errors. They could also make it harder for teams to determine which information was current.

The o9 platform gives demand and supply teams access to the same data. When one team changes the demand plan for a bike, the effect is immediately visible on the supply side. This has reduced information leakage and made the process less dependent on manual updates.

“Everybody is looking at the same information,” Tips said. “It is all consolidated in the platform. They can look at the same data without any delay.”

He believes this shared view is also improving trust between teams.

“There are a lot of things that can go wrong in a manual process, and a lot of these we eliminate,” he said. “It improves the level of trust between the teams, and more trust means better collaboration.”

Keeping implementation lean

Tips advises other organizations to avoid making the initial implementation more complicated than it needs to be. Long implementation cycles can create a gap between the solution users originally requested and the one they eventually receive. During that time, business requirements, market conditions, and user expectations may all change.

“What happens a lot, and what we saw also in Canyon, is that we overcomplicate the implementation,” he said. “It runs very long, and during that time, the demands of the users change.”

His recommendation is to launch a focused solution earlier, even if it initially covers only part of the business. This allows teams to begin working with the platform and provide feedback based on real experience.

Those requirements tend to be more useful than assumptions captured during the blueprinting phase.

“The faster you can get to this, even if it is with a subset of your business, the faster you can show the impact of the platform and start collecting real user requirements,” Tips said.

For Canyon, implementation was only the beginning. Much of the transformation work has taken place since go-live, as teams have become more familiar with the platform and moved away from legacy tools.

Building internal ownership through a Center of Excellence

Canyon initially worked with implementation partners to develop the platform. It has since created its own center of excellence to manage enhancements and make the solution increasingly fit for purpose.

Tips leads the work around the solution, collaborating with business leads and key users to prioritize changes. This internal capability gives Canyon more control over the direction and pace of the transformation. It also helps the company respond as user needs and business conditions evolve.

Tips sees this ownership as particularly important in an unpredictable environment.

“Take ownership as much as you can of the transformation journey yourself,” he said. “Setting up the center of excellence allows you to do configurations of the platform yourself and not rely a lot on external expertise.”

A center of excellence can also shorten the distance between user feedback and platform improvements. Canyon can identify an issue, evaluate it with the relevant business teams, and make changes without beginning a new external project each time.

Learning from reluctant users

Early adopters have an obvious role in transformation programs. They are often enthusiastic about the technology and willing to help test new processes. Tips believes organizations should also pay close attention to the people who are less comfortable with the change.

Their reluctance may highlight gaps that project leaders and key users have overlooked. In many cases, the concern is not about the platform itself. Users may feel that a necessary capability is missing, that the process has not been explained clearly, or that they are losing control over part of their work.

“It is important to find the more reluctant people and understand what is actually driving their reluctance,” Tips said.

Since January, Canyon has put more focus on users who have been slower to adopt the platform. These conversations are not always easy, but they are helping the company build a more robust process.

“The complexities that the people see who are more reluctant to this change are probably things that I, as a product owner, or the key users don’t think of because we are all very enthusiastic about this journey,” he said.

This broader approach helps prevent adoption from being judged only by the experience of the people most likely to embrace the platform.

Accepting the twists and turns of transformation

Tips describes Canyon’s transformation as a rollercoaster.

There have been successes, setbacks, and requirements that only became apparent after the platform went live. Expecting a completely smooth journey, he said, would be unrealistic.

“There are things that don’t work immediately as you expect them to,” he explained. “There are some things you experience only after go-live that you didn’t think of before.”

Even so, the organization is beginning to see teams become more comfortable with the new approach.

“Not everybody likes it in the beginning, but at the end everybody is happy about it,” Tips said.

The analogy also reflects the importance of maintaining momentum. Each stage of the journey provides information that can be used to improve the next stage.

Mapping the supply chain end to end

Tips recommends mapping the full process before beginning a planning transformation, even when the initial implementation focuses on only one module. For Canyon, that means looking from the end consumer through manufacturing and into the raw materials and components supplied by its partners.

An end-to-end map helps the business understand where the first implementation can create value and where it may make sense to expand later.

“Even if you are planning only to start with a certain module of o9 or a certain focus point, my recommendation would still be to do the mapping end to end,” Tips said.

Data quality deserves the same attention.

Organizations often focus on whether data is available and structured correctly. Tips argues that neither matters if the underlying information cannot be trusted.

“If the quality is not great, it doesn’t even matter how it is structured,” he said.

Poor lead-time data, inaccurate master data, or inconsistent supplier information can limit the value of the planning platform even when the configuration itself is strong.

Building the foundations before pursuing AI

Tips sees considerable potential in AI, but believes many organizations still have more immediate work to do. Data quality and automation maturity remain barriers. Companies may struggle to apply advanced AI capabilities when core processes still require manual intervention or when the information feeding the models is unreliable.

“I wouldn’t say AI is overrated because there is for sure a lot of power there,” he said. “I do think, though, that the maturity level of a lot of organizations is not there to really start using it in the ways that it is being sold.”

Improving the fundamentals remains the priority. Better data, stronger automation, and more connected processes can prepare the organization to use AI more effectively when the right applications emerge.

Neuro-Symbolic Agentic AI for Agile and Adaptive Enterprises

Enterprises don't struggle to gather data. They struggle to turn it into action while it still matters.

By the time the root cause is clear, the window to respond has often closed. This White Paper outlines how neuro-symbolic AI changes that equation, giving leaders a path from signal to grounded, governed decision in the same cycle the problem appears.

Download now

Improving collaboration with bicycle component suppliers

Supplier collaboration is one of the next areas Canyon plans to develop. The bicycle industry relies heavily on OEM suppliers for major components such as wheels and groupsets. Canyon wants greater visibility into supplier bottlenecks, changing lead times, and whether delivery commitments are being met.

Tips believes there is still significant room for improvement compared with more mature supplier networks in industries such as automotive. More accurate supplier information would support better material requirements planning and help Canyon make firmer commitments to its customers.

The eventual goal is to replace broad delivery estimates with much more precise promises.

“Once you order a bike, you want that delivery promise to be as accurate as possible,” Tips said.

Rather than giving a customer a two-week delivery window, Canyon wants to move towards a two-day window or even a confirmed delivery date. Achieving that will require better connections across the wider ecosystem, from the customer order through Canyon’s operations and into its supplier network.

“Connecting the ecosystem end to end is where I think the next step is for Canyon in this journey of transformation,” Tips said.

The progress Canyon has made so far has created a shared planning foundation and a more detailed view of customer demand. The next stage will extend that connection beyond the company, helping teams understand supplier constraints earlier and give cyclists a delivery date they can rely on.

A Guide to the o9 Enterprise Knowledge Graph

The o9 Enterprise Knowledge Graph (EKG) is a four-layer, closed-loop system designed to transform how enterprises plan, decide, and execute.

Download now