When your technology project matters most, choose experience.
Since 2003, we have been building software solutions tailored to your business challenges and mission-critical systems. Our approach to AI is built on the same rigour, reliability and high quality standards.

Trusted by industry leaders for more than 20 years





















Years of Experience
Digital Experts
Cross-Industry Clients
International Projects

Solutions built around your business challenges
Since 2003, Spiria has been a trusted digital partner for the creation of complex software, the scalability of development teams and the support of critical systems.

Custom Software Development

Application Modernization

Artificial Intelligence
A high-stakes project is as much about the relationship as the technology.
Digital systems that work for your business
Our approach brings clarity, usability, and technical precision to every stage — from discovery to design to delivery.
Discovery Phase
We understand your problem before writing a single line of code. That prevents costly mid-project rework.
Design
We create interfaces your teams actually adopt, because a tool that goes unused is a wasted investment.
Development
We deliver durable, secure code that integrates with your systems and evolves with you.
Not sure where to start?
Our Work
For over 20 years, we've been supporting industry leaders in bringing their technological ambitions to life. Proud to be a part of our clients’ successes. Here’s a glimpse at a few of their stories.
What They Say About Us

Your Career at Spiria
Spirians are more than just strategists, designers, and developers, they are agile problem-solvers who thrive on challenges and, of course, technology.
At Spiria, you can expect a culture where collaboration, curiosity, and innovation drive meaningful work.
We’re a Proud Canadian Company

A Canadian team, close to your reality.
Founded in Canada in 2003, Spiria brings together bilingual experts in Montreal, Gatineau and Toronto. You work with people who understand your business context as much as your technology.
Spiria’s Blog
Sometimes I feel like I’m turning my back on my past.
In the early ’80s, I was typing in code listings from Compute! magazine. I wanted to understand everything, control everything. After a decade of personal projects, including a BBS, that passion became a career.
Despite the demands of work and my move into management, I never lost my taste for programming. Until recently, I was still setting myself coding goals for the holiday break: writing code recharged my batteries.
So I dreaded the arrival of AI coding agents. Now that they’re here, I feel melancholy, even sadness. What do you do when the thing you love, the thing that defines part of who you are, gets handed over to robots?
And yet, I’ve stopped resisting. Agents make it possible to achieve great things in a fraction of the time. Used well, they produce quality code. Those who denounce “AI slop” clearly haven’t seen all the “human slop” I’ve reviewed, or written, over the past 40 years!
So it’s with enthusiasm for what’s possible, but also while grieving an activity that nourished me for so long, that I decided to move our agentic shift forward.
Human-Centered Agentic Development
Our client experience relies heavily on our employee experience. It’s hard to deliver great service if our teams aren’t happy, motivated and engaged.
That’s why we approached this transition by putting people first: everyone who wanted to make the change had to have the opportunity to do so.
Our process must bring in humans at the right moments, for the right things. Their judgment and creativity are essential. That, I believe, is exactly what we need to protect. The risk is very real: a developer flooded with proposals to validate ends up approving them mechanically. They no longer review, they just stamp (the infamous rubber-stamping). At that point, the human is no longer in the loop. They’re just part of the scenery.
Agent capabilities keep evolving. We have ideas about the future roles of our teams, but we’re keeping an open mind. We’re asking everyone to embrace change, break down silos between practices and foster collaboration.
However, in all of this: how do you find joy again when you’re no longer doing what you loved?
Rediscovering Meaning at Work
Cutting stones, building walls or raising a cathedral: everyone can find fulfillment at different levels. Meaning at work is personal, and it shifts from project to project and moment to moment.
So I won’t pretend to define the meaning of developers’ new work. That would be reductive. What I can do is share the realizations that helped me make the leap.
First, I came to understand how much programming let me get into “the zone,” that state where time disappears and focus becomes deeply satisfying. That pleasure is no small thing: the brain gets real rewards from it. Replacing those hours with exchanges with agents is more efficient, but far less rewarding.
I sometimes find that bubble again by focusing on a specific task while my agents carry out my instructions. To get there, I have to resist the urge to constantly check on their progress.
Second, I rediscovered the satisfaction of seeing someone use what I’ve built. A script, a microservice or a feature: meeting a real need is still motivating.
Agents speed up that response, with an unexpected bonus: I’m more open to change requests. After a few hours of building rather than several weeks, I’m less attached to the initial solution. Happier users, more often: that’s rewarding.
Finally, I’ve always been confident in my ability to find technical solutions. Learning a language or a technology mostly took time. Agents save me that time and let me focus more on the “what,” at a speed I never had access to before.
These realizations are personal. You may not recognize yourself in them, and that’s okay. First, you need to understand what used to bring you joy, so you can find your own way to evolve.
Because there’s no going back: coding agents are here to stay.
What the Future Holds
I don’t have a crystal ball, but I believe the transformation of software development is only just beginning.
It requires rethinking the entire development lifecycle to integrate AI in an efficient and controlled way. Simply replacing a few steps risks producing disappointing software, for users and creators alike.
Engaged teams, however, will be able to solve far more problems, far faster. For developers, that means shifting our attention from the “how” to the “what” and the “why.”
Of all the changes I’ve lived through in four decades, this is the one I find the hardest. Still, I believe I’ve reached my tipping point, without turning my back on the curious teenager who brought me here.
I’m convinced you can make the leap too, in your own way. I’d love to hear about your experiences!
Agentic AI: when to use it, when to avoid it and how much control to hand over
Handing an AI agent the follow-up on overdue invoices, the triage of fraud alerts or the preparation of a claims file means opening your systems to it and letting it act on your behalf. In a regulated industry, where every action can affect a client, a regulated file or the safety of a team, one question needs an answer before any deployment: how much control should the agent have? Three guideposts help you answer it, from choosing the use case to setting the autonomy of each agent.
What sets an AI agent apart from an AI model?
Agentic AI refers to AI systems that carry out tasks and interact with an organization’s systems, going beyond content generation. Adoption is moving quickly, with nine in ten companies already exploring it in some form, according to BSI, the UK’s national standards body.
An AI model produces an answer or a recommendation that you then decide whether to use, whereas an agent pursues a goal by carrying out actions in your systems itself, with the tools and access you have granted it. Within an organization, the agent is part of a broader setup: models that read and draft, written and versioned skills that describe how a task is done, limited access to authorized systems, orchestration that coordinates the steps, and people who set the rules and approve sensitive decisions. All of an agent’s governance therefore starts with its scope, meaning what it is allowed to do and which systems it can reach.
When is agentic AI the right choice?
An agent delivers the most value when four conditions come together: high-volume repetitive work, clear written rules, available data and errors that are easy to detect and correct. The more of these boxes your use case checks, the stronger it is, which is why this check is worth doing before you choose a technology.
- High-volume repetitive work. An accounting team can receive hundreds of supplier invoices every week, and that volume is what justifies investing in an agent rather than having your teams handle each document by hand.
- Clear written rules. A travel expense policy, with its caps, required receipts and eligible categories, gives the agent a solid foundation to rely on, while rules that exist only in the head of an experienced employee leave it with nothing to go on.
- Available data. When the history of past files sits in personal inboxes or on paper, the agent has no way to use it, however good the model may be.
- Detectable, reversible errors. An email filed in the wrong processing queue can be spotted and moved in seconds, whereas a wire transfer sent to the wrong account is much harder to recover.
How can you tell whether your rules are documented well enough?
A good test is to ask whether a new hire could apply the procedure using only the existing documents, without having to ask a colleague. If the answer is no, the agent will run into the same obstacle, and your first project will be to put those rules in writing, which benefits your teams as much as your future agents.
What volume justifies an agent?
The threshold comes from weighing the time saved against the cost of an error. Volume works both ways, since it makes the agent cost-effective but also amplifies its flaws: at a thousand files a day, a small systematic error quickly becomes a significant problem. That is why volume appears both among the conditions for success and among the criteria used to set an agent’s level of autonomy, as you will see further on.
AI agent or traditional automation: which should you choose?
When a process follows fixed, predictable rules, traditional automation or well-designed software does better than an agent, since it costs less, always produces the same result and is easier to verify. An agent makes more sense when the task meets the four conditions described above, and in practice, four situations call for a different answer.
- The process follows fixed rules. Calculating taxes, transferring a file every night or sending a payment reminder on a set date is a job for traditional automation, and adding an agent would introduce uncertainty with no gain at all.
- Human judgment or the relationship is at stake. Delivering bad news to a long-standing client, negotiating a contract renewal or supporting someone in distress are moments when trust is built or lost, and while an agent can prepare the meeting, a person stays in control.
- History and data are missing. With incomplete, scattered or poor-quality files, the agent produces results that look convincing but rest on nothing, so your best investment goes first into data collection and quality.
- The action is irreversible and its impact significant. Cancelling an insurance policy, ending someone’s employment or recalling a product from the market are acts whose errors cannot be undone, so a person should make the call.
How do the costs of the two approaches compare?
Costs point the same way, since giving an agent a task that a simple rule can handle means paying more for a less stable result: each run calls on a model whose cost varies with volume and whose answer can change slightly from one time to the next. For predictable tasks, coded rules and traditional automation therefore remain the most economical choice and the easiest to audit, and in short, when a single tool can solve your problem, conventional software is enough.
Can you combine both in the same process?
The two approaches work very well together: within the same process, the predictable steps can rely on coded rules while the agent gathers information, sorts files or writes a first draft. The choice is made step by step, when the solution is designed, based on what each step truly requires.
What does agentic AI look like in finance, insurance and manufacturing?
In regulated industries, the strongest use cases share one principle: the agent prepares the file, and the person decides. Preparation tasks, such as sorting, gathering information and checking that a file is complete, make a good starting point because they often meet the four conditions for success while leaving the decision with your teams.
- In finance, for fraud alerts. Agents sort the alerts, pull together the client’s history and document the file, so the analyst no longer has to search five different systems and can focus on the decision.
- In insurance, for claims. Agents classify incoming files, detect that a repair invoice or a police report is missing and alert the claims adjuster, so the file arrives complete, without back-and-forth with the policyholder.
- In manufacturing, for equipment anomalies. When a sensor flags abnormal vibration on a production line, agents suggest diagnoses, retrieve the maintenance history and bring it all together for the technician before they even reach the plant floor.
How do several agents work together?
To see this collaboration in action, take the fraud example again with a fictional scenario, a $4,800 transaction made abroad at 3 a.m. on the card of a client who has never travelled: this suspicious payment triggers the process, and three agents step in, each with its own role and access.
- The detection agent analyzes the transaction and can only access the transaction feed.
- The investigation agent gathers the client’s history, such as spending habits and travel notices, and has access to the client file.
- The compliance agent checks that the applicable rules are followed and has access to policies and regulations.
At the centre, the orchestrator coordinates the work and tracks steps, errors and approvals, so if the investigation agent cannot find the file, the orchestrator detects it and flags it. At the end of the chain, the analyst receives a complete file and decides whether or not to block the card.
You will notice that each agent has different access, and that choice is deliberate. By limiting each one to the data it needs, you reduce the risk of leaks and unintended use, a principle that belongs to the Zero Trust approach and becomes essential when you move to production.
How much control should you give an AI agent?
An agent’s autonomy is set on a four-level scale, and the right level depends on the risk of each task, which lets you place the dial differently from one step to the next:
- The agent recommends, and a person decides and acts.
- The agent prepares and asks for approval before acting.
- The agent acts, then a person reviews its work.
- The agent acts on its own, within a pre-authorized, monitored scope.
This dial reflects a trade-off: at the first level, you stay in control, but the process is slower and depends on your teams’ availability, while at the fourth level, you gain speed and volume, provided you trust the agent and the guardrails around it.
What changes most from one end of the scale to the other is the person’s role, since at the first level they do the work with the agent’s help, whereas at the fourth they supervise what the agent does. “These are two different skill sets, and your teams need to be prepared for them,” says Gabriel Mongeon.
What criteria should you use to set the level of autonomy?
The level of autonomy should stay proportional to the risk, and six criteria help you assess it:
- Reversibility of the task. A misfiled document is easy to refile, whereas a payment that has already gone out is much harder to cancel.
- Impact. Measure the real consequences of an agent error for your clients, your operations and your organization.
- Volume. The more often a task repeats, the more a systematic error multiplies, as discussed earlier.
- The agent’s proven reliability. An agent that got it right on 500 reviewed files deserves more trust than one deployed last week.
- Human and ethical impacts. Refusing a loan or insurance coverage directly affects someone’s life.
- Legal and contractual requirements that apply to your industry and to your agreements with clients.
Can several levels coexist within the same process?
Yes, and it is an effective way to spread the risk. Going back to the fraud example, the detection agent can flag a suspicious transaction on its own, while the decision to freeze the account stays with a person. In the same way, an agent can be allowed to prepare 100 refunds without being able to send them until a person approves them, so each step gets the level that matches its own risk.
How do you move an agent up the scale?
You can start at the lower levels and move up over time as the agent proves its reliability on reviewed files. The movement works in both directions, since you can also step down a level if the context changes, for example after a model update or a change to your rules. To make these decisions on solid ground, you need a record of what the agent has done, hence the importance of an action log, which lets you measure its reliability based on facts.
Which decisions should stay with humans?
Irreversible decisions that directly affect a person, their rights or their safety should stay in human hands, whatever level of autonomy the agent has been given. Each industry has its own rules, but the logic is the same from one sector to another: identify these sensitive decisions, then set your agents’ autonomy accordingly, based on your risk tolerance.
- In insurance, denying a claim. The agent builds the file, but a person is the one who says no to the policyholder.
- In finance, freezing an account. The agent can flag a suspicious transaction, and the analyst decides what happens next.
- In defence, granting access to controlled data. The agent should never be the one that opens the door.
- In manufacturing, authorizing equipment to return to service after an incident. Worker safety is at stake, and that decision belongs to a qualified person.
These examples are illustrations, since every organization has its own sensitive decisions, which are worth mapping out before you deploy a first agent.
Which frameworks apply to your industry?
The regulatory landscape is moving quickly, and financial institutions face a firm deadline in May 2027, while other sectors rely on established frameworks:
- Federally regulated financial institutions. OSFI Guideline E-23 on model risk management takes effect on May 1, 2027 for all federally regulated financial institutions, and its definition of a model explicitly includes AI and machine learning methods.
- Insurers and financial institutions also operating in Quebec. Quebec’s Autorité des marchés financiers published the final version of its guideline on the use of artificial intelligence in April 2026, which takes effect on May 1, 2027 and applies to authorized insurers, financial services cooperatives, trust companies and authorized deposit institutions, among others.
- Ontario’s public sector and its suppliers. In January 2026, Ontario’s Information and Privacy Commissioner and the Ontario Human Rights Commission released joint principles for the responsible use of AI, and although these principles are not legally binding and mainly target the broader public sector, they call for a human in the loop and for organizations to be able to explain how an AI system works, expectations that may be passed on to the companies serving these institutions.
- Defence. The Controlled Goods Program governs access to sensitive goods and technical data.
- Manufacturing. ISO 9001, industry standards and Ontario’s Occupational Health and Safety Act set the boundaries for decisions that affect quality and safety.
- All sectors. If you serve clients in Quebec, Law 25 requires you to inform a person of a decision based exclusively on automated processing and allow them to have it reviewed, and the EU AI Act applies as soon as an AI system or its outputs are used in the European Union.
How do you document accountability?
Whatever the agent’s level of autonomy, a person remains accountable for its decisions, which means being able to explain after the fact what was done, by whom, on what basis and with what result. That is the role of the agent’s action log, which also helps you respond when a client asks for the reasons behind an automated decision, as Quebec’s Law 25 allows, or when a regulator asks how your system reached a conclusion. The design of this log and of the other technical controls around an agent in production will be the subject of an upcoming article.
Key takeaways
Before handing a process over to an AI agent, three guideposts shape the decision. First, choose a use case that combines high volume, written rules, available data and reversible errors, keeping traditional automation for the predictable steps. Next, set each agent’s autonomy according to the risk of its task and your tolerance for that risk, even if it means starting low and moving up as the agent proves itself. Finally, frame that autonomy with rules and technical controls, always keeping a person accountable for the decisions that matter.
In practice, a good first step is to list your organization’s sensitive decisions, then choose a file-preparation process where an agent can prove itself at the first or second level of autonomy, with an action log in place from day one.
That doesn’t mean I’m not proud of what we’ve accomplished. I’d just rather let the facts speak for themselves. Our Clutch.co profile is a perfect example: I much prefer letting our clients talk about their experience with us over trying to prove our expertise and professionalism.
With a stellar score like ours (spoiler alert: we’re at 4.9 out of 5 as I write this), you’d think the last thing we should do is mess with a winning recipe.
Maybe, but that’s not how I see it. And it would have made for a pretty short article.
What’s Behind a Near-Perfect Score
Our Clutch.co profile has been active for several years. Our near-perfect rating there makes for an excellent calling card and shows the level of service our clients are entitled to expect.
We also measure our Net Promoter Score (NPS) with our clients, and here too, we have an exceptional score of 83. Not a single detractor in sight.
What our 26 Clutch reviews and roughly 25 NPS respondents don’t show are all the people who didn’t answer the call. Where are the hundreds of clients we’ve served since we started out in 2003?
That missing data keeps me up at night: what on earth is the silent majority thinking? With that in mind, we’ve launched a major customer experience initiative to get to the bottom of it and, let’s be honest, help me sleep at night.
Customer Experience: Where Do You Start?
Customer experience is the heart of a services company. Probably of every type of company, but certainly of ours.
Every department, every employee, can tie what they do directly to a client, or at most with one degree of separation. In the famous RACI matrix, if everyone is Responsible for customer experience, who is ultimately the one person Accountable?
The easy answer would be me, but you could say that about practically everything.
Instead, we agreed that the marketing team would take charge of our clients’ experience, or more specifically, our Vice-President of Marketing. We took the opportunity to change her title to “Vice-President, Marketing and Customer Experience” to highlight how much importance we place on it, and to reinforce that this isn’t a project with a beginning, a middle and an end.
Now that there’s an accountable VP, we’re all set. Right?
Systematizing Human Experiences
Customer experience rests on a series of human interactions. The words used, the tone, the speed of the exchanges and the outcome all matter a great deal, but ultimately, it’s how people feel that truly lasts.
So how do we make sure our clients’ experience is memorable, for the right reasons, consistently, no matter who they’re talking to? Here’s the approach we chose to take.
First, we need to take stock of where things stand:
- Who talks to clients?
- At what point(s)?
- How?
It’s also essential to measure current client satisfaction. Hard to improve if you don’t know where you’re starting from!
As mentioned earlier, we already had an indirect measure through our Clutch.co reviews, and we now systematically measure NPS with our active clients. The next step will be to get the silent majority talking, without alienating them.
The biggest challenge is still ahead of us. Once we’ve mapped out every client interaction, we’ll need to define the RACI for each step and make sure it’s clearly understood, and applied, by every single person.
Next, standards (response times, communication channels, level of language, etc.) will need to be defined across the board, adapted to our different client personas, and our staff trained accordingly. Once that’s firmly in place, we can look at the key moments in our customer journey to delight our clients and build even stronger loyalty than we do today.
It’s no small feat, but we’re convinced that in a world undergoing profound transformation, a customer experience built on meaningful human relationships remains essential.
Frequently Asked Questions
We start from your business problem, not the technology. Sometimes artificial intelligence is the right answer, sometimes it’s a better architecture, modernization or better data. Our job is to figure out the difference before we begin.
When AI is the right path, we target a concrete use case (optimizing a process, automating a task, making better use of your data or deploying generative AI) then we build a roadmap tailored to your context. Our approach is human-first, because to be adopted, AI has to fit your tools, your processes and your teams’ reality.
We choose technology based on your needs, not the other way around. From UX/UI design to development, we deliver web, mobile and cross-platform applications, and we work with the major cloud platforms, AWS, Azure and Google Cloud, in single or hybrid environments. Depending on the project, our teams use technologies such as .NET, Node.js and Angular, along with Swift and Kotlin for native mobile.
Yes. It’s a common request. A prototype validates an idea, but a product meant for production demands robustness, security and the ability to scale. We take over your existing work, consolidate the architecture, close the quality and security gaps, then deliver a solution ready to be deployed and maintained over time.
The first step would be to contact us. Even if you are very early in your process, our team can help you how to get there.
Our work is as varied as the organizations we work with, but our process is consistent.
In a typical software project, we follow a proven process. We begin with a Discovery Phase to clarify user needs, technical constraints, and risks before development starts. We then design the solution, followed by agile development and QA to bring it to life. Once your application is delivered, we stay with you to support, maintain, and evolve it over time.
Spiria is SOC 2 Type 2 certified, the most rigorous standard in this area, because it verifies the effectiveness of our controls over time, not just their design. It covers five criteria: security, availability, processing integrity, confidentiality and privacy.
Yes. That’s what we did for Cominar. After a first vendor was unable to complete the project, we finalized development, launched the application and consolidated its architecture for a large-scale rollout.
Check out our case studies to see how we helped companies like yours.






