Documents trickling in, dozens of reminders at the end of every month, staff spending part of their day looking for an answer in the BOFiP or in the firm’s procedures… All time your teams would rather spend with your clients. At Kreante, we design custom AI solutions for chartered accounting firms. We start by taking the time to understand your organisation, then we build on top of your software, Pennylane, Cegid, Sage, ACD or others, to automate what they don’t yet do. All in strict compliance with professional secrecy, and with a team that stays by your side long after go-live.
265+ projects delivered in 35 countries · 4.9/5 average rating on Clutch · teams in Paris, Madrid, Miami and Lima
Does this sound like your firm?
Clients chased three times for the same bank statement, and files stuck waiting for their supporting documents
Staff each using ChatGPT on their own, without knowing which data they are allowed to paste into it
Engagement letters, know-your-client forms and due diligence obligations that take ages to prepare
The same client questions about VAT or expense claims, asked every week to the same people
Production software that already includes AI, but doesn’t talk to your document management system, your client portal or your email
A “Firm_procedures_v4_up_to_date.docx” file that nobody has opened in two years
According to the Ordre’s barometer, 71% of chartered accountants have already tried at least one AI tool and 91% see it as an opportunity[1]. What remains is to turn it into a real time saving, every day, for the whole firm. To get there, AI must be connected to your software, governed by rules everyone understands, and used by the whole team. That is where we come in, from the first idea to your staff getting to grips with it.
AI keeps the list of missing documents for you, file by file. It reminds your clients at the right time, in the right tone, and only alerts you when a client does not respond.
Taking on a new client means gathering a lot of information, then checking it carefully. AI prepares the file, and your teams approve each step.
Your staff ask their question as they would ask a colleague, and get a sourced answer, drawn from your procedures, your templates and the documentation you have chosen.
Let’s be clear, AI does not sign off any accounts. It prepares the ground, so that your staff can spend their time on analysis and advice.
Pennylane, Cegid or Sage offer their own AI features, often very effective for data entry, bank reconciliation or pre-review. But a firm’s day-to-day is not just its production software: document management, email, client portal, engagement letters, internal procedures… It is often in the back-and-forth between these tools that the most time and information is lost.
| Criterion | Your accounting software’s AI | Kreante custom solution |
|---|---|---|
| Ideal for | Data entry, matching, reconciliation and pre-review | Connecting your tools together and automating the firm’s own processes |
| Scope | The data held in the software | Your production software, your document management system, your email and your procedures |
| Customisation | Configuration within the vendor’s limits | Adapted to your organisation, your templates and your internal rules |
| Ownership | Included in the subscription | You own the code, with no per-user licence |
Your clients entrust you with their most sensitive information: their accounts, their salaries, their tax returns, sometimes their assets. As you know, professional secrecy is a fundamental ethical obligation, and the Ordre points out that some consumer AI tools may use the data entrusted to them to train their models[2].
With today’s AI tools, one of your staff can build a small app in an afternoon, then share it with the whole team without anyone checking who can access what. And fraudsters use AI too, to send you fake emails from clients or suppliers that look more real than the real thing, or to find the weaknesses of a poorly protected tool faster. That is why every solution we deliver is reviewed and tested by our senior developers before going live:
Your data hosted in Europe, and never used to train AI models
Access rights defined per file, per team and per staff member
Your data anonymised whenever the use allows it, as recommended by the Ordre[2]
Systematic human approval of anything that commits your firm
A log of the AI’s actions, so you know at all times who did what
Clients clearly informed when they are interacting with an AI, as required by the European regulation since 2 August 2026[3]
In most firms, some staff use AI every day, others never. Often, nobody has simply shown them what it can change in their work. The Ordre recommends training teams, appointing an AI lead and adopting a usage charter[2][4]. We help you do it:
Time spent on reminders, time to collect documents, recurring client questions: we measure your processes before suggesting anything. You know where AI will really save you time, and you see the proof, file after file.
Your staff keep the tools they know. Our solution connects to them, without disrupting their habits or forcing a migration on you.
AI prepares, your teams approve. An engagement letter, a due diligence item or a reply to a client always go through the chartered accountant or an authorised staff member before they commit the firm’s liability.
We know there is no question of taking up your time in the middle of tax season. Development and training are planned with you, at times when your teams are available.
The scope is set in writing before we start, and the budget does not change along the way. The code is yours, with no per-user licence, even as your firm grows or opens new offices.
We started out with platforms such as Bubble, WeWeb or Xano. Today, our teams develop with Cursor, Codex and Claude Code, and our own AI agents write a large part of the code, under the supervision of our senior developers. The result: a first version delivered in a few weeks, and a team that knows exactly where AI helps, and where a human must stay in control.
Free
30 minutes with an expert
Custom quote
Immersion in the firm, then a costed roadmap
Fixed price, custom quote
Scope and budget approved in writing before we start
The AI consulting engagement is described in detail on its own page.
We spend time with your teams to understand your organisation and what slows you down.
We measure your current processes: time to collect documents, number of reminders, recurring questions, closing times.
We develop a first use case, connected to your tools. Our AI agents develop, and our senior developers steer and approve every step.
We test it with one team or one portfolio of files, train the staff involved, then roll it out to the rest of the firm.
We compare the results with the initial measurements, and decide together what comes next.
Challenge
Stack
Performance and payroll management platform for AutoCartel field photographers.
Challenge
The platform ingests property data daily via Zillow scraping, runs AI-driven renovation cost and ARV estimates using OpenAI, and surfaces the highest-potential deals first. Users can review…
Stack
An AI-powered real estate intelligence platform built for a Miami-based investment team. DAVCO AI replaces manual Zillow filtering and spreadsheet-based calculations with an automated map interface that displays estimated profit margins across all active single-family listings in the Miami area.
Challenge
Tango event organizers across Europe were running everything manually — registrations, confirmations, payments, check-in. They needed one purpose-built platform to manage the full event lifecycle,…
Stack
TheFlow is a web platform built for tango event organizers in Europe. Kreante evolved it across multiple phases from a basic registration tool into a complete event management and ticketing product — covering event creation, participant management, waitlists, online payments, QR check-in, automatic invoicing, and an international tango event calendar.
Challenge
Kreante developed a comprehensive platform for Pure Engagement using NoCode technologies. Built with Bubble for the frontend and Xano for the backend, this solution facilitates organizational…
Stack
Pure Engagement needed a platform capable of handling the complexity of organizational transformation, recognizing that success depends not only on structural change but also on people’s psychological and emotional transition.
Challenge
Build an iOS app that turns iPhones plus an audio interface into a complete, professional podcast recording studio, capturing high-quality sound and video across several phones at once and keeping…
Stack
A mobile app that lets creators record, sync, edit, and export podcast audio and video using a dedicated interface and multiple iPhones working together as one studio.
Challenge
Patients leaving clinic checkups with a list of medical recommendations and lab results often had no clear, practical way to turn that information into daily meals, leading to poor adherence and high…
Stack
Kreante built REMI AI, a system that reads a patient's genetic and medical test results and automatically turns them into a personalized nutrition and supplement plan that gradually evolves over several months, with clinic staff reviewing every AI-generated interpretation before it reaches the patient.
Challenge
Stack
In the evolving landscape of web development, choosing the right approach for custom software development is crucial.
Challenge
Stack
In the sustainability-focused retail landscape, product repair and maintenance play a pivotal role in circular economy initiatives. Businesses are increasingly adopting innovative solutions to reduce waste and extend product life cycles.
Challenge
Stack
When Garde-Robe presented their innovative vision to make fashion more social and collaborative, Kreante, a leading LowCode agency, eagerly embraced the challenge.
Challenge
When INSPO approached our LowCode agency with their vision of creating the definitive platform for thought leadership, we knew this project would push the boundaries of what’s possible with…
Stack
In the rapidly evolving landscape of LowCode development, creating sophisticated applications no longer requires months of traditional coding.
Challenge
Stack
Connect with verified construction professionals, find new projects, recruit subcontractors, and grow your business with ShareLeads' trusted B2B platform.
Challenge
The basketball community in Washington D.C. lived on courts and in scattered WhatsApp groups. What was missing: a place to give it visibility, bring more people together, find players at your…
Stack
What we built In 3 months, Kreante delivered all three platforms at once. The mobile app lets you find pickup games within a 10-mile radius, rate players to compete at the right level, track your progress, and meet up to watch games together. Two tiers: a free version and a premium subscription at $39.99/season — proof that the community is willing to pay to play better. For this kind of project, visual identity isn't just a detail — it's what creates the sense of belonging from the very first open. The entire branding was conceived and built by Kreante. The landing page was built to convert: a strong visual world, a clear message, one goal — trigger the download. The e-commerce store pushed the logic even further: unapologetic street style, rooted in DC culture, to rep your colors beyond the court. Launched at a Virginia tournament, HoopSquad is now live across 13 regions in the United States — on the App Store and Google Play.
Challenge
The Meetern team had been connecting students and companies for years, through physical events. Many great encounters and opportunities later, they understood that to create real impact at scale,…
Stack
What we built Kreante designed and developed Meetern: a complete matchmaking platform, with three distinct interfaces for students, companies, and academic institutions. Students build their profile, apply, and track their applications. Companies post opportunities and receive intelligently matched profiles. Academic institutions monitor placements in real time. Across all three: integrated messaging and a matching algorithm that replaces manual introductions. The platform is multilingual, French and English at launch, Dutch on the way. A V1 delivered in 6 months, a V2 launched in March 2026 with extended language support. Today, 50 to 100 active users every day. And a team that no longer runs events, but a platform.
Challenge
Every manager knows a motivated team performs better. But motivation is invisible. And without understanding what truly motivates each person, engagement initiatives remain educated…
Stack
Kreante designed and developed Motives Solutions: a bilingual SaaS platform (FR/EN), from branding to application. Team members answer 3 anonymous questions. The app analyzes responses and generates a detailed report by motivational driver, for each individual, each team, each organization. Two modules: Motives TEAM for team-level insights, Motives ORGA for the full picture. Tracking is longitudinal: engagement evolution over time, visualized. Three questions. A clear picture of what truly moves a team forward. Measuring the invisible, so you can finally act on it.
Challenge
After a decade training thousands of women for tech jobs, Laboratoria saw its graduates stall on the way to leadership: in engineering and product, only 52 women are promoted to management for every…
Stack
Laboratoria+ is the membership platform of Laboratoria, the Latin American organization that has helped more than 14,000 women access quality jobs in tech. Built with Bubble, it brings together live courses and learning circles, 1:1 career mentoring with a network of senior women executives, online and in-person events, and a free plan alongside paid Pro and Plus subscriptions.
Challenge
Stack
Transform your organization with ROC's secure hyperautomation platform. Orchestrate workflows, governance, and access management from a living organizational chart.
Challenge
Class2Class wanted any teacher in the world to find a partner class and run a real project together, but international collaboration in schools depended on personal contacts, scattered tools and…
Stack
Class2Class is a global learning community, based in Denmark, where teachers connect their classrooms to run real-world projects around the UN Sustainable Development Goals. Kreante rebuilt the web platform with Bubble and Xano — teacher profiles, class matching, project creation and collaboration spaces — and delivered the rebranding and landing page. The community now counts more than 25,000 teachers in 190+ countries.
Challenge
In Switzerland as across the world, independent cab drivers face the same reality: ride-hailing platforms that set the rates, impose the rules, and own the client relationship. Olivier Fouvy wanted…
Stack
SmartCab is built on a radical premise: for the end customer, nothing changes. No new app to download, no account to create, no interface to learn. They send a WhatsApp message to their driver, just as they always have. Behind that message, an entire machine kicks into gear: an AI engine processes the request, calculates the route, confirms the booking, and triggers invoicing — automatically. Everything an app does. Without the app. They send a WhatsApp message. The rest happens without them. For drivers, it means freedom regained: customizable pricing, a client relationship that belongs to them, no algorithm to appease to stay visible. For fleet operators, a dispatch module handles ride assignments and real-time driver tracking. Three subscription tiers: Lite, Pro, Premium — built for every profile. What SmartCab proves is that real sophistication doesn't announce itself. It's felt — in a booking that requires zero effort, in a relationship of trust that no one gets to monetize. Available on iOS and Android.
Your teams know better than anyone the tasks that take up most of their time. Let’s start from there, and see together what AI can change for your firm, in a first conversation that is free and without commitment.
There is no single AI that does everything, but rather several families of tools. In most firms, they complement each other.
| Type of tool | Uses in a firm | Examples | Watch out for |
|---|---|---|---|
| AI built into the production software | Data entry and OCR, matching, bank reconciliation, pre-review, anomaly detection | Pennylane, Cegid, Sage | Limited to the software’s data and processes |
| Regulatory research assistant | Querying the French chart of accounts (PCG), the BOFiP or collective agreements, with sourced answers | Luca by ComptaSecure | Knows neither your files nor your internal procedures |
| The Ordre’s assistant | Answering questions about professional practice and statutory tasks | ExpertCHAT | Scope limited to the profession |
| General-purpose AI | Writing a client email, summarising a document, rephrasing an explanation | ChatGPT, Claude, Mistral, Copilot | Never non-anonymised client data in the consumer version |
| Custom solution | Connecting the production software, document management and email, querying your procedures | An agency like Kreante | Requires scoping and data preparation |
Before choosing, check above all where the data is hosted and whether it is used to train the models. We cover these points in detail in the question on professional secrecy.
No, but it is transforming the profession, and this is only the beginning! AI already handles part of the repetitive tasks, and that share will grow with e-invoicing, which brings better-structured data. Everything that requires judgement, responsibility or human relationships, on the other hand, remains in the hands of professionals.
As the Ordre points out, AI output must never be taken as absolute truth, and must always be reviewed[2]. The International Labour Organization reaches the same conclusion on a larger scale: for most occupations, generative AI transforms work far more than it eliminates it[8]. For a firm, the challenge is therefore to free its staff from production work, so they can develop higher-value engagements.
No, that is not its role. ChatGPT is a very good assistant for writing an email, summarising a document or rephrasing a technical explanation for a client. But it is not designed to keep accounts: it can be wrong with great confidence, it does not know your files, and its consumer version does not guarantee the confidentiality of the data you give it. The Ordre recommends favouring solutions designed for the profession, and never pasting non-anonymised client data into it[2].
It is a fundamental ethical obligation, and some consumer AI tools may use the data entrusted to them to train their models[2]. Before adopting a tool, take the time to check five points, which the Ordre’s bodies also recommend[1][2]:
Remember also to tell your clients how the firm uses AI. It is a sign of transparency they appreciate, and one of the good practices highlighted by the Ordre[1].
Technically yes, and some production software already offers it for simple transactions. But an automatically posted entry is only acceptable under a few conditions:
For all unusual transactions, the rule remains simple: AI suggests, and the staff member approves.
Yes, several resources are available free of charge, starting with the Ordre’s. Just bear in mind that a free tool has no place in your clients’ files:
As soon as your clients’ files are involved, you need a solution that guarantees their confidentiality, with controlled hosting, no training on your data and real access control.
The European AI regulation requires businesses that use AI systems to take measures so that their teams have a sufficient level of knowledge[5]. Since its revision in 2026, this is an obligation of means: no duration or qualification is imposed, but the firm must act, taking into account how each person uses AI[6]. In practice, it is also the best way to reassure your teams and make AI a real everyday reflex.
Since 1 September 2026, all businesses in France must be able to receive electronic invoices, and large and mid-sized companies must also issue them in this format. SMEs and micro-businesses will follow from 1 September 2027[7].
In practice, your clients’ invoices increasingly reach you as structured data, much easier for AI to use than a scanned PDF. You can therefore automate more of the production work, and spend the time saved on new engagements such as cash-flow monitoring or forecasting for your clients.
The budget depends on the number of processes involved, the software to connect and the size of your firm.
At Kreante, every project is priced at a fixed rate on a scope defined in writing, after a free assessment. On top of that comes the AI usage cost, which depends on the volume of documents and questions processed. We estimate it with you before we start, so there are no unpleasant surprises.
There is no “best AI agency” in absolute terms, only one suited to your firm. Before committing, ask it these five questions:
The market brings together accounting software vendors that include AI, specialist assistants, training providers and agencies that design custom solutions.
| Provider | Type | Positioning |
|---|---|---|
| Kreante | Custom-build agency | AI solutions designed for each firm, built on the production software and existing tools, with team training. 265+ projects delivered in 35 countries, 4.9/5 on Clutch |
| Pennylane | Software with built-in AI | Accounting production platform with automated data entry, reconciliation and pre-review, and an AI assistant |
| Luca (ComptaSecure) | Specialist assistant | Search across accounting, tax and employment texts, and analysis of the audit file (FEC) |
| Studeria | Agents and support | AI agents for firms’ production tasks, with three levels of autonomy: alert, suggestion, execution |
| Agence Talos | Agency | AI for accounting firms: document collection, reminders, client requests, engagement letters |
| Moon | Agency | Training, process audits and custom tool development for accounting firms |
This list is not exhaustive.
Written by Jorge del Carpio, CEO and co-founder of Kreante. Since it was founded in 2020, the agency has delivered 265+ projects in 35 countries.
Published Updated
From the blog
Guides, comparisons and field notes from the projects we deliver.
ToolsPick Lovable to get a hosted, Supabase backed live app fast. Pick Claude Design when engineering teams need code first prototypes and tighter code control.
DevelopmentMost AI automation projects show no measurable result. A Kreante project manager explains the sequence that works, with pricing and a real case study.
DevelopmentPilot AI coaching for one to three teams over 6 to 8 weeks, measure workflow KPIs, and demand embedded deliverables to keep skills in house.
Insights & TipsOutcome first AI playbook for SMBs: use a 5-criteria scoring rubric, run a 4-week before and 4-week after task audit, and pilot in 6–12 weeks to prove ROI.
DevelopmentAn outcomes first AI lifecycle mapping seven stages from prototype to production, covering agents, RAG, evals, guardrails, and a short roadmap.
Insights & TipsExecutive guide to AI consulting with an ROI first approach. Get a roadmap ordered by return, avoid vendor lock in, and secure code ownership.
