📊 Complete Case StudyHow Next Decision automates lead qualification with artificial intelligenceThe story of Noé BONNE, an AI consultant who transformed a time-consuming manual process into an intelligent automated systemTalk to an AI ExpertFree TrialA consulting firm facing a Growth ChallengeNext Decision is a consulting and expertise firm that has been supporting companies in all matters related to data for over 20 years. With around 250 employees spread across 10 offices throughout France, the company originated in Nantes and now covers the entire country.“We support all types of companies—small, medium-sized, and large enterprises—across all industries,” explains Noé BONNE, AI consultant at Next Decision, in charge of delivery and training. “Historically, we come from the data world, and we’ve expanded into several other areas: artificial intelligence, governance, CSR, strategic roadmaps… Overall, if it’s related to data, we know how to do it.”“Qualifying these leads—these incoming messages—took time and, above all, we lacked responsiveness. At Next, we don’t really have dedicated salespeople; it’s the consultants who handle this. As a result, processing all these incoming messages and reacting quickly—whether it’s a client requesting a service or a CV submission—was not something we were always able to do fast enough.”Noé.But even for a data expert like Next Decision, a persistent operational challenge remained: qualifying incoming leads.Each week, around ten messages arrive via the website’s contact form. Requests of all kinds: large enterprises looking for strategic support, SMEs wanting to structure their data, but also students submitting their CVs or poorly qualified inquiries.The manual process was time-consuming: for each message, a consultant had to search for the company online, check whether it already existed in the CRM, identify the contact’s role and level of experience, assess the relevance of the request, and then create or update the information in the system.📊 The Problem in Numbers⏱️ 15 minutes per message for manual qualification📧 10 messages received each week⏰ 2+ hours lost per week on repetitive tasks⚠️ High risk of missing business opportunitiesThe Turning Point: Leveraging AI by Starting with DataFor Next Decision, adopting artificial intelligence didn’t come from a trend, but from a natural business logic.“The turning point for us was that we have strong integration with companies and their data foundations,” explains Noé. “These are our clients, and we’re usually the ones who built their entire data foundation. What’s interesting with AI is that you can generally only leverage it when you have quality data.”“The turning point for us was that we have strong integration with companies and their data foundations. These are our clients, and we’re usually the ones who built their entire data foundation. What’s interesting about AI is that you can generally only use it when you have quality data.”NoéThis historical expertise in data structuring allowed Next Decision to spot the opportunity before others:“Once we’ve established a solid data structure within a company, we want to make the most of all that data. And one of the best ways to do that is to use artificial intelligence to extract insights from it.”But the arrival of generative AI changed the game:“Whereas before we started from a solid data foundation and enhanced it with AI, now it gives us the ability to leverage data within companies that wasn’t previously considered high quality: unstructured data.”PDF documents, text files, all of that information that didn’t fit into a traditional database table can now be exploited.“On the contrary, we can now extract value from these documents with generative AI, using systems that can scan all these files and pull out meaningful information.”Why Swiftask? A Carefully Considered Strategic DecisionFaced with the many solutions on the market, Next Decision tested several platforms: ChatGPT, Claude, and even internal proofs of concept using open-source models like Llama.Geographic and Human Proximity“It’s a company from Nantes. We like working with nearby companies,” explains Noé. This proximity isn’t just about distance:“Responsiveness… we immediately saw that with the Swiftask team—when we request a new feature, they’re on it within a week.”Unbeatable Value for Money"Le rapport qualité-prix est hyper concurrentiel et c'est peut-être l'élément le plus important", souligne Noé. "Pour se lancer sur une plateforme, le coût d'entrée si on a beaucoup de licences peut être assez gros. Là où Swiftask, on peut vraiment commencer très petit avec un coût très faible et c'est super pour monter en puissance."The Versatility of Integrated Tools“What’s interesting with Swiftask is that sometimes we enter a company, map out their business ecosystem with their CRM, ERP, and the various software we might need to connect to, and we realize that all of this is already integrated with Swiftask,” explains Noé. “All this initial tool setup is already done, so everything moves very quickly afterward.”Governance and Security“Generally, we needed a platform for governance and to have a shared platform accessible to all employees,” explains Noé. Swiftask meets this critical need by eliminating Shadow IT, where everyone uses ChatGPT on their personal PC without oversight.“When I discovered Swiftask, I thought, ‘Why not?’”NoéA Multi-Vendor Approach“We always operate… we’re never tied to a single provider or a single vendor,” emphasizes Noé. “What we do with clients is often a decision matrix. We present the different platforms available on the market and show what each can do, their strengths.”And the observation is clear:“What we see is that many clients turn to Swiftask, especially for its value for money and the versatility of the tools already integrated.”Several factors motivated this choice:Ready to Transform Your Lead Qualification Process?Talk to an AI ExpertFree trialThe Solution: An AI Agent That Does the Work for YouNext Decision’s idea is simple yet powerful: place an AI agent between incoming website messages and the consultants to do the heavy lifting for them.“The idea is to place an AI agent between the incoming website message and us, so it simply does the heavy lifting for us.”NoéHow Does It Work in Practice?When a message is sent via Next Decision’s website form, the AI agent automatically retrieves it and performs a series of tasks:Company Research: Identifies the company, its industry, location, and revenue using Papers.Contact Research: Determines the contact’s role, experience, and professional background.CRM Check: Verifies if the company is already a client, checks ongoing processes, and identifies the account manager.Lead Scoring: Rates the relevance of the lead from 1 to 5 stars.Automatic CRM Update: Creates the contact and company if needed, or updates existing information.“These were tasks we used to do manually, but now they’re automated,” explains Noé. “We have all this information right in front of us when we handle lead qualification.”A Convincing DemonstrationDuring the webinar, Noé gave a live demonstration using a fictional example: Tim Cook from Apple US contacting Next Decision for support on process optimization.In just a few seconds, the AI agent:✅ Identified Apple US, its industry, and revenue✅ Found Tim Cook’s role (CEO) and professional experience✅ Assigned a 5/5 score (“strategic AI project aimed at process automation, high potential”)✅ Automatically created the opportunity and contact in Zoho CRM“There’s no human intervention in this entire process,” emphasizes Noé. “Human input only comes in when we’re in our software with the list of all incoming messages, and we can process them.”An Accessible Setup: No Code, Just Business LogicCreating this agent may seem complex, but Noé shows that it’s within reach for any business professional.1.Choose the Brain (the LLM Model)“We chose GPT-4o, the same model as ChatGPT,” explains Noé. “We tried several, and this one offered the best performance for the lowest cost.” The pricing is transparent: one Swiftask credit per word generated.2.Select the ToolsThis is where the magic happens. The agent receives a “toolbox” with:The ability to perform internet searchesAccess to Papers for reliable dataConnection to Zoho CRM via an MCP server“When we add tools, I click ‘add a tool,’ search for ‘web search,’ and just like that, I have all the tools. I can simply click, and it’s added,” demonstrates Noé. “It’s really like Legos. It’s your little Sims that you build.”For non-native tools like Zoho, Swiftask provides MCP servers:“Any software, no matter how niche, any business software… the fact that Swiftask lets you manage MCP servers means you can build your own tool, and it’s relatively simple.”And the most interesting part:“Once we’ve built it for one company, any other agent I create can use that tool—it’s already built. It’s shared, and once it’s created, it works for everyone.”3.Give the Instruction“We describe its role,” explains Noé, showing the agent’s instruction. “It’s an agent responsible for analyzing incoming leads at Next Decision. We outline our business sectors so it knows where we can respond or not.”The instruction details the processing logic, step by step: analyze the lead, research the company, consult the CRM, identify the contact’s role, assign a score, create the opportunity.“It’s really chronological, a business-oriented approach,” confirms Noé. “It’s what we could give to an intern if we wanted to explain how to do this task. We explain: you’ll start by doing this research, then that, then this, and so on.”Not a Single Line of Code“There’s truly no coding involved,” emphasizes Noé. “We take the building blocks, the connectors, tell it to fetch from this Drive folder that’s automatically updated, and describe what it should do in natural language.”Three simple steps:Immediate and Measurable ResultsThe impact of this agent on Next Decision is direct and measurable.“We’re a relatively small team where the volume isn’t huge. We have many clients for whom we handle similar use cases, but instead of 10 messages per week, it could be 10,000. And that’s when the ROI looks completely different.”NoéA Significant Time Savings“The clearest ROI is simply how much time we’ve saved,” explains Noé. “We get around ten messages per week. For each message, we’d spend about ten minutes doing all the research in our CRM, online, checking the client, and assessing interest.”💰 Calculated ROI10–15 minutes saved per message× 10 messages per week= 1 full workday saved per month🚀 And that’s just for 10 messages per week!Increased ResponsivenessNo more waiting for a consultant to be available to qualify a lead. The agent works 24/7, instantly.“We weren’t always reactive enough. Now, as soon as a message arrives, it’s processed immediately.”Improved Lead Qualification QualityThe agent never gets tired, never skips a step, and applies the same rigor every time.“The agent is smart. It doesn’t just create something new each time—it checks if the contact already exists, links it if it does. Same for the client. It’s truly equivalent to what we would do manually.”A CRM Always Up to Date“Sometimes, salespeople don’t have the time to create or update the CRM, add contacts, input information,” notes Noé. “We don’t always do this automatically and quickly. Now, it’s done systematically.”Immediate Scalability“Once we have the tool, it scales easily,” emphasizes Noé. “We spend more time automating and optimizing than building the agent.”Beyond Lead Scoring: A Comprehensive AI StrategyThe lead qualification agent is just one component of a broader AI strategy at Next Decision.1. Automated Competitive Intelligence“The first use cases we implemented were for competitive intelligence,” says Noé. “The concept is pretty simple. We want an agent to scan everything happening with our competitors online—news, updates—every week or month, and send us a short recap email. It’s easy to set up and super fast in Swiftask.”2. The HR Agent for Internal Processes“Our HR team was often responding to questions—emails from employees asking for information that was already in Next’s documents,” explains Noé. “Searching through the 30 PDFs we have and just sending an email takes time, and it’s not something that adds value.”Solution: An agent integrated into the intranet, accessible to everyone, that instantly answers questions about HR processes by using PDFs automatically updated on the Drive.3. The Technical Agent for Documentation“We did the same with a technical agent that searches through our internal documentation on all processes and technologies we use, and provides answers to employees,” explains Noé.“It’s something relatively simple to experiment with, and that’s the advantage of AI agent tools like Swiftask. Setting up the basic configuration of a new agent is easy, and a business professional can create their agent and try things out. It’s helpful to have guidance at the beginning to set the right direction, know which use cases to apply, and which tools to build. But once you have that, the goal is for you to be completely autonomous with the platform.”Noé.A Gradual and Strategic Adoption“It’s something relatively simple to experiment with, and that’s the advantage of AI agent tools like Swiftask,” explains Noé. “Setting up a new agent is easy, and a business professional can create their agent and try things out.”Noé’s Recommendation:“It’s helpful to have guidance at the beginning to set the right direction, know which use cases to apply, and which tools to build. But once you have that, the goal is for you to be completely autonomous with the platform.”Other Deployed Use Cases:A Surge in DemandNext Decision’s AI expertise is certainly getting noticed.1. Security and Governance“There’s a strong need for data security. We want to stop Shadow IT, and clients come to us saying: we know everyone is using ChatGPT on their personal PCs, and that’s not acceptable. We need an enterprise-wide platform where we can govern everything.”2. Speed of Implementation“We move quickly toward automation because once we have this platform, as you’ve seen, it’s fast to implement,” explains Noé.“Just this month alone, I think we have 5 or 6 clients—5 or 6 clients where it’s really in progress. Most are using Swiftask, while other clients are on different platforms. These are really large accounts.”Noé⚡ Deployment TimeFrom zero to an operational AI platform with multiple use cases:10 days – a few days to at most around ten days.“To go from nothing to ‘I have an AI platform in my company with several deployed use cases,’ it can take just a few days, around ten days, maybe slightly more. It happens very quickly, and that’s what clients love right now.”This surge is driven by two converging needs:Join the Companies Automating with AITalk to an AI ExpertFree trialExpert Tips for Getting StartedDrawing on his experience, Noé shares his recommendations for companies looking to get started.1. Experiment Without Delay“The advantage of these tools is that you can try them right away,” encourages Noé. “It’s not a complicated tool to get started with. Whether it’s ChatGPT or a one-week free subscription on Swiftask, you have the platform, you can run tests, create agents. It all happens very quickly.”2 . Get support with the strategy"When trying to build an AI integration strategy within the company, it's helpful to get expert guidance," recommends Noé. "We have experience in this area and have seen what's happening with our other clients. We can guide you toward the use cases with the greatest added value and those we can address the quickest."3. Build a shared tool library"It's interesting at the beginning to think: we're going to build the tools that allow each agent to connect to our software," explains Noé. "Once we have these tools, building the agents can go super fast because we have all the building blocks."4. Aim for autonomy"We often work collaboratively, building with you, and that's also the goal," explains Noé. "The goal is for you to be completely autonomous with this platform."Key TakeawaysThe story of Next Decision demonstrates that integrating artificial intelligence into business is not reserved for tech giants or companies with colossal budgets."The ROI is obvious. We're trying to automate a process that we used to do manually. The clearest ROI is how much time we've saved."Noé✅ With a pragmatic approach, Next Decision has:.✅ Identified a time-consuming process: lead qualification (15 minutes per message)✅ Chosen the right tool: Swiftask for its flexibility, value for money, and governance✅ Created an intelligent agent in just a few hours, without coding✅ Achieved immediate results: one day of work saved per month✅ Deployed a comprehensive AI strategy: competitive intelligence, HR support, technical documentation✅ Shared expertise: supported 5 to 6 clients simultaneouslyAnd this is just the beginning. As Noé points out, "We're a relatively small group. We have many clients for whom the volume is enormous. Instead of 10 messages per week, it's going to be 10,000. And there, the ROI is different."Artificial intelligence doesn't replace Next Decision's consultants. It frees them from repetitive tasks so they can focus on what really matters: providing strategic support to their clients, building innovative data solutions, and creating value."AI is becoming transparent," Noé concludes. "It's the integration of AI tools into business processes. A Swiftask agent is running in the background, but you don't see it."Perhaps that, ultimately, is the real revolution of AI in business: becoming invisible, integrating naturally into existing workflows, and allowing humans to focus on their expertise rather than administrative tasks.Ready to Automate Your Processes?Join Next Decision and hundreds of other companies that are transforming their productivity with AI.Talk to an AI expertFree trial