How can we use analytics, boosted by agentic AI, to support companies in their green transformation?<\/p>\n<\/blockquote>\n For years, the focus of my blog was always on using Supply Chain Analytics methodologies and tools to solve specific problems.<\/p>\n At Logi<\/a>G<\/a>reen<\/a>, the startup I founded, we deploy these analytics solutions to help retailers, manufacturers, and logistics companies meet their sustainability targets.<\/p>\n In this article, I will demonstrate how we can supercharge these existing solutions with AI agents.<\/p>\n The objective is to make it easier and faster for companies to implement Sustainability<\/a> initiatives across their supply chains.<\/p>\n As political and financial pressures shift focus away from sustainability, making the green transformation easier and more accessible has never been more urgent.<\/p>\n Last week, I attended the global ChangeNOW <\/strong>conference, held in my hometown, Paris.<\/p>\n This conference brought together innovators, entrepreneurs and decision-makers committed to building a better future, despite the challenging context.<\/p>\n It was an excellent opportunity to meet some of my readers and connect with leaders driving change across industries.<\/p>\n Through these discussions, one clear message emerged.<\/p>\n Companies face three main obstacles when driving sustainable transformation:<\/p>\n In the following sections, I will explore how we can leverage Agentic AI<\/strong> to overcome two of these major obstacles: <\/p>\n The first step in any sustainable roadmap is to build the reporting foundation.<\/p>\n Companies must measure and publish their current environmental footprint before taking action.<\/p>\n<\/blockquote>\n For example, ESG reporting communicates a company\u2019s environmental performance (E)<\/strong>, social responsibility (S)<\/strong>, and governance structures\u2019\u00a0<\/strong>strength (G)<\/strong><\/span>.<\/p>\n Let\u2019s start by tackling the problem of data preparation.<\/p>\n However, many companies face significant challenges right from the start, beginning with data collection<\/strong>.<\/p>\n In a previous article, I introduced the concept of Life Cycle Assessment<\/a> (LCA) \u2014 a method for evaluating a product\u2019s environmental impacts from raw material extraction to disposal.<\/p>\n This requires a complex data pipeline to connect to multiple systems, extract raw data, process it and store it in a data warehouse.<\/p>\n These pipelines serve to generate reports and provide harmonised data sources for analytics and business teams.<\/p>\n How can we help non-technical teams navigate this complex landscape?<\/p>\n<\/blockquote>\n In LogiGreen<\/a>, we explore the usage of an AI Agent for text-to-SQL applications.<\/p>\n The great added value is that business and operational teams no longer rely on analytics experts to build tailored solutions.<\/p>\n As a Supply Chain Engineer myself, I understand the frustration of operations managers who must create support tickets just to extract data or calculate a new indicator.<\/p>\n With this AI agent, we provide an Analytics-as-a-Service experience for all users, allowing them to formulate their demand in plain English.<\/p>\n For instance, we help reporting teams build specific prompts to collect data from multiple tables to feed a report.<\/p>\n \u201cPlease generate a table showing the sum of CO\u2082 emissions per day for all deliveries from warehouse XXX.\u201d<\/p>\n<\/blockquote>\n For more information on how I implemented this agent, check this article<\/a> Automate Supply Chain Analytics Workflows with AI Agents using\u00a0n8n | Towards Data Science Even after collecting the data, companies face another challenge: generating the report in the required formats<\/strong>.<\/p>\n In Europe, the new Corporate Sustainability Reporting Directive (CSRD)<\/strong> provides a framework for companies to disclose their environmental, social, and governance impacts.<\/p>\n Under CSRD, companies must submit structured reports in XHTML format<\/strong>.<\/p>\n This document, enriched with detailed ESG taxonomies<\/strong>, requires a process that can be highly technical and prone to errors, especially for companies with low data maturity.<\/p>\n Therefore, we have experimented with using an AI Agent to automatically audit the report and provide a summary to non-technical users.<\/p>\n How does it work?<\/p>\n<\/blockquote>\n Users send their report by Email.<\/strong><\/p>\n The endpoint automatically downloads the attached file, performs an audit of the content and format, searching for errors or missing values.<\/p>\n The results are then sent to an AI Agent, which generates a clear summary of the audit in English.<\/p>\n The agent sends a report back to the sender<\/strong>.<\/p>\n We have developed a fully automated service to audit reports created by sustainability consultants (our customer is a consultancy firm)<\/em> that anyone can use without requiring technical skills.<\/p>\n Interested in implementing a similar solution?<\/p>\n<\/blockquote>\n I built this project using the no-code platform n8n.<\/span><\/p>\n You can find the ready-to-deploy template in\u00a0<\/span>my n8n creator profile.<\/a> <\/p>\n Now that we have explored solutions for reporting, we can move on to the core of green transformations: designing and implementing sustainable initiatives.<\/strong> <\/p>\n My focus over the last two years has been on building analytics products, including web applications, APIs and automated workflows.<\/p>\n What is a sustainability roadmap?<\/p>\n<\/blockquote>\n In my previous experience, it often started with a push from top management.<\/p>\n For example, leadership would ask the supply chain department to measure the company\u2019s CO\u2082 emissions for the baseline year of 2021.<\/p>\n I was responsible for estimating the Scope 3 emissions<\/strong> of the distribution chain.<\/p>\n This is why I implemented the methodology presented in the article linked above.<\/p>\n Once a baseline is established, a reduction target<\/strong> is defined with a clear deadline.<\/p>\n For instance, your management can commit to a 30% reduction by 2030.<\/p>\n The role of the supply chain department is then to design and implement initiatives that reduce CO2 emissions.<\/p>\n In the example above, the company reaches a 30% reduction by year N through initiatives across manufacturing, logistics, retail operations and carbon offsetting.<\/p>\n To support this journey, we develop analytics products that simulate the impact of different initiatives, helping teams to design optimal sustainability strategies.<\/p>\n So far, the products have been in the form of web applications with a user interface and a backend connected to their data sources.<\/p>\n Each module provides key insights to support operational decision-making.<\/p>\n \u201cBased on the outputs, we could achieve a 32% CO\u2082 emissions reduction by relocating our factory from Brazil to the USA.\u201d<\/p>\n<\/blockquote>\n However, for an audience unfamiliar with data analytics, interacting with these applications can still feel overwhelming.<\/p>\n How can we use AI agents to better support these users?<\/p>\n<\/blockquote>\n We are now evolving these solutions by embedding autonomous AI agents that interact directly with analytics models and tools through API endpoints.<\/p>\n These agents are designed to guide non-technical users<\/strong> through the entire journey, starting from a simple question:<\/p>\n \u201cHow can I reduce the CO\u2082 emissions of my transportation network?\u201d<\/em><\/p>\n<\/blockquote>\n The AI agent then takes charge of:<\/p>\n The user doesn\u2019t need to understand how the backend works. \u201cImplement Solution XXX with an investment budget of YYY euros to achieve a CO\u2082 emissions reduction of ZZZ tons CO\u2082eq.\u201d<\/em><\/p>\n<\/blockquote>\n By combining optimisation models, APIS, and AI-driven guidance, we offer an Analytics-as-a-Service experience.<\/p>\n We want to make sustainability analytics accessible to all teams, not just technical experts.<\/p>\n Before closing, a word about minimising the environmental footprint of the solutions we develop.<\/p>\n We are fully aware of the environmental impacts of using LLMs.<\/p>\n Therefore, the core of our products remains built on deterministic optimisation models<\/strong>, carefully designed by us<\/strong>.<\/p>\n Large Language Models (LLMS) are used only when they provide real added value, primarily to simplify user interaction or automate non-critical tasks.<\/p>\n This allows us to:<\/p>\n In short, we are committed to building solutions that are sustainable by their design.<\/p>\n For me, AI agents are becoming powerful allies in helping our customers accelerate their sustainability roadmaps.<\/p>\n As I interact with a non-technical target audience, this is a competitive advantage, as it allows me to provide Analytics-as-a-Service solutions that empower operational teams.<\/p>\n This simplifies one of the biggest obstacles companies face when starting their green transformation.<\/p>\n By communicating insights in plain language<\/strong> and guiding users through their journey, AI agents help <\/strong>bridge the gap between data-driven solutions and operational execution.<\/p>\n Let\u2019s connect on\u00a0Linkedin<\/a>\u00a0and\u00a0Twitter<\/a>; I am a Supply Chain Engineer using data analytics to improve\u00a0Logistics<\/a>\u00a0operations and reduce costs.<\/p>\n For consulting or advice on analytics and sustainable\u00a0Supply Chain<\/a>\u00a0transformation, feel free to contact me via\u00a0Logigreen Consulting<\/a>.<\/p>\n Samir Saci | Data Science & Productivity<\/strong> The post AI Agents for a More Sustainable World<\/a> appeared first on Towards Data Science<\/a>.<\/p>\n<\/div>\n\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-160.png?ssl=1\")
Obstacles for Green Transformations of Companies<\/h2>\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-159-1024x576.png?resize=1024%2C576&ssl=1\")
\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-161.png?ssl=1\")
\n
Solving Reporting Challenges with AI Agents<\/h2>\n
\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-162.png?ssl=1\")
Issue 1: Data Collection and Processing<\/h3>\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-163.png?ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-164.png?ssl=1\")
\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-165-1024x288.png?resize=1024%2C288&ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-166-1024x769.png?resize=1024%2C769&ssl=1\")
\n
![\"\ud83d\udc47\"](\"https:\/\/i0.wp.com\/s.w.org\/images\/core\/emoji\/15.0.3\/72x72\/1f447.png?ssl=1\")
.<\/p>\n![\"\u2197\"](\"https:\/\/i0.wp.com\/s.w.org\/images\/core\/emoji\/15.0.3\/72x72\/2197.png?ssl=1\")
<\/a><\/p>\nIssue 2: Reporting Format<\/h3>\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-167-1024x691.png?resize=1024%2C691&ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-168-1024x434.png?resize=1024%2C434&ssl=1\")
\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-169-1024x228.png?resize=1024%2C228&ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-170-1024x268.png?resize=1024%2C268&ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-171-1024x637.png?resize=1024%2C637&ssl=1\")
<\/figure>\n\n
Agentic AI for Supply Chain Analytics Products<\/h2>\n
Analytics Products for Sustainability<\/h3>\n
\n
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-182.png?ssl=1\")
<\/a>![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-183.png?ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/image-184.png?ssl=1\")
![\"\"](\"https:\/\/i0.wp.com\/contributor.insightmediagroup.io\/wp-content\/uploads\/2025\/04\/temp.gif?ssl=1\")
\n
\n
Agentic AI for Analytics Products<\/h3>\n
\n
\n
They receive a direct, business-oriented output like:<\/p>\n\n
Conclusion<\/h2>\n
Using AI Responsibly<\/h3>\n
\n
AI Agents are a game changer for Supply Chain Analytics<\/h3>\n
About Me<\/h1>\n
A technical blog focusing on Data Science, Personal Productivity, Automation, Operations Research and Sustainable\u2026<\/em>samirsaci.com<\/a><\/p>\n