for sustainability weakens, the need for long-term sustainable practices has never been more critical.
How can we use analytics, boosted by agentic AI, to support companies in their green transformation?
For years, the focus of my blog was always on using Supply Chain Analytics methodologies and tools to solve specific problems.
At LogiGreen, the startup I founded, we deploy these analytics solutions to help retailers, manufacturers, and logistics companies meet their sustainability targets.
In this article, I will demonstrate how we can supercharge these existing solutions with AI agents.
The objective is to make it easier and faster for companies to implement Sustainability initiatives across their supply chains.
Obstacles for Green Transformations of Companies
As political and financial pressures shift focus away from sustainability, making the green transformation easier and more accessible has never been more urgent.
Last week, I attended the global ChangeNOW conference, held in my hometown, Paris.
This conference brought together innovators, entrepreneurs and decision-makers committed to building a better future, despite the challenging context.
It was an excellent opportunity to meet some of my readers and connect with leaders driving change across industries.
Through these discussions, one clear message emerged.
Companies face three main obstacles when driving sustainable transformation:
- A lack of visibility on operational processes,
- The complexity of sustainability reporting requirements,
- The challenge of designing and implementing initiatives across the value chain.
In the following sections, I will explore how we can leverage Agentic AI to overcome two of these major obstacles:
- Improving reporting to respect the regulations
- Accelerating the design and execution of sustainable initiatives
Solving Reporting Challenges with AI Agents
The first step in any sustainable roadmap is to build the reporting foundation.
Companies must measure and publish their current environmental footprint before taking action.
For example, ESG reporting communicates a company’s environmental performance (E), social responsibility (S), and governance structures’ strength (G).
Let’s start by tackling the problem of data preparation.
Issue 1: Data Collection and Processing
However, many companies face significant challenges right from the start, beginning with data collection.
In a previous article, I introduced the concept of Life Cycle Assessment (LCA) — a method for evaluating a product’s environmental impacts from raw material extraction to disposal.
This requires a complex data pipeline to connect to multiple systems, extract raw data, process it and store it in a data warehouse.
These pipelines serve to generate reports and provide harmonised data sources for analytics and business teams.
How can we help non-technical teams navigate this complex landscape?
In LogiGreen, we explore the usage of an AI Agent for text-to-SQL applications.
The great added value is that business and operational teams no longer rely on analytics experts to build tailored solutions.
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.
With this AI agent, we provide an Analytics-as-a-Service experience for all users, allowing them to formulate their demand in plain English.
For instance, we help reporting teams build specific prompts to collect data from multiple tables to feed a report.
“Please generate a table showing the sum of CO₂ emissions per day for all deliveries from warehouse XXX.”
For more information on how I implemented this agent, check this article 👇.
Automate Supply Chain Analytics Workflows with AI Agents using n8n | Towards Data Science↗
Issue 2: Reporting Format
Even after collecting the data, companies face another challenge: generating the report in the required formats.
In Europe, the new Corporate Sustainability Reporting Directive (CSRD) provides a framework for companies to disclose their environmental, social, and governance impacts.
Under CSRD, companies must submit structured reports in XHTML format.
This document, enriched with detailed ESG taxonomies, requires a process that can be highly technical and prone to errors, especially for companies with low data maturity.
Therefore, we have experimented with using an AI Agent to automatically audit the report and provide a summary to non-technical users.
How does it work?
Users send their report by Email.
The endpoint automatically downloads the attached file, performs an audit of the content and format, searching for errors or missing values.
The results are then sent to an AI Agent, which generates a clear summary of the audit in English.
The agent sends a report back to the sender.
We have developed a fully automated service to audit reports created by sustainability consultants (our customer is a consultancy firm) that anyone can use without requiring technical skills.
Interested in implementing a similar solution?
I built this project using the no-code platform n8n.
You can find the ready-to-deploy template in my n8n creator profile.
Now that we have explored solutions for reporting, we can move on to the core of green transformations: designing and implementing sustainable initiatives.
Agentic AI for Supply Chain Analytics Products
Analytics Products for Sustainability
My focus over the last two years has been on building analytics products, including web applications, APIs and automated workflows.
What is a sustainability roadmap?
In my previous experience, it often started with a push from top management.
For example, leadership would ask the supply chain department to measure the company’s CO₂ emissions for the baseline year of 2021.
I was responsible for estimating the Scope 3 emissions of the distribution chain.
This is why I implemented the methodology presented in the article linked above.
Once a baseline is established, a reduction target is defined with a clear deadline.
For instance, your management can commit to a 30% reduction by 2030.
The role of the supply chain department is then to design and implement initiatives that reduce CO2 emissions.
In the example above, the company reaches a 30% reduction by year N through initiatives across manufacturing, logistics, retail operations and carbon offsetting.
To support this journey, we develop analytics products that simulate the impact of different initiatives, helping teams to design optimal sustainability strategies.
So far, the products have been in the form of web applications with a user interface and a backend connected to their data sources.
Each module provides key insights to support operational decision-making.
“Based on the outputs, we could achieve a 32% CO₂ emissions reduction by relocating our factory from Brazil to the USA.”
However, for an audience unfamiliar with data analytics, interacting with these applications can still feel overwhelming.
How can we use AI agents to better support these users?
Agentic AI for Analytics Products
We are now evolving these solutions by embedding autonomous AI agents that interact directly with analytics models and tools through API endpoints.
These agents are designed to guide non-technical users through the entire journey, starting from a simple question:
“How can I reduce the CO₂ emissions of my transportation network?”
The AI agent then takes charge of:
- Formulating the correct queries,
- Connecting to the optimisation models,
- Interpreting the results,
- And providing actionable recommendations.
The user doesn’t need to understand how the backend works.
They receive a direct, business-oriented output like:
“Implement Solution XXX with an investment budget of YYY euros to achieve a CO₂ emissions reduction of ZZZ tons CO₂eq.”
By combining optimisation models, APIS, and AI-driven guidance, we offer an Analytics-as-a-Service experience.
We want to make sustainability analytics accessible to all teams, not just technical experts.
Conclusion
Using AI Responsibly
Before closing, a word about minimising the environmental footprint of the solutions we develop.
We are fully aware of the environmental impacts of using LLMs.
Therefore, the core of our products remains built on deterministic optimisation models, carefully designed by us.
Large Language Models (LLMS) are used only when they provide real added value, primarily to simplify user interaction or automate non-critical tasks.
This allows us to:
- Guarantee robustness and reliability: for the same input, users consistently receive the same output, avoiding stochastic behaviours typical of pure AI models
- Minimise energy consumption: by reducing the number of tokens used in our API calls and optimising every prompt to be as efficient as possible.
In short, we are committed to building solutions that are sustainable by their design.
AI Agents are a game changer for Supply Chain Analytics
For me, AI agents are becoming powerful allies in helping our customers accelerate their sustainability roadmaps.
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.
This simplifies one of the biggest obstacles companies face when starting their green transformation.
By communicating insights in plain language and guiding users through their journey, AI agents help bridge the gap between data-driven solutions and operational execution.
Let’s connect on Linkedin and Twitter; I am a Supply Chain Engineer using data analytics to improve Logistics operations and reduce costs.
For consulting or advice on analytics and sustainable Supply Chain transformation, feel free to contact me via Logigreen Consulting.
