A single virtual microscopy platform
Slides analysed one at a time, and images too large for the tools already in use.
We use AI in the development of every project and integrate machine learning models into the software we build: computer vision, speech-to-text, classification.
How does dotenv use artificial intelligence?
In our work, we use AI on every project: to read documentation and requirements and to support the developers while they write the code. And, of course, in the software we build, to recognise images, transcribe and translate audio, classify text and content. Client data only passes through dotenv’s private AI services.
We use AI assistants on every project. Architecture choices stay with the team, and every release has an owner.
AI extracts and structures requirements from technical documentation and meeting transcripts.
The developers work with AI assistants while they write the code. dotenv answers for the code we release.
It only passes through dotenv’s private AI services, never through external AI services.
With AI, we automate repetitive checks on text, audio and images. The model makes the first pass, the person validates the doubtful cases (human-in-the-loop).
Image analysis, very high resolution included: the model detects the items to check and sends them to whoever validates them.
Transcription of meetings and talks, live or from a recording, with noise reduction and delivery of the text to the participants. It can be installed on-premise: the audio does not leave the client’s servers.
Multilingual translation during meetings, webinars and talks.
Automatic classification of text, images and video: the model decides the clear cases, blocks the ones outside policy and forwards the doubtful ones to a person, with the detail of the analysis.
The model is a component of the software: the results go into the ERP, the CRM or the platform already in use.
We build AI agents inside the systems you already use. They read the documents that come in, such as a supplier invoice, check them against the ERP and prepare the work: a posting, a reply, an exception with the documents side by side.
For an engineering company in Emilia-Romagna the agent checks about a hundred invoices a day against orders and delivery notes. A person always approves the posting.
And what about copyright? The Italian law on artificial intelligence, passed in 2025, says that code written with the help of AI can be protected, if it is the result of a person’s intellectual work. The code we write for you is yours, with the documentation and the environments.
Software with AI inside has to comply with the AI Act, the European regulation on artificial intelligence. The transparency rules apply from 2 August 2026: whoever talks to a chatbot has to be informed that they are talking to an AI system, unless it is obvious, and in software that is an interface choice. The rules on high-risk systems, after the AI Omnibus, apply from 2 December 2027, and from 2 August 2028 for AI inside regulated products such as machinery, toys and lifts.
In Italy, since 30 September 2026, Legislative Decree 160 of 2026 is also in force, aligning Italian rules with the AI Act on civil and criminal liability. That is why, when we build software with AI, we define with you where the model runs and where the data resides, which decisions of the system are recorded (logs and traceability) and which deliverables we hand over at the end of the project.
No. It only goes through dotenv’s private AI services, never through external ones.
Yes, on every project: the assistants work alongside whoever writes the code. dotenv answers for the code we release.
It depends on the data: on dotenv’s private AI services, or on-premise, on the client’s servers, when the data must not leave.
With a call, free of charge. Then a visit to your site, to see how you work today and where AI can help.
Slides analysed one at a time, and images too large for the tools already in use.
Hand-written transcripts lost details, and whoever wrote them missed the meeting.
Every listing was read by a person before it could go live.
We bring AI into your software.