Skip to content
Landry Tchouela
FR
All projects
Internship at Intelligence Industrielle · applied AIIn progress

AI Report Reader

AI reads vendor maintenance reports and proposes work orders; a human validates.

Role
Review screens, demo mode, performance and theming, in development driven with an AI agent
Period
November 2026
Team
Intelligence Industrielle product team
Stack
Next.js 16, React 19, TypeScript, Tailwind CSS 4, Generative AI
Private code (Intelligence Industrielle)
Illustration of the principle, with made-up data.
every field points to its page and sentence
Cited
priority comes from explainable rules, not the model
Rules
always validates before export
Human
PDFs, scans and photos, in both languages
FR / EN

Try it

From a pile of reports to a batch of work orders.

Start the reading: reports get sorted. Open one, change a signal and watch the priority recompute; validate, then export. This is the principle with made-up rules and data, not the internal tool.

01The problem

At an industrial client, maintenance vendors send their service reports: PDFs, scans, photos, handwritten notes, in French or English. One person reads them one by one; the backlog grows and urgent recommendations get lost.

02What I built

  1. The review screen: reading the report, the proposed work orders and filing.
  2. A realistic demo mode, with edge cases and reading spread over time.
  3. A reading badge and notifications to follow reports in progress.
  4. Locating citations in the page image when the report is a scan.
  5. Performance, code cleanup and traceability; fixes and much smoother scrolling.

03Architecture

  1. 01DropEmails, .zip, folder
  2. 02AI readingCitations: page and sentence
  3. 03RulesExplainable priority
  4. 04Review and exportA human validates

04Decisions

  1. 1AI locates, rules compute: priority comes from explainable rules, not from the model.
  2. 2Guardrails: a stopped asset or a health and safety risk never comes out as low priority.
  3. 3Every field cites its source, page and sentence, boxed on the document.
  4. 4Québec’s Law 25: the AI notes that a technician was present, never their name.
  5. 5A human always validates before exporting to the maintenance software.

05Where it stands

In progress at Intelligence Industrielle (November 2026). Presented here as in an interview: no client or product name, no internal figures or data; the demo shows the principle with made-up rules and data. Development driven with an AI agent. Happy to go into more detail in an interview.