Artificial intelligence for oil, gas, and energy
Procedures, permits, and the shift log — answered on the network you already trust, in Persian and English.
Request a consult for your operation.
How energy companies use AI
Operators already run predictive maintenance and control systems. The newer gap is the written plant: procedures, incidents, and the answer a new shift supervisor needs at 2 a.m.
Procedures and permits
A technician asks what the procedure requires before a job and gets the current revision, not a photocopy from a binder.
Maintenance knowledge
Failure history, work orders, and the vendor manual are queried together when a unit trips.
Incidents and lessons
Investigation reports stop being a folder nobody reopens. The next similar job can find the lesson.
Contracts and joint-venture files
Commercial teams ask the PSC, the tender, or the partner agreement and get the clause.
Plant networks
Air-gapped deployment, your own model endpoints, and offline licensing when the site has no path to the public internet.
Shift handover and training
New operators learn from the site's own procedures instead of a generic course.
What energy leaders are reporting
Use is already common. Deep change to how the company works is still a minority.
of US energy leaders said their company was using or piloting AI
Honeywell AI in the Energy Industry survey, 300 leaders, March–April 2025
said they were using AI virtual assistants
Honeywell AI in the Energy Industry survey, 2025
named predictive maintenance as a top area of AI impact
Honeywell AI in the Energy Industry survey, 2025
of workers at surveyed energy, resources, and industrials companies now have a sanctioned AI tool, doubled in one year. 23% of those companies are using AI to transform the business
Deloitte, State of AI in Energy, Resources and Industrials
Figures come from the published surveys and case reports named on each card. They describe those samples, not a promise of the same result.
What Convex puts in front of the team
The control system stays where it is. Convex is the layer over procedures, contracts, and the questions people ask of them.
Several models
Pick the model for the task from several leading models, in one place.
Specialized assistants
Assistants for permit-to-work questions, shift reports, and contract lookup, with access limited by role.
A personal assistant
Each person has an assistant tuned to how they work.
Workspace assistants
Shared assistants that keep the company's context for the whole team.
Search over your documents
Answers come from your own procedures, contracts, and records, with the source attached.
Documents out
Word files and images today. CSV export is planned.
A cap per person
Token use is visible per person, and the spend can be exported.
Adoption dashboard
See where AI is actually being used, and where it is not.
Cloud, or entirely on your own infrastructure
The same product. The difference is where the data sits.
Cloud
What is available today, hosted.
- Access to several leading models
- Specialized, personal, and workspace assistants
- Search over the company's documents
- Word documents and images
- Token-use tracking and reports
- Adoption dashboard
On-premise
Full control inside your environment, including a network with no outbound connection.
Everything in Cloud, plus:
- Your own model endpoints
- Offline licensing and payment for a disconnected site
- Assistants and workflows built for your process
Start with one procedure set
A single unit's operating procedures are enough to see whether the answers are citeable.