Artificial intelligence for engineering and technical consultancies
Standards, previous calculations, and the report you already wrote for a similar plant — available to the engineer on the next job, in Persian and English.
Request a consult for your consultancy.
How engineering firms use AI
The same research that covers contractors covers design firms. The valuable work is rarely a new model. It is finding the assumption that was already checked.
Standards and codes
An engineer asks which clause applies and gets the passage from the standard you have licensed and stored, not a guess from the open web.
Calculation narratives and reports
The structure of a previous report — scope, assumptions, exclusions — is reused and then rewritten for this client.
Client questions during design
A project assistant answers from the basis of design, the minutes, and the last issued drawing list.
What changed between revisions
Comments, transmittals, and the revision history are summarized before someone rewrites a section that was already agreed.
Juniors beside the archive
A new engineer can ask how the firm usually treats a detail, and the answer cites a real project rather than a generic textbook.
Client confidentiality
One client's files are not retrieved for another client's question. Access follows the project and the role.
What the AEC research shows
Design firms sit in the same surveys as contractors, and the same gap between pilot and practice shows up.
construction productivity rose about 10% from 2000 to 2022, against about 90% in manufacturing — the gap AI is being asked to narrow
McKinsey, How AI is reshaping the future of the AEC industry
of RICS respondents use AI across multiple processes. Most are still at no use or a pilot
RICS, Artificial Intelligence in Construction, 2025
of construction and engineering businesses in the Deloitte Asia-Pacific sample use AI or machine learning
Deloitte and Autodesk, State of Digital Adoption, 2026
global construction output in 2025, the market these firms design and supervise
McKinsey, citing GlobalData Construction Intelligence Center, accessed 2026
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 firm's method lives in old reports. Convex makes that method searchable without training a model on the client's data.
Several models
Pick the model for the task from several leading models, in one place.
Specialized assistants
Assistants for standards lookup, report drafting, and project questions, limited to the files that project may see.
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 discipline
Pick structural, process, or MEP. Bring the standards you already own and two finished reports.