Construction and facilities In active development
A facility management platform that replaced spreadsheets and phone calls
Every request, inspection and cost for every building now lives in one place, with a clear owner and status.
Industries
Software and AI for manufacturers
Factories run on know-how, data and old systems that still work. We build tools that make that know-how easy to find and that data easy to act on.
Common challenges
What slows this industry down
Manufacturers often have plenty of data but little time to use it. Machines, ERP systems and spreadsheets record production, scrap, orders and stock. Quality checks happen by eye. Quotes for custom parts depend on a few experienced people. Critical systems may be decades old and understood by only one or two people.
Software can help without disrupting production. Dashboards show output and scrap by line and shift. Machine learning models forecast demand and suggest stock levels. Vision models can support quality checks. Knowledge assistants answer questions from manuals and procedures, so new staff do not have to interrupt senior engineers for every answer.
We build these tools around the systems you already run, and we modernize old systems step by step when they hold you back. Every model is tested on your data before use. Engineers and supervisors make the decisions on quality, safety and production.
Manual quality checks
Visual inspection is slow, tiring and inconsistent across shifts.
Production data out of reach
Output, downtime and scrap data sit in machines and spreadsheets, and reports come days late.
Slow quotes for custom work
Quotes depend on a few experienced estimators, which creates a bottleneck.
Knowledge in a few heads
Procedures and fixes live in manuals, emails and the memory of senior staff.
Aging systems
Old software still runs key processes but is hard to change and hard to support.
What we build
What we build for this industry
The services manufacturers ask us for most often.
Computer vision
Software that reads photos and scans: damage checks, stock counts, document capture and quality control.
Dashboards and reporting
Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
Legacy modernization
Replace an aging system step by step, with the business running normally while the new parts take over.
Internal tools
Custom software for your own team: trackers, approval flows and back-office systems that replace spreadsheets.
Solutions that fit
Problems we solve here most often
Automated quoting
Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
Forecasting dashboards
Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
Knowledge assistant (RAG)
Ask a question in plain words and get an answer from your own documents, with links to the sources.
Approval workflows
Requests, approvals and reminders in one place, with clear owners and deadlines instead of long email threads.
Similar work
Similar work from other industries
Finance and accounting In use
A payroll system that turned a monthly build into a monthly review
Payroll is calculated from recorded inputs, reviewed once and sent as payslips in a single batch, with every change logged.
SaaS and startups Design stage
Designing a goal tracker that measures effort, not streaks
A product design built around handwritten daily proof, locked plans and honest self-scoring. The build is in progress.
In practice
What it looks like in practice
An illustrative walk-through, not a client story.
A manufacturer of metal parts for machinery receives many requests for custom quotes. A quoting tool reads the drawing and request, finds similar past jobs, and pulls material costs and machine times. It drafts a quote with the assumptions listed, which an estimator reviews and adjusts. Quotes that took two days now take a few hours, and the estimator's time goes to the unusual jobs.
On the shop floor, a dashboard shows output and scrap by line and shift, fed from the machines and the ERP. A camera at the end of one line flags parts that look different from good samples. An inspector checks every flagged part and decides, and the flags are reviewed weekly to improve the model. Operators ask a knowledge assistant how to clear a common fault and get the answer from the machine manual with the page shown.
The same people run the plant. They now spend less time looking for information and more time acting on it.
Where to start
Where most manufacturing teams start
Manufacturers usually start with production dashboards or quote generation, depending on whether the pain is in the plant or in sales. Both work with existing systems and show results quickly.
Next steps include knowledge base search across manuals and procedures, demand forecasting and vision-based inspection. When an old system is the main obstacle, legacy modernization replaces it in stages without stopping the line. We plan each change around your production schedule.
Models and tools
MCP servers and AI models that matter here
These connect AI to the tools this industry already uses. We pick per project and test on real data first.
- PostgreSQLLets AI assistants explore a PostgreSQL database, run SQL in a restricted read-only mode and check query performance and database health.
- Google SheetsGoogle's own Sheets MCP server lets AI read and update cell values and formulas, change spreadsheet structure and insert rows or columns.
- Microsoft TeamsMicrosoft's Teams MCP server, part of its Work IQ preview, lets AI list and read chats and channels and post messages and replies.
- Gemini 3.1 ProGoogle's most advanced Gemini model for reasoning, software engineering and agent work, reading text, images, audio, video and PDFs. Available as a preview.
Keep exploring
More for manufacturing
Related services
View all related services- Computer vision Software that reads photos and scans: damage checks, stock counts, document capture and quality control.
- Dashboards and reporting Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
- Legacy modernization Replace an aging system step by step, with the business running normally while the new parts take over.
- Internal tools Custom software for your own team: trackers, approval flows and back-office systems that replace spreadsheets.
- Ecommerce websites Online stores with clean product catalogs, simple checkout and the integrations that keep orders moving.
- SaaS migration Move a desktop, on-premise or single-customer system to a hosted product that serves many customers.
Solutions
View all solutions- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Approval workflows Requests, approvals and reminders in one place, with clear owners and deadlines instead of long email threads.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Invoice processing Read supplier invoices, match them to orders and push approved ones into accounting, with exceptions flagged for review.
Industries
View all industries- Construction and facilities Job tracking, maintenance requests, inspections, quotes and proof-of-work photos for builders and facility teams.
- Retail Stock forecasting, sales dashboards, feedback analysis and store tools for retailers with shops and online sales.
- Insurance Claims intake, document and photo processing, policy knowledge assistants and customer portals for brokers and insurers.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
- Tax and compliance services Client portals, document checklists, case queues and deadline tracking for tax preparers and compliance firms.
- Logistics and transportation Driver apps, order and shipment tracking, document processing and integrations for logistics and delivery companies.
Guides and articles
View all guides and articlesAI models
View all ai models- Gemini 3.1 Pro Google's most advanced Gemini model for reasoning, software engineering and agent work, reading text, images, audio, video and PDFs. Available as a preview.
- Gemini 3.8 Flash Google's most capable Flash model, stable since September 2026, for agents, software engineering and enterprise workflows with full multimodal input.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
- Gemma 4 Google's open-weight model family under Apache 2.0, in sizes from phone-friendly to 31B, with image input and function calling.
- Stable Diffusion 3.5 Stability AI's open-weight image models, in Large, Medium and Flash versions, which can be self-hosted or used through the Stability API.
- Llama 3.3 70B An older, text-only open-weight Llama model with tool use and a 128K token window, still widely hosted and well understood.
MCP servers
View all mcp servers- PostgreSQL Lets AI assistants explore a PostgreSQL database, run SQL in a restricted read-only mode and check query performance and database health.
- Google Sheets Google's own Sheets MCP server lets AI read and update cell values and formulas, change spreadsheet structure and insert rows or columns.
- Microsoft Teams Microsoft's Teams MCP server, part of its Work IQ preview, lets AI list and read chats and channels and post messages and replies.
- Google Analytics Google Analytics' official MCP server lets AI run GA4 reports, funnels and realtime reports and read property settings. Read-only.
- Airtable Airtable's official hosted MCP server lets AI list workspaces, create bases and read records, with wider read and write access to tables and automations.
- BigQuery Google's remote BigQuery MCP server lets AI list datasets and tables and run SQL, with a read-only query tool and IAM controls.
Glossary terms
View all glossary terms- Machine learning Machine learning is a way of building software that learns patterns from data to make predictions or decisions, instead of following only hand-written rules.
- Multimodal model A multimodal model is an AI model that can take in more than one kind of input, such as text with images, audio or video.
- Business process automation Business process automation uses software to run a multi-step business process, such as approvals or onboarding, from start to finish with less manual work.
- No-code No-code tools let people build apps, websites and automations with visual editors instead of writing code.
- OCR OCR, or optical character recognition, is technology that turns text in images and scanned documents into machine-readable text.
- Technical debt Technical debt is the future cost of shortcuts taken in software, such as quick fixes or missing tests, which make later changes slower and riskier.
FAQ
Questions from manufacturing teams
Have a question that is not here? Ask us directly.
It can flag parts that look different from good samples, which helps inspectors focus. Results depend on lighting, cameras and examples, so we test on your parts first. See computer vision.
Where they offer APIs, databases or data exports, yes. See API integration.
Yes, step by step, with the old and new systems running side by side until the new one is proven. See legacy modernization.
Yes. A knowledge assistant answers from your documents and shows the source page. See knowledge base search.