AI back office for remodelers: connect Claude to JobTread for proposals, vendor bills and job-close audits
Element Design Build
What they did with AI
Element Design Build, an eight-person design-build remodeler in Hudson, Ohio, uses Anthropic's Claude as the link between its existing software: JobTread for project management and job costing, Fireflies for call transcripts, and Microsoft 365. Owner Vlatko Demrovski records prospect calls and consultations with Fireflies, then has Claude summarize them and help prepare JobTread proposals from templates and historical job costs; he says proposals that took 60 to 90 minutes now take 10 to 15, and a $150,000 kitchen estimate that took two days often takes about three hours. On the accounting side, an AI agent helps input vendor bills, match purchase orders and budget line items, and support reconciliation; job-close audits now happen on every job, and commission calculations that took a full day are done in under an hour with an audit trail. Claude also drafts schedules from the company's actual task durations. Element grew from $3.74 million (2024) to $3.92 million (2025) with the same headcount, which Demrovski largely credits to this setup. He reviews every output ("I read every single word") and tests spreadsheet instructions on one row first. Figures are owner-reported in Qualified Remodeler's 2026 Fred Case Award profile.
Related use cases
AI for plumbing and HVAC back office: Claude-built pricing calculators, payroll workbooks and automatic install jobs
Blanton & Sons (Adam Grubb, GM; Charleston, SC area)
Blanton & Sons, a family-owned plumbing and HVAC company in the Charleston, South Carolina area, runs on ServiceTitan, and general manager Adam Grubb (a former plumber) automates every back-office process he can. He used Claude and ChatGPT to build his own tools: a mobile pricing calculator where a tech enters equipment cost, material cost, target margin and commission and gets a price plus a range of acceptable prices, a reverse version that shows management the margin and commission a quoted price implies, and payroll workbooks that handle South Carolina's overtime-on-commission math. With an outside AI shop he built a workflow that takes a job a tech marks "perform later," builds the install job in ServiceTitan and sends the purchase order, which replaced the install coordinator's paperwork; that employee now spot-checks the automation and spends her time with customers. Techs use ServiceTitan's Atlas assistant and ChatGPT for troubleshooting and manuals, and a vendor tool called Buck AI assigns calls on the dispatch board by tech skills, area and schedule. Grubb says dispatch "used to be an all-day job" and is now weekly capacity management. He outsources anything with legal exposure, such as payroll automation. No figures beyond his own descriptions.
AI agent for remodeling project management: Nash Build's super talks to schedules, selections and subs
Nash Build
Qualified Remodeler profiled Milan Vladic, Executive Superintendent at Nashville-based Nash Build, who built an AI agent connected to the company's email, schedules, Slack and project-management software. Field staff can ask it what tile or trim finish was selected for a job, and each project's Slack channel gives it the context of which job is being discussed. The article says it can email painters room-by-room finish schedules, send subcontractors advance notice before their start date, check weather against project schedules to flag possible delays, and summarize long email chains and past project decisions. When someone builds an estimate with the agent, it can write up the steps as a reusable "estimating skill." The article gives no time or dollar results, does not name the AI model behind Nash Build's agent, and notes that outputs still need human review. It also profiles North Shore Masonry near Chicago, whose COO Zac O'Hara says field staff dump walkaround transcripts and photos into AI to produce bid requests in the company's format, with agents limited to drafting emails rather than sending them.
AI agents for a large remodeler's back office: AP processing, vendor reconciliation and job-cost syncs
Neil Kelly Company
Neil Kelly Company, an 80-year-old design-build remodeler in Portland, Oregon, now runs about 30 background AI agents, according to Jeremy Wood, its senior director of IT, on JobTread's Builder Stories podcast. They check estimates against scopes of work, process accounts payable, reconcile vendor invoices (including pulling invoices from a supplier portal), and sync new CRM opportunities and Sage Intacct job costs into JobTread twice a day. Wood says the AI writes and tests ordinary scheduled data pipelines rather than guessing each time, so numbers like job costs are deterministic, and an AP clerk reviews what the agents surface. He also had AI agents grade construction software against a requirements rubric, then set up a JobTread test in an afternoon with a handful of jobs whose job costing he says reconciled to the penny against Intacct. Employees started with ChatGPT before the company built an agent layer; he advises small shops to begin read-only (for example a morning email summary) and to use company accounts that don't train on their data. These are the IT director's own statements in a podcast hosted by JobTread's CEO, with no audited results.