AI agent for remodeling project management: Nash Build's super talks to schedules, selections and subs
Nash Build
What they did with AI
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.
Related use cases
AI back office for remodelers: connect Claude to JobTread for proposals, vendor bills and job-close audits
Element Design Build
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.
AI lead response for a solo electrician: Sloan Electric and Podium's AI Employee save 10+ hours a week
Sloan Electric
Mark Sloan, owner of Sloan Electric and a solo electrical contractor, says in a Podium customer case study that its AI Employee sends a preliminary message to every lead within one or two minutes, so customer conversations start while he is on a job. He says that after entering every material he uses into Podium's price book he can send leads an estimate in about 10 minutes, where before it often took more than a day, and that review requests now go out automatically after each job. He estimates he saves 10 hours a week. Note the source credits the price book and invoicing workflow, not AI, for the faster estimates; the AI Employee is credited with the instant lead response. This is a vendor-published case study with no date on the page, and the figures are Sloan's own.
AI-assisted HVAC diagnostics: a McDonough, GA contractor's in-house software and its 90% drop in callbacks
Absolute Best Air
Absolute Best Air, a residential HVAC company in McDonough, Georgia, says owner David Longino built a proprietary diagnostic and indoor-air-quality system called AI IAQ (patent application pending). The company's website describes software that pulls system and indoor-air-quality measurements into one view so the technician can see patterns, document conditions and explain a repair or replacement recommendation; it says a technician stays in control and the software does not replace judgment. In an Oct 22, 2026 press release the company reports that since deploying it in March 2026 it completes its 151-point inspection in about 30 minutes instead of roughly three hours, cut callbacks and return trips 90% and reached a 99% first-time fix rate. These are company-reported figures from its own release; the release does not describe the underlying model or how the results were measured, and the company says its continuous-monitoring hardware is still in development.