I've been experimenting with some different architectures for a construction site diary. If you aren't familiar with the concept, the site diary is one of the most important construction tools. You basically document everything that happens on site: who did what and how much work you got done each day. Then you use the data to feed your project control system. It also makes incredibly powerful evidence for any construction claims In this video I outlined a simple architecture using Airtable as the database, Claude and Claude dispatch for updating the diary, and WhatsApp for tracking project correspondence and tasks

Been heads down building out our full back-office automation stack at Ferguson Brothers and figured I'd share what's actually running (and what's still in progress). The three streams I'm working on: Stream 1 — Field time cards → productivity metrics Crew submits time cards in the field → routes into Notion → mapped against our cost code unit table → surfaces productivity rates by trade/task. Goal is to know our actual labour productivity so I can estimate from real numbers, not guesswork. Stream 2 — Billable receipts → job costing Any receipt that belongs on a job goes through a shared Google Drive folder structure (one folder per job) → automatically routed into JobTread as a cost → tagged and coded → shows up in the budget instantly. No more manual entry at end of week. Stream 3 — Overhead receipts → QBO direct Company expenses (materials, tools, subs that aren't job-specific) bypass JobTread and go straight to QuickBooks. Keeps the books clean without cluttering job records. The backbone of all three is Claude + JobTread MCP — Claude has live read/write access to JobTread so I can query job data, build estimates, review budgets, and push records without switching screens. Still building but the architecture is pretty much locked. Happy to go deeper on any of it. What are you building? (written with the help, guidance and tutelage of Claude).

Hey Everybody A knew month so I thought I’d start a new welcome thread. Please comment and introduce yourself. Let me know what you are trying to achieve and if you have any questions about the resources. If you click on the “Classroom” tab you’ll get access to all the resources. My goal in June is to keep growing my consulting business and focus on re-building my construction project management course. The original is around 9 hours, but the new one I want to be around 30 hours and cover a few more important topics like software, AI and personal skills. Let me know if you have any questions!

"WhatsApp is the most successful construction technology tool ever built." — Prakash Senghani, CEO of Navatech https://www.instagram.com/p/DZXQ8rLFaij/

AI is getting really good. Every day I’m blown away by what you can do in Claude. If you aren't getting good results from it, I believe you are most likely doing one of two things wrong: 1. Insufficient context 2. Poor direction Most people drastically underestimate how much background information you need to do a task well. Writing a scope of work? You need the drawings, project specifications, previous templates, package register and a list of previous variations from past projects. Then you need to define exactly how to do it. What goes into each section, how to populate the pricing schedule, systematically check that all head-contract requirements are transferred to the sub-contractor. Generic AI is generic. It doesn't know construction process, and it knows nothing about your business — your rates, your subbies, your contract positions, how you run a job. An AI Operating System solves this problem. This week, I'll cover what it is, the parts and how to build it. Check out ContractorOS. We have built most of this for you. Pre-built skills, the business brain structure and weekly calls to help you implement it. Purpose-built AI workflows you download and install. We run weekly workshops and offer unlimited one-on-one tech support to ensure you get the most out of AI. What an AI operating system actually is A system that lets you get genuinely useful work out of AI — not a chatbot you ask questions. Out of the box, AI has three limits: it's generic, it doesn't know the construction process, and it has none of your business background. The fix is two things: give it the right process (a workflow) and the right data (context). Fundamentally, an AI OS is data + workflows. Everything else is plumbing to serve those two. One mindset shift before the parts: use AI as a data transformation tool, not a coworker. It doesn't think like a senior estimator. It moves data you already have into the shape you need.