I did a quick video summarizing my testing and experimenting on it: https://youtu.be/9iOHzkDl5zc?si=4lwFgt46Hae8-Mfy Here are the benchmark results: https://contractoros.build/benchmarks/ Gemini 4 Argon came close to Claude on my construction take-off tests, but struggled with the management work. It scored 52% on my take-off benchmark, compared with 53% for Claude Opus 5.5, across 130 questions from 10 drawing sets. I would treat that as effectively equal. Gemini was stronger at counting items and weaker at measuring lengths and areas. The way you use the model also matters. For drawing questions, the raw Gemini model ranked in the top three. Running it through the Gemini app connected to Google Drive dropped it to 10th. On estimating, procurement and scheduling, it made some basic mistakes: - Changed a quoted 16-week steel lead time to seven weeks. - Used the client sell price, including profit, as the cost budget. - Claimed files were finished when the output folders were empty. My view: promising for reading drawings, but I would keep Claude or ChatGPT for more complex construction tasks. These results used the Gemini app with Google Drive. I have not yet repeated the tests in Google’s Antigravity coding tool.

This has been a big month for me. Last week I became a Dad (super excited but sleep deprived), also feels very wierd calling myself a Dad. So this month I'm in a tiny bit of a holding pattern but I've got two main focuses this month. 1. I want to engage way more on here and restructure the classroom. We've got sample projects, tons and tons of templates and more. I really want to try and get people to use them 2. Rebuild my email newsletter so its genuinely useful for people. I'm planning on breaking each week down into three parts: news updates - what's happened in the last week of construction/AI, inform - some interesting insight or perspective change and work - a new approach or solution to a task. What are your goals for October? Comment them down below!

Curious what everyone’s running. Here’s mine: • JobTread — PM, estimating, budgets, and the file system: plans, drawings, receipts, job docs all live here • QuickBooks — accounting • Notion — business brain / SOPs + cost history • Airtable — Contractor OS data layer • Claude / ChatGPT — the glue. Skills + MCP connectors so I’m not re-entering the same data three times Google Drive is still in there, but honestly it’s redundant — it only exists as a staging spot until I get receipt capture running properly through the agents. Once that’s clean it comes out. What are you running — and what’s sitting in your stack that you know you don’t actually need?

What’s your social media presence like, and have you built any workflows or automations around your content? Curious what people are actually doing here — what’s your presence like, what content works, and have you built or developed any workflows, content automations, scripts, etc. to make it easier?

How to Use AI in Construction Estimating Without Losing Control of the Bid A construction estimate is a commitment: we can build this scope for this price, in this time, from documents we’ve often only had for a couple of weeks. That’s why handing the whole bid to AI and hoping for the best is a terrible idea. I think there are three sensible levels: - Start with risk reduction. Use AI to check your estimate for missed requirements, gaps, double-counting and formula errors. - Use it to structure information. Build requirements and clarifications registers, then review them before they feed into the next step. - Once your data is organised, use it for more of the heavy lifting like assemblies, line-item pricing, subcontractor quote comparisons and submission documents. The important part is keeping human review between each workflow so errors don’t compound. Where are you currently using AI in your estimating process?