In the last couple of months AI players have been releasing their version of what a true agent style interface looks like. Grok Bot, Muse, Dots, Hermes and soon Duet from Anthropic. I went into more details in the video on how each perform and which one will be best for who. My main point is also that these are great for their running around tasks like picking up items that are coming up due in registers, reminders on tasks you promised in a meeting and that ad-hoc admin tasks. Work like extracting trade packages, reviewing contracts and line item pricing all still belong using skills in Claude Cowork or ChatGPT Work. You want reliable results where you know what the AI has done so you can review the output before carrying on. I'm interested in how you all are using these agents and whether it has changed much for the way you work?

Construction accounting and finance is pretty simple, right? You just bill a client more than it costs you to do the work. Track the invoices and expenses. Simple. Wrong. Construction accounting and finance is one of the most confusing topics I’ve dealt with. Retention. Progress claims. Secured and unsecured variations. Cost tracking. Estimating. Corporate overheads. There are so many elements to this topic. So I’ve been trying to research and lay out the entire topic in a simple, step-by-step framework. This week, I’m going through how those pieces fit together, from pricing a job to deciding whether the business can afford another one. As always, it’s structured around News, Inform and Work. Just quickly, I’m looking for some customer feedback on a new product I’m launching. Would love if anybody has the time to fill this out: https://docs.google.com/forms/d/e/1FAIpQLSdILOUFSeoYJRJOfY5g5BHnI8ZLPHcfZhiL78nOE0AFOpRdTQ/viewform?usp=header News Claude Duet: an assistant that keeps working in the background. Anthropic’s new agent runs on its own computer in the cloud. It can prepare email replies, meeting briefs and financial models using your connected apps. I can see this helping contractors keep up with admin while they’re on site. It is currently a US-only research preview for Pro and Max users, through a waitlist, and is designed to ask before sending messages. See how Claude Duet works. Anthropic has filed for an IPO. The company behind Claude filed its public IPO paperwork on 26 October and intends to list on Nasdaq under the ticker ANT. The share price and number of shares are still to be determined. For businesses building workflows around Claude, this makes the company behind the tool worth following too. Read Anthropic’s announcement

For me, it’s poorly prepared bid packages. You get sent hundreds of documents that all say different things. Then you spend 10 hours going through them to work out what the client wants. Unfortunately AI is making it even easier to produce hundreds of pages of junk for someone else to read. What’s yours? What part of working in construction do you wish someone would sort out? I’ve been working on a new product. And yes, this is one of those annoying product research surveys where I ask what your problems are and how I can help. If you’ve got five minutes, I’d really appreciate you filling it out. https://docs.google.com/forms/d/e/1FAIpQLSdILOUFSeoYJRJOfY5g5BHnI8ZLPHcfZhiL78nOE0AFOpRdTQ/viewform?usp=header

You've probably heard some variant of the saying "what gets measured, get's managed" I don't think that's completely right. It should be, "what get's measured and communicated, get's managed" A construction dashboard should help someone make a decision. My recommendation is to start with who will use it and what they need to know. A project team needs upcoming milestones, cost overruns and risks requiring action. A client overseeing several projects may also need a simple scope summary. I would build it around three areas: Cost: Are we forecast to finish within budget? Where are variations accumulating, and when are payments due? Risk: Which risks need attention? How much will our planned treatments reduce their likelihood or impact? Programme: Which milestones are approaching, and where have dates slipped against the original plan? The information behind it needs to be structured and maintained. Build updates into your existing forecasting, payment and reporting processes so the dashboard stays current without duplicating administration. Then use it in your project reviews. If the same question keeps sending you back into a spreadsheet, that information probably belongs on the dashboard.

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.