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?

Made this with Astra in about 20 minutes. Cost $6 in API tokens (could probably have saved a few bucks by being more specific in the first prompt.) https://drive.google.com/file/d/1tfVEzXuTfaQZO2OlR3C7f8i2PN7GFlew/view?usp=sharing

Hi All, Has anyone set up both inbound and outbound calling for their agent? If so, how is that handled, in the prompt or through some other manner? Use case: inbound calls classify caller as prospect, current client, vendor/supplier, field technician or urgent caller and then routes call to proper workflow (get info, take message, schedule appt., forward call, etc.), updates crm records etc. If field technician, records info on job status, updates job and creates task list. Outbound: calls suppliers back, makes call based on tasks created by field technician such as calls supplier to place order, calls sub contractor to schedule work, etc.

I think one of the biggest problems contractors deal with is information from a bunch of different places. When clients sends an email, a sub texts an update, a PM gets a phone call, someone uploads a revised drawing, etc. The PM has to remember what changed, update multiple systems, create tasks, chase people for updates It doesn't sound like a huge problem on its own, but across multiple projects it adds up to hours of admin every week. This is where I think AI could be really useful. Not replacing the PM, but by pulling information together, spots what changed, creates the necessary tasks, and flags anything that needs a human decision. Curious, how are you guys currently handling this? Are you still moving information between systems manually?

Hi everyone, great to be here! I'm Craig and I've been a Contracts Director for a supply and installation company for the past 10 years. I’m joining this community because I really want to connect with like-minded construction professionals and draw on your real-world experiences to help improve my current processes. My number one goal right now is streamlining. I'm specifically looking for new, highly efficient ways of tracking projects from start to finish. Currently, my main tech stack consists of G Suite and Salesforce, but I’m incredibly interested in exploring how to integrate AI into my workflows to save time and reduce friction. If anyone has successfully brought AI into their project management, or has any favorite integrations/workflows that play nice with Salesforce and G Suite, I would absolutely love to hear about them! Looking forward to learning from you all and sharing what I know along the way. What is everyone else using to track their projects right now?