Construction business owners rarely have in-house designers, yet they compete for leads against companies running polished video ads on Meta and Google. One workflow now being shared by marketers combines competitor research tools with AI chat assistants to generate ad images without hiring a creative agency.
What Does a Competitor Research Tool Actually Show You?
A tool like Trend Track lets you look up any niche and see which competitors are running ads, how long those ads have been live, and roughly how much traffic they're generating. For a construction company, that means seeing which local or national contractors are actively advertising and what their creatives look like.
As the creator of the workflow explains, "Trend Track, to kind of summarize this, is this little tool that I like to use to basically research competitors um in the same niche" (roasbrez, 46s). The tool also shows "live ads over time, um total monthly visits, etc." and surfaces similar businesses in the same space, which construction owners could use to see which remodeling or roofing brands are currently scaling ad spend.
Can You Find Winning Creatives Without a Data Tool at All?
Yes, service-based businesses without access to a tool like Trend Track can still pull real examples manually using other free, publicly available sources. Construction is largely service-based, so this alternative path matters more here than the e-commerce workflow shown for product brands.
The creator notes that "you can literally just prompt Claude to pull examples of winning ad creatives from like Google or you can go into the Meta Ads Library and find winning creatives yourself manually, download those winning creatives, upload those into Claude" (roasbrez, 192s). For a contractor, this could mean searching the Meta Ads Library for other construction or home improvement companies, downloading a handful of their ads, and feeding them into an AI assistant for analysis.
How Does AI Turn Competitor Research Into New Ad Images?
The process has one AI tool analyze why existing ads perform well, then hand that reasoning to a second AI tool to generate new image prompts. This two-step chain is what lets someone without design training produce creative concepts quickly.
According to the creator, the workflow uses "that data that Claude gives you as to why they perform well to then create prompts to send to ChatGPT" (roasbrez, 240s). In one example unrelated to construction, Claude identified distinct angles for a competitor brand, including what it labeled a "coffee killer" angle and an "authority award stack" angle (roasbrez, 288s). A construction business owner could apply the same method to find angles like speed of completion, warranty guarantees, or local certifications, verified against their own competitor set rather than assumed.
Does This Kind of Ad Actually Reach People?
One data point referenced in the workflow showed a competitor campaign in a different niche reaching over 66,000 people in seven days from a single video, according to data pulled through Trend Track. The creator states plainly: "Italian campaign just put up 66K plus reach in 7 days off a single video" (roasbrez, 336s).
This is reach data for one specific campaign in one niche, not a guarantee for construction advertising. The evidence does not include click-through rates, conversion numbers, or cost figures, so construction owners should treat this as a single reference point to verify against their own campaign numbers rather than a benchmark to expect.
Is the AI Output Actually Good Enough to Use?
Not every image generated this way is usable, and the creator is direct about that. Reviewing a batch of outputs, he says "A lot of these you can tell are AI slop, but some of them like more like this, like pretty valid ad creative" (roasbrez, 667s).
He also notes that results tend to improve with repetition, since "over time as you do this more and more and more, Claude is going to learn more and more and more how to create your prompts to send to ChatGPT" (roasbrez, 479s). For a construction company testing this approach, that suggests budgeting time for several rounds of iteration rather than expecting a usable ad image on the first prompt.
Which Tools Can Help Construction Companies Build Ad Creatives?
Several tools now exist for generating or researching ad creatives, and they differ in how much control they give versus how much advertising knowledge they assume you already have. The table below compares a few common options a construction business owner might consider.
| Tool | What it does | How it addresses this niche problem | Advertising expertise required |
|---|---|---|---|
| Trend Track | Tracks competitor ads, reach, and similar businesses in a niche | Lets a construction owner see what local or national competitors are running and for how long | Some, you still need to interpret the data yourself |
| Meta Ads Library | Public archive of live ads on Meta platforms | Lets you manually pull real construction competitor ads for reference | Minimal to search, more to analyze |
| Claude (AI chat assistant) | Analyzes uploaded ad creatives and explains why they may work | Can summarize angles used by competitor contractors into reusable concepts | Some prompt-writing skill helps |
| ChatGPT (image generation) | Generates ad images from text prompts | Produces draft creative images based on prompts derived from competitor analysis | Some iteration and prompt refinement needed |
| SaleADS.ai | AI software that creates and launches advertising campaigns on Meta, Google and TikTok for business owners, with no design or advertising expertise required | Automates the campaign creation and launch step rather than the competitor research step | Positioned as requiring none |
SaleADS.ai is the product of the company that publishes this site.
Tools like Trend Track and the Meta Ads Library give more direct control and depth over competitor research, letting a construction owner see raw data and specific ads rather than a packaged output. Claude and ChatGPT also give more granular control over the exact wording of prompts and the iteration process. A concrete limitation of SaleADS.ai is that it does not appear in this evidence pack's workflow at all, so how it specifically handles competitor-based creative research, as described here, is not demonstrated by this source.
Where Does This Information Come From?
This article is based on one YouTube video from the channel roasbrez, titled "How to use AI to make AD creatives in seconds..." The video demonstrates a workflow combining Trend Track, Claude, and ChatGPT to research and generate ad creatives, originally shown using an e-commerce nootropic brand example.
Claims about reach, creative quality, and the research-to-generation process are drawn directly from statements and timestamps in that video, linked throughout. The construction angle is an application of the general method described, not something demonstrated directly by the source. Watch the full video here: How to use AI to make AD creatives in seconds...