The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Can a simple 4-step workflow replace hours of manual research?
I’ve been obsessed with hands-off AI systems lately because they don’t just save time, they preserve your mental bandwidth.
Automating web search directly into document generation turns a 30-minute manual research task into an instant, hands-free result.
It’s been a minute since I last built an end-to-end Make scenario, so with some new client intake processes to streamline, this felt like the perfect excuse to jump back in and test out Make's latest AI Web Search modules.
I included a quick breakdown of the scenario setup in the comments.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
Experimented a bit today with Krea and image generation for a case study I’m putting together around AI EarPods connected to OpenAI.
The focus has been on creating fashion-forward product imagery and art directing a world that feels specific to the identity, rather than just generating nice-looking AI images.
The trickiest part has been product consistency. Especially getting the EarPods to actually sit snug in the ear. If you’ve worked through this process, you probably know the struggle 😅
Simply telling AI to “make it fit more snug or in the ear” doesn’t always work. It loves to reinterpret the product every time.
Still experimenting, but getting closer. If anyone has found a good workflow for keeping products consistent across AI-generated shoots, I’d love to hear it!
TOP!
Some quick mockups for Relay, an AI infrastructure platform concept built around model routing, observability, and performance.
Exploring what a mobile command center could look like for teams managing multiple AI models, with a focus on clear data, fast decisions, and a developer-first UX.
Product design, mobile UI, AI tools, and a little systems thinking all in one.
the blue dots and orange blocks pop. did you build this in Framer?
From a 40-Minute Client Call to a Working Interactive Prototype in Hours (5x Faster with AI Agents)
Going from an initial client briefing to an approved wireframe usually takes 3 to 7 days of manual note-taking, layout debates, and generic copy.
In this video, I walk through my exact 3-phase workflow to cut that timeline down to a single afternoon using raw call transcripts and custom AI agent
Descript MCP Workflow
Instead of scrubbing through the timeline manually, I used the Descript MCP with an AI agent to instantly generate accurate YouTube timestamps, description and video titles directly from the project context — killing post-production busywork in seconds.
YouTube Video Link: https://youtu.be/lI3sCyUabHQ
Descript Video: https://share.descript.com/view/7AlW3niOPfx
Descript MCP Session Workflow: https://www.loom.com/share/848564eb31074c43b8f0d2068460e1be (I used Google Antigravity, which doesn't have a shared chat option)
the blue prototype card looks cool