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
Airtight Revenue, an AI voice receptionist for HVAC shops that answers missed calls, triages emergencies, and texts a booking link. Built on Retell with GPT-4.1 Mini. The part I am proudest of: it is tested like a product. A 43-scenario behavioral QA suite covers core flows, compliance, adversarial jailbreak attempts, and Spanish calls, scored by an LLM judge. Any emergency-scenario failure blocks deploy. The AI-disclosure first line is hardcoded because compliance law is not a place for creativity.
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Can a fully automated, faceless YouTube channel actually run for free?
That question is basically what turned into crank, a terminal AI agent I've been building for myself. It's turned into a full video production system: it writes, renders, voices, captions, and publishes, start to finish, with no editing on my end.
It's currently running from production to upload at:
https://youtube.com/@ecnivs
Not public yet, but it's coming
Built JobTracker AI — because a spreadsheet shouldn't be your job search strategy. 📋➡️🤖
Paste a JD, get an instant fit score against your resume, and see exactly where the gaps are before you hit apply. No more guessing why the callback never came.
Full pipeline tracking (Applied → Interview → Offer), automated follow-up reminders via n8n, and AI-powered parsing that actually reads the JD so you don't have to read it five times.
Built end-to-end — architecture, AI integration, automation, deployed and working. Not a prototype that dies after the demo.
Open to building this (or something like it) for you. DMs open.
Amazing work
My core stack is less "generate pretty pictures" and more "build the pipeline that does the thinking":
n8n — the glue. Great for orchestrating multi-step agent workflows and connecting APIs without writing a service from scratch. Weakness: gets messy fast on complex branching logic, and debugging a broken node chain eats time.
RAG (usually with a vector DB + LangChain-style retrieval) — lets me ground LLM output in actual client data instead of hallucinated generalities. Strength: dramatically improves accuracy for domain-specific asks. Weakness: chunking/retrieval quality is finicky, and a bad embedding setup silently tanks results without throwing an error.
Claude/GPT for reasoning + code — my default for anything needing judgment: analysis writeups, SQL/Python generation, proposal drafting. Strength: fast iteration. Weakness: still needs a human check on numbers — confident-sounding ≠ correct.
Power BI / Tableau — where the AI output actually becomes something a client trusts. AI can shortcut the analysis, but the dashboard is what gets signed off on.
The honest lesson: the "AI" part is maybe 30% of the workflow. The rest is validation, data plumbing, and making the output legible to a non-technical stakeholder.
Silent failures are what I watch closest. I treat an answer as untrusted unless I can show exactly which source text the model read, because fluent output can hide a bad match.
