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
Saving 75% of the time on a task sounds like a win.
It becomes one only if someone decides what the saved time is for.
Without that decision, the hours quietly fill up with other work, and nobody can say what the automation did for the business.
Before you automate anything, answer three questions:
-> What does the team do with the time?
-> Which number should improve: speed, volume, or accuracy?
-> Who owns that number?
On our recent AI-enabled CRM and dispatch project for the construction industry, the time saving is the easy part to measure.
The harder and more valuable part is turning those hours into something your customers notice.
I'd love to hear from someone who got this right.
#AIAutomation #ConstructionTech #WorkflowAutomation #OperationsManagement #CustomSoftware
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
Related posts
AI Customer Support Agent for Web Form, Gmail & WhatsApp
An AI support agent that answers customer questions across a web form, Gmail and WhatsApp, and hands off to a human team when it should. Load-tested with 200+ messages and no lost messages.
I built an AI customer support agent as a demo for a fictional SaaS company called Flowmint. Customers can write through a web form, Gmail or WhatsApp. The agent finds the answer in a knowledge base, replies on the same channel, and passes the conversation to a human team (Billing, Sales, Support) for refunds, special pricing, or when a customer asks for a person.
One agent for three channels, with replies formatted for each (a clean HTML email, a short WhatsApp message, a private web tracking page)
Safety rules written in code: it can only quote approved prices, and refunds always go to a human
Remembers returning customers on email and WhatsApp
Private ticket tracking page with a secret tracking code
If the AI service is busy, it switches to backup AI models, and to a knowledge-base answer if all are limited
I load-tested the agent for 24 hours with 200+ messages across all three channels, using simulated customers plus real emails and WhatsApp messages I sent myself.
212 messages in, 212 replies out, none lost
Only 3.3% needed a human
Areas I’m improving: faster replies with a paid AI plan, and spam protection for the web form.
Tech stack: Python, FastAPI, OpenAI Agents SDK, Kafka, PostgreSQL, Next.js, Docker, Gmail API, WhatsApp Cloud API.
Writing the safety rules in code, not in the prompt, is the part I like most: approved prices only, and refunds always go to a human. My RAG demo also passes the question to a person when the guide has no answer. How does your agent decide that a customer "asks for a person": a fixed list of phrases, or does the model decide?
Two designs. One idea. Two different ways to experience travel. ✈️
What if planning your next trip felt less like managing a checklist and more like discovering a story waiting to unfold?
Trailora makes discovery feel effortless, while Horizon turns travel planning into a smarter, more structured experience.
Same industry. Different design directions.
Which direction would you choose: the freedom to explore or the confidence of a well-planned journey?
25 voted
71%
10 voted
29%
35 votes
Closed
Both are lovely! The second one feels more like an adventure, which fits travel well.