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
AI Travel Planner
Built an AI travel planning agent using LangGraph, Groq, Tavily, flight search tools, and PostgreSQL to generate personalized travel plans and coordinate multiple tools.
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
What if your PC could actually listen, understand, and do the work for you?
I’m building that idea into something real.
Meet AURA — my personal AI voice assistant for Windows.
Instead of building another chatbot that only answers questions, I’m experimenting with an AI agent that can actually interact with my computer and help with everyday work.
So far, AURA can:
• Have live voice conversations
• Convert speech to text and respond with voice
• Open applications like Excel, Power BI, Chrome, and Windows Settings
• Search the web and YouTube through voice
• Perform basic PC and file operations
• Understand requests through Gemini
• Execute actions through a safety-controlled automation layer
• Continue listening after completing a task
But this is only the beginning.
My long-term goal is to make AURA understand my actual workspace — including what’s happening on my screen and inside applications — so I can simply say:
“Open my Excel file, check the sales data, clean the date column, and add a formula for total revenue.”
And let AURA handle the workflow.
I also want it to become useful for my own Data Analytics work — from Excel and Power BI workflows to repetitive desktop tasks, research, and automation.
I’m building AURA with Python, AI, voice technologies, desktop automation, Excel, Power BI, and LLMs, while keeping safety and human control at the core.
It’s still far from the final vision.
But that’s exactly what makes the project interesting.
I’m not just learning how AI agents work.
I’m trying to build one that I can actually use every day.
Building in public. Learning by building. 🚀
#AI #AIAgents #Python #AIAssistant #VoiceAI #DesktopAutomation #DataAnalytics #PowerBI #Excel #Automation #BuildInPublic
The screen-reading step is where I would put the guardrail. Once AURA can read what is in the window, everything on that screen is input - and a page it opened from a voice search can hold a sentence written to be read as an instruction. I spent a while trying to rob my own...
As an AI Agent Developer, I build agents into an operating flow rather than leaving them as a voice demo. Dispatchly lets lending, insurance, and staffing teams upload leads, choose a use case, run campaigns, and route qualified results into a CRM, with a transcript and recording for every call. I add approvals around consequential actions and read-back after integrations. If you need an AI agent connected to real operations, message me.
I came across a UI I designed more than 2 years ago, and it made me think about how much AI has changed the design process.
This was an eSIM product where we needed to show different plans for different countries.
I wanted each country to feel unique, so I used:
→ Country flag colors
→ A recognizable landmark
→ Travel-related visual context
Today, this kind of work is much easier with AI. You can generate variations, explore visual directions, find references, and iterate much faster.
But when I designed this 2+ years ago, almost everything was manual.
I had to research each country → Find the flag → Search for popular landmarks → Figure out which landmark would actually mean something to a traveler → Download and prepare the assets → Then test how everything worked together inside the UI.
It took days.
Looking back, I don't think AI is making design “easy.”
It is making the execution faster, and that's an important difference.
The designer still needs to decide:
What should we show?
Why should we show it?
Which option is actually relevant to the user?
AI can help us get to the answer faster.
But the quality of the answer still depends on the thinking behind it.
The country-by-country framing is a smart way to make a utility product feel personal. I especially like how the color-coded plan matrix turns a dense comparison into something scannable.