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
ARH Jarvis | Voice and Text Command Automation Assistant (n8n + Windows Agent)
A personal automation assistant that takes voice or text commands from a web page or phone and carries them out on a real Windows computer, in English or Roman Urdu.
Voice commands are transcribed through Groq, then converted into a structured command. Text commands go through a separate authenticated route: common commands are resolved with deterministic rules with no AI cost involved, while complex natural-language requests are planned by DeepSeek before execution. Both paths converge on the same Windows agent, connected through a permanent tunnel, with a confirmation step before any sensitive action runs.
Current capabilities include opening and searching applications such as YouTube, Gmail, and WhatsApp Web, sending Gmail messages and WhatsApp messages, checking the PC's live status, writing files to approved folders, and monitoring the automation platform itself: it can detect the latest failed workflow execution, summarise the error, and save a report to the desktop.
Every request is authenticated at each hop, and errors return as structured categories such as authentication_error, planner_error, or execution_error, rather than a plain crash. Actions such as arbitrary software installs, unrestricted system commands, or unrestricted file deletion are intentionally blocked by design, not because they were forgotten.
This is a personal proof of concept still being hardened, with voice recognition consistency and fully autonomous multi-step flows as the current development focus. It uses the same architecture principles I bring to client systems: hybrid AI plus deterministic logic, authenticated multi-hop communication, and structured error handling.
Stack: n8n (self-hosted on Contabo), Groq, DeepSeek, Windows local agent, ngrok, Gmail API.
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
Just posted mobile design for event platform 🎫 Share your feedback
Looks sharp
Added a MacBook mockup to the Vision Engine hero section, and it’s looking really good! ✨
Small detail, big impact. Love how much more polished the hero feels now :)
⬇️ What would you rate it ? /10
great...💯
AI-Powered Client Enquiry Automation
Project Overview:
I built an AI-powered client enquiry automation workflow using Zapier, Google Forms, Google Sheets, AI by Zapier, Gmail, and Google Calendar.
The goal was to automate the initial handling of client enquiries from receiving the enquiry to understanding the client's needs, sending an acknowledgement, and creating a follow-up task.
The Problem:
Managing client enquiries manually can be repetitive and time-consuming. Each new enquiry needs to be reviewed, categorized, summarized, responded to, and followed up.
Without a structured process, it's easy for enquiries to be delayed or follow-ups to be missed.
The Solution:
I designed a workflow that automates these repetitive administrative tasks while using AI to analyze the information provided by the client.
The automation follows this process:
Client submits enquiry
↓
Google Sheets captures the enquiry
↓
AI analyzes the enquiry
↓
Gmail sends an acknowledgement
↓
Google Calendar creates a follow-up
How It Works:
1. Enquiry Collection.
The client submits their details and enquiry through a Google Form. The information is automatically recorded in Google Sheets.
2. AI Analysis.
AI by Zapier reviews the enquiry and extracts key information such as the service category, priority, concise summary of the client's needs, and recommended next action.
This eliminates the need to manually review every enquiry just to determine what it is about and how it should be handled.
3. Automated Client Response.
After the enquiry is processed, Gmail automatically sends the client an acknowledgement, ensuring they receive a timely response.
4. Follow-Up Management.
The workflow creates a Google Calendar follow-up, helping ensure that the enquiry doesn't get lost after the initial response.
Result:
The completed workflow turns a manual enquiry process into a structured automated system:
Capture → Analyze → Respond → Follow Up
The key improvement is the use of AI as a decision-making layer, rather than simply moving information from one application to another.
This demonstrates how AI automation can reduce repetitive administrative work, improve response consistency, and help businesses stay organized with client enquiries.
Tools Used:
Zapier | AI by Zapier | Google Forms | Google Sheets | Gmail | Google Calendar
Skills Demonstrated:
AI Automation • Workflow Design • Administrative Automation • AI Prompting • Client Enquiry Management • Email Automation • Calendar Automation • Process Optimization
Really clean workflow, Ann. The Capture → Analyze → Respond → Follow Up structure makes the business value immediately clear. One useful next layer could be an exception route for urgent or low-confidence enquiries, so AI handles the routine cases while anything uncertain...
