Swastik
AI/ML enthusiast specializing in building intelligent system
Ready for work
Swastik is ready for their next project!
I built an AI engine that does the work of an entire creative team.
You give it a single product photo. The system then analyzes the visual details, brainstorms creative concepts, and automatically generates high resolution images and cinematic videos. It even handles the file storage and database syncing for you.
I am turning complex, hours long design cycles into a hands free operation.
If you are looking to scale your content without the overhead, let’s build something together.
#AIContentCreator #aivideo #freelancerlife #AutomationEngineers #n8n #CreativeAI #FLORA #brandvisuals
0
7
One of my financial consulting clients had a massive problem: their AI voice agent, training on 50+ diverse funding programs, was starting to hallucinate. They were packing everything into one prompt, making it slow and unreliable.
I offloaded all that program data into an external Knowledge Base (RAG), integrated seamlessly via n8n. Now, when a customer asks a complex question, the agent performs a micro-lookup, retrieves the exact, verified program details, and answers with 100% precision. Her core prompt is 90% shorter, reducing token cost and latency.
The result isn't just a friendly bot, it’s a reliable expert in real-time.
Short Skills: #RetellAI #n8n #RAG #KnowledgeBaseIntegration #PromptEngineering #AIVoice #AIHallucinationMitigation #FinancialAutomation #ConversationalDesign
0
45
Most "omni-channel" AI agents are just disconnected silos. If a lead chats with you on the web and then calls 10 minutes later, the agent asks for their name and scenario all over again. Friction = Canceled Bookings.
My client was spending $25k+ on PPC and losing high-value real estate leads at that handoff point.
I built a frictionless Omni-Channel Real Estate AI Agent with Instant State Transfer. The AI agent knows who you are, what you were looking for, and where you left off, regardless of whether you are chatting or calling.
The Tech Stack:
1️⃣ Context Cache (Supabase): I used Supabase as a persistent, real-time database to act as the AI’s central nervous system.
2️⃣ Web Chat (OpenAI API/React): The lead inputs property details (e.g., property value, current rate).
3️⃣ n8n Orchestration: n8n listens to the chat completion, sanitizes the data, and appends it to the Supabase context.
4️⃣ Voice (Retell AI / ElevenLabs v2.5): If the user calls, n8n detects the caller ID, performs an instant lookup in Supabase, and pre-loads the context into the agent’s prompt.
The "Aha!" Moment: When the lead calls, the AI opens with: "I see we were just chatting about refinancing your $600k property on Oak Street. I have your info. Can I schedule that specialist call for tomorrow?" Conversion rate for refinancing inquiries doubled.
No generic questions. No manual data entry. Just instant, intelligent qualification and booking.
Skills: #OmniChannelAI #Supabase #n8n #RetellAI #OpenAI #APIIntegration #BuildInPublic #RealEstateAutomation
0
45
One of my clients, a high-volume service contractor, was spending tens of thousands a month on lead sources like Google Guarantee and Yelp. The problem wasn’t the volume; it was the bottleneck on their internal team.
Every incoming inquiry hit their CRM (Workiz) as a generic "Electrician Needed."
This meant the intake team was wasting hours every day manually clicking and reading customer notes like "panel is sparking" or "EV charger installation" just to assign the right technician. Returning customers were triggering deduplication nightmares, creating an "Identity Crisis" in their data.
I built a "common sense" triage engine using n8n to read those notes first.
The Breakdown:
Keyword Intelligence (Code Node): I wrote custom JavaScript logic to scan the incoming payloads for high-value keywords (e.g., "Panel," "EV Charger," "Generator"). The system now auto-assigns the exact "Job Type" in Workiz via API.
CRM Data Sanitization: Solved recurring Workiz API "400 Bad Request" errors by building a formatting layer that cleans JSON-breaking characters, like line breaks and special symbols in customer notes.
Zero Duplicate History: Implemented historical contact matching to preserve the customer's entire conversation stack, ensuring zero data leakage for returning clients.
The team no longer clicks; they schedule. Every lead is categorized and assigned in less than 2 seconds.
Skills: #n8n #Workiz #LeadAutomation #JavaScript #APIIntegration #DataSanitization
0
56
I built an AI voice agent that can pre-qualify $400k business loans, but for a week, it sounded like a database reading a grocery list. 🎙️
The problem? Variable Leakage. Instead of asking about equipment naturally, it would say: "I have equipment_cost noted as 400,000." Total conversion killer.
Here’s how I humanized the tech:
⚡ Speed is EQ: I moved the stack to Flash v2.5 to hit sub-100ms response times. In voice AI, latency kills the illusion of a real conversation. Speed = Trust.
🎭 Conversational Masking: I rewrote the logic so the AI confirms concepts, not data fields. It stopped "reading the code" and started "playing the character."
🧠 Keyword Intelligence: On the backend, I built an n8n pipeline that scans customer notes to automatically map leads to the right job type in the CRM. No more manual triage or duplicate "identity crisis" bugs.
The result is a self-healing lead engine that sounds human and keeps the CRM spotless. ⚡
#n8n #AIVoice #ElevenLabs #CRMAutomation #APIIntegration #BuildInPublic
0
54