Freelancers using OpenAI in Punjab

Freelancers using OpenAI in PunjabFreelancers using OpenAI in Punjab

Projects People

proLahore, Pakistan

AI Automation Engineer | Full-Stack Apps & Integrations

66x: Hired

4.9: Rating

155: Followers

Expert

Expert

+2

AI Automation Engineer | Full-Stack Apps & Integrations

Cover image for Gut Health SaaS Platform Development

Gut Health SaaS Platform Development

1

17

Cover image for Magnai | UK Public Affairs

Magnai | UK Public Affairs

6

88

Cover image for Humoni - secure housing in under 72 hours

Humoni - secure housing in under 72 hours

7

146

Cover image for Wellbeing Wizard AI

Wellbeing Wizard AI

8

190

Toolshed (Data, Automation, AI Agents, Buildship, Framer)

maxLahore, Pakistan

Data, Automation, AI Agents, Buildship, Framer, Bubble

$100k+: Earned

7x: Hired

5.0: Rating

74: Followers

Top

expert

+1

Data, Automation, AI Agents, Buildship, Framer, Bubble

Cover image for BuildShip AI Automation & Internal Tool for Job Analysis

BuildShip AI Automation & Internal Tool for Job Analysis

0

7

Cover image for Multi-Tenant Insurance BI Platform

Multi-Tenant Insurance BI Platform

2

29

Cover image for AI Agents & GoHighLevel Workflow Automation

AI Agents & GoHighLevel Workflow Automation

2

58

Cover image for Construction FP&A & Revenue AI Platform

Construction FP&A & Revenue AI Platform

6

314

Muhammad Abdullah

Lahore, Pakistan

AI Automation Builder | Website Design

New to Contra

AI Automation Builder | Website Design

Cover image for [4:07 PM, 7/6/2026] Abdullah: AI

[4:07 PM, 7/6/2026] Abdullah: AI agent that handles scheduling end-to-end 🤖📅 [4:07 PM, 7/6/2026] Abdullah: • Hold context-aware conversations (with memory across the session) • Check your Google Calendar availability • Book new appointments directly • Send confirmation emails via Gmail • Log every interaction to Google Sheets for tracking [4:08 PM, 7/6/2026] Abdullah: No manual back-and-forth. No double bookings. Just a conversational front door that turns “can we find time to talk?” into a booked, confirmed, logged event — automatically. This is the kind of workflow I build for real estate and home services businesses who are tired of losing leads to slow follow-up. If you’re exploring how AI automation could save your team hours every week, let’s talk.

1

239

Cover image for Losing leads because you respond

Losing leads because you respond too slow? Responding within 5 minutes = 9x more likely to close. Most agents take hours. Or never respond at all. I’ll build you an AI Lead Qualification System that works the second someone fills your contact form: •Scores every lead Hot, Warm, or Cold instantly •Sends a personalized follow-up email in seconds #Logs everything to Google Sheets automatically No more guessing who to call first. Your hot leads get instant attention — you just focus on closing. ⏱️ Delivered in 24-48 hours #AIAutomation #n8n #EmailMarketing #LeadGeneration

1

318

Cover image for The Problem
Most real estate agents

The Problem Most real estate agents miss 30% of their calls. A buyer calls at 9 PM. No answer. They call the next agent. That agent closes the deal. Not you. Hiring a receptionist costs $3,000/month. And they still can't work 24/7. The Solution An AI Voice Receptionist that answers every call instantly — day or night — qualifies the buyer and books the appointment directly into your calendar. Automatically. Results 100% call answer rate — zero missed leads Appointments booked overnight while you sleep 10+ hours saved per week on call handling System cost: fraction of a human receptionist Works 24/7 — no sick days, no lunch breaks Before vs After Before: Missed calls, lost leads, manual follow-ups, paying for a receptionist, losing deals after hours. After: Every call answered instantly by AI, every lead qualified automatically, every appointment booked directly to your calendar — while you focus on closing deals. Your competitors are still missing calls. You won't be.

1

324

Cover image for Built a fully automated cold

Built a fully automated cold email outreach system using n8n, Gmail and Google Sheets. The system sends personalized cold emails to leads automatically, follows up with those who don't reply, tracks every response and logs replies directly into Google Sheets — all without any manual work. Results: 100% follow-up rate Replies tracked automatically Zero manual sending Runs 24/7 on autopilot

0

33

Multan, Pakistan

AI Automation Engineer | AI Agents | n8n | GHL | LangChain

New to Contra

AI Automation Engineer | AI Agents | n8n | GHL | LangChain

Cover image for Your Team Doesn’t Need More

Your Team Doesn’t Need More Leads. It Needs a Better System to Handle Them. How many potential clients are being lost because someone has to manually find prospects, research companies, qualify leads, update the CRM, write outreach messages, follow up, and track responses? The expensive part isn’t just the time. It’s the qualified lead that never gets contacted, the follow-up that gets forgotten, and the hours your team spends doing repetitive work instead of closing opportunities. That’s exactly what this AI Lead Generation Agent built with n8n is designed to solve. It can turn a repetitive lead-generation process into an automated workflow: Find Leads → Research & Enrich → AI Qualify → Score → Save to CRM → Generate Personalized Outreach → Human Approval → Send → Track → Notify → Report Instead of treating every prospect the same, the AI can analyze available lead information against your Ideal Customer Profile (ICP), organize and score prospects, and help prioritize the opportunities worth your team’s attention. For outreach, it can use available business context to prepare personalized messages instead of sending the same generic pitch to everyone. And when human judgment matters? Keep it. Add an approval step so your team can Approve, Edit, or Reject an AI-generated message before anything is sent. The result is simple: less repetitive research, faster lead handling, organized CRM data, more consistent follow-ups, and more time for your team to actually sell. This workflow can be customized for B2B companies, SaaS businesses, agencies, real estate, recruitment, consulting, e-commerce, local businesses, service businesses, startups, and other sales teams. Already have a lead-generation process? → Send me your current workflow, and I’ll show you where AI automation can remove the repetitive steps. Still generating and managing leads manually? → Tell me your business and ideal customer, and I’ll help map out an AI lead-generation workflow around your process. SEO Keywords AI Lead Generation Agent, AI Lead Generation, Lead Generation Automation, Automated Lead Generation, n8n Automation, n8n Workflow, n8n AI Agent, AI Automation, AI Agent Development, AI Workflow Automation, B2B Lead Generation, B2B Sales Automation, Sales Automation, Lead Generation System, Lead Qualification, AI Lead Qualification, Lead Scoring, Prospecting Automation, AI Prospecting, Sales Prospecting, Lead Enrichment, CRM Automation, Automated Outreach, Personalized Outreach, Email Automation, Cold Email Automation, Sales Outreach Automation, Follow-Up Automation, AI Sales Agent, AI Sales Automation, Business Process Automation, Workflow Automation, Marketing Automation, CRM Integration, Airtable Automation, Gmail Automation, Slack Automation, Notion Automation, SaaS Automation, Agency Automation, Real Estate Lead Generation, Recruitment Automation, E-commerce Automation, Business Automation, No-Code Automation, AI Integration, Digital Transformation #AILeadGeneration #LeadGeneration #LeadGenerationAutomation #AutomatedLeadGeneration #AIAgent #AIAgents #AIAutomation #AIWorkflow #WorkflowAutomation #n8n #n8nAutomation #n8nWorkflow #SalesAutomation #AISalesAgent #AISales #B2BLeadGeneration #B2BSales #B2BMarketing #LeadQualification #LeadScoring #LeadEnrichment #SalesProspecting #AIProspecting #Prospecting #CRM #CRMAutomation #SalesOutreach #OutreachAutomation #EmailAutomation #ColdEmail #FollowUpAutomation #MarketingAutomation #BusinessAutomation #ProcessAutomation #SaaS #SaaSAutomation #AgencyAutomation #RealEstate #RecruitmentAutomation #EcommerceAutomation #StartupAutomation #NoCode #LowCode #ArtificialIntelligence #GenerativeAI #DigitalTransformation #SalesTech #MarTech #BusinessGrowth #SalesGrowth #AutomationExpert

2

3

136

Cover image for What if every new lead

What if every new lead could be handled before you even open your inbox? ⚡ This AI-powered workflow turns a new email inquiry into a structured, ready-to-handle lead — automatically. A new inquiry arrives → AI extracts the important details → Airtable/CRM is updated → the response goes through optional human approval → a personalized email is sent → Notion is updated → the team gets notified in Slack → performance data is collected for reporting. The goal isn't to remove people from the process. It's to remove the repetitive work around them. This type of workflow can be customized for B2B companies, SaaS businesses, agencies, real estate, e-commerce, recruitment, consulting, customer support, healthcare, finance, education, and other service businesses. Already know what you want to automate? → Send me your current workflow and I’ll map out how we can automate it. Still doing repetitive work manually? → Tell me the task that consumes your team’s time, and I’ll help identify what can be automated. #AIAutomation #AIWorkflow #AIWorkflows #AIAgents #Automation #WorkflowAutomation #BusinessAutomation #ProcessAutomation #n8n #n8nAutomation #ArtificialIntelligence #GenerativeAI #B2B #B2BAutomation #SaaS #SaaSAutomation #SalesAutomation #LeadGeneration #LeadAutomation #LeadManagement #EmailAutomation #CRMAutomation #CustomerSupport #CustomerServiceAutomation #MarketingAutomation #AgencyAutomation #RealEstateAutomation #EcommerceAutomation #RecruitmentAutomation #HRautomation #FinTech #HealthcareAutomation #EdTech #BusinessGrowth #BusinessEfficiency #DigitalTransformation #NoCode #LowCode #OpenAI #AIAgent #CRM #Airtable #Notion #Slack #Productivity #FutureOfWork

4

2

165

Cover image for AI Recruitment Automation — From

AI Recruitment Automation — From Application to Interview Hiring teams shouldn’t spend hours manually reviewing resumes, updating candidate records, sending repetitive emails, and coordinating interviews. I designed an AI-powered recruitment automation workflow that connects the entire hiring process into one intelligent system. Candidate Application → Data Extraction → Airtable → AI Resume Screening → Candidate Scoring → Shortlisting → Interview Scheduling → Team Notifications → Reporting The AI can analyze candidate information against the job requirements, identify relevant skills and experience, generate structured summaries, and help route applications based on predefined hiring criteria. The workflow can also automate candidate status updates, interview scheduling, hiring-team notifications, rejection/shortlist emails, and recruitment analytics. For better reliability, the system includes logging and monitoring around AI calls, making it easier to trace executions, identify workflow errors, and monitor AI processing without unnecessarily exposing sensitive candidate content. This type of automation can be customized for recruitment agencies, HR teams, startups, staffing companies, and growing businesses that want to reduce repetitive hiring operations while keeping important decisions under human oversight. #AIRecruitment #RecruitmentAutomation #HRTech #HRAutomation #AIAutomation #WorkflowAutomation #MakeAutomation #AirtableAutomation #OpenAI #HiringAutomation #RecruitmentTech #TalentAcquisition #ResumeScreening #BusinessAutomation #AIAgents #APIAutomation #AutomationDeveloper

2

191

Cover image for AI-Powered Email & Lead Automation

AI-Powered Email & Lead Automation Workflow Built a smart AI automation workflow that turns incoming emails into structured, actionable business data — while keeping the AI process traceable and easier to debug. The workflow automatically handles: Email/Webhook → Data Extraction → Airtable → Validation → AI Processing → Human Review → Response → Team Notification → Reporting I also added a dedicated logging layer before and after the AI call to improve reliability. It can capture the input schema structure, model parameters, input/output hashes, timestamps, execution status, and error information without unnecessarily storing sensitive prompt content. This makes it easier to identify edge cases between Airtable and OpenAI, troubleshoot failed executions, monitor AI behavior, and maintain a clear audit trail. This type of system can be customized for lead management, customer support, sales inquiries, CRM automation, reporting, internal operations, and other AI-powered business workflows. If your team is spending hours manually processing emails, updating databases, generating responses, or moving information between different tools, I can build a workflow around your actual business process. #AIAutomation #WorkflowAutomation #MakeAutomation #AirtableAutomation #OpenAI #AIAgents #BusinessAutomation #EmailAutomation #APIAutomation #CRMautomation #NoCodeAutomation #ProcessAutomation #AIWorkflow #AutomationDeveloper #ArtificialIntelligence.

1

147

Sialkot, Pakistan

Forward Deployed AI Engineer | AI Agents & SaaS

New to Contra

Forward Deployed AI Engineer | AI Agents & SaaS

Cover image for I built an end-to-end AI-powered

I built an end-to-end AI-powered email outreach system designed to automate lead generation, personalized cold email creation, campaign sending, reply handling, and CRM updates. The workflow finds and verifies leads, uses AI to generate personalized outreach messages, sends campaigns through connected email providers, tracks campaign performance, analyzes replies, and automatically stores qualified leads and conversation data in the CRM/database. I also integrated warmup and deliverability monitoring so the system can support safer email sending while maintaining inbox health. The system connects tools such as n8n, OpenAI, Google Sheets, Gmail, Supabase, Instantly, Warmbly, Slack, Notion, and CRM/database services into one automated workflow. The goal of this project was to reduce manual prospecting and outreach work while making lead generation more scalable, personalized, and organized.

0

13

Cover image for I built an AI-powered WhatsApp

I built an AI-powered WhatsApp automation system designed to handle customer conversations, qualify leads, book appointments, and keep customer data organized automatically. The system receives incoming WhatsApp messages, understands customer requests with AI, provides instant responses, checks availability, books appointments, stores lead information in the CRM/database, sends confirmation emails, and triggers follow-up sequences when needed. I connected the workflow with tools including n8n, OpenAI, WhatsApp, Supabase, Google Calendar, Gmail, Slack, and CRM/database integrations to create an end-to-end customer communication system. The goal was to reduce repetitive support work, improve response times, and make sure every lead is captured, followed up with, and moved through the customer journey efficiently. This project demonstrates my work in AI agents, WhatsApp automation, lead qualification, appointment booking, CRM integration, workflow automation, and customer support systems.

0

18

Cover image for I built an AI-powered booking

I built an AI-powered booking and customer support automation designed to handle customer inquiries, qualify leads, manage bookings, and keep customer data organized automatically. The system can respond to incoming website or WhatsApp inquiries, answer common questions, check availability, book appointments, send follow-ups, and sync lead information with a CRM/database. The goal of this project was to reduce manual customer support work while helping the business respond faster and convert more inquiries into bookings. This project demonstrates my work in AI agents, workflow automation, customer support automation, appointment booking, CRM integration, and multi-channel communication.

0

26

Cover image for I built an AI-powered LinkedIn

I built an AI-powered LinkedIn content automation system designed to streamline the full content workflow from idea generation to publishing. The system can research relevant topics, generate LinkedIn posts with AI, format the content, add hashtags, schedule posts, and track performance from one automated workflow. I connected the automation with tools such as n8n, OpenAI, LinkedIn, Google Sheets, Notion, Slack, and Gmail to create a complete content system that reduces repetitive work and helps maintain a consistent posting schedule. The goal of this project was to turn LinkedIn content creation into a faster, more organized, and scalable process while keeping human control over the final output. This project demonstrates my work in AI automation, content generation workflows, API integrations, scheduling systems, and social media automation.

0

22

sharjeel mansha

Lahore, Pakistan

AI Automation Engineer, AI Agents, CRM & AI Full-Stack Dev.

New to Contra

AI Automation Engineer, AI Agents, CRM & AI Full-Stack Dev.

Cover image for AI Slack Automation | n8n, OpenAI & CRM Integrations

AI Slack Automation | n8n, OpenAI & CRM Integrations

2

1

Cover image for 𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐋𝐞𝐚𝐝 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 & 𝐂𝐑𝐌

𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐋𝐞𝐚𝐝 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 & 𝐂𝐑𝐌 𝐀𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧 𝐒𝐲𝐬𝐭𝐞𝐦 I built an automated lead generation system designed to simplify the entire sales pipeline from lead capture to follow-up. The system collects leads from multiple sources, processes and qualifies them, adds them directly into the CRM, updates pipeline stages automatically, and triggers personalized follow-up sequences based on lead activity. Instead of managing leads manually across different tools, the entire workflow runs through one connected automation system. 𝐖𝐡𝐚𝐭 𝐭𝐡𝐞 𝐬𝐲𝐬𝐭𝐞𝐦 𝐡𝐚𝐧𝐝𝐥𝐞𝐬: -Lead capture from multiple sources -Lead enrichment and qualification -Automatic CRM entry -Pipeline stage updates -Automated follow-up sequences -Reply and meeting tracking -Opportunity management The goal is simple: reduce manual work, improve response speed, and make sure valuable leads don’t get missed. 𝐖𝐚𝐧𝐭 𝐭𝐨 𝐛𝐮𝐢𝐥𝐝 𝐚 𝐬𝐢𝐦𝐢𝐥𝐚𝐫 𝐥𝐞𝐚𝐝 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐚𝐧𝐝 𝐂𝐑𝐌 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧 𝐬𝐲𝐬𝐭𝐞𝐦 𝐟𝐨𝐫 𝐲𝐨𝐮𝐫 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬? 𝐋𝐞𝐭’𝐬 𝐜𝐨𝐧𝐧𝐞𝐜𝐭.

2

3

304

Cover image for 𝐓𝐮𝐫𝐧 𝐎𝐧𝐞 𝐏𝐫𝐨𝐝𝐮𝐜𝐭 𝐈𝐦𝐚𝐠𝐞 𝐈𝐧𝐭𝐨

𝐓𝐮𝐫𝐧 𝐎𝐧𝐞 𝐏𝐫𝐨𝐝𝐮𝐜𝐭 𝐈𝐦𝐚𝐠𝐞 𝐈𝐧𝐭𝐨 𝐚 𝐂𝐨𝐦𝐩𝐥𝐞𝐭𝐞 𝐔𝐆𝐂 𝐕𝐢𝐝𝐞𝐨 𝐂𝐚𝐦𝐩𝐚𝐢𝐠𝐧 𝐰𝐢𝐭𝐡 𝐀𝐈 Creating multiple product videos manually can take hours. This AI-powered workflow simplifies the entire process from start to finish. Upload a single product image, and the system automatically analyzes the product, creates a complete UGC storyboard, generates multiple creative scenes, sends each scene to Google Flow for AI video generation, and then organizes everything into a final editing workflow. The result is a faster and more scalable way to create product content without repeating the same manual process for every scene. 𝐖𝐨𝐫𝐤𝐟𝐥𝐨𝐰: Product Image → AI Analysis → UGC Storyboard → Scene Generation → Google Flow → Video Clips → Automated Editing Built for brands, eCommerce businesses, agencies, and content teams that need to produce more product videos with less manual work. 𝐖𝐚𝐧𝐭 𝐚 𝐬𝐢𝐦𝐢𝐥𝐚𝐫 𝐀𝐈 𝐯𝐢𝐝𝐞𝐨 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧 𝐬𝐲𝐬𝐭𝐞𝐦 𝐟𝐨𝐫 𝐲𝐨𝐮𝐫 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬? 𝐋𝐞𝐭’𝐬 𝐛𝐮𝐢𝐥𝐝 𝐢𝐭.

3

139

Cover image for 𝐑𝐀𝐆 𝐀𝐈 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 |

𝐑𝐀𝐆 𝐀𝐈 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 | 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐭 𝐒𝐞𝐚𝐫𝐜𝐡, 𝐀𝐈 𝐀𝐧𝐬𝐰𝐞𝐫𝐬 & 𝐕𝐞𝐜𝐭𝐨𝐫 𝐃𝐚𝐭𝐚𝐛𝐚𝐬𝐞 I designed and built a RAG-powered AI knowledge platform that lets businesses search documents, websites, databases, and internal knowledge using natural language. The system processes content, creates embeddings, stores them in a vector database, retrieves the most relevant information, and uses AI to generate accurate, source-grounded answers. My services include: RAG development, document ingestion, semantic search, vector database setup, OpenAI/LLM integration, internal knowledge assistants, API integrations, and analytics. The solution helps teams find information faster, reduce repetitive research, improve answer consistency, and build scalable AI-powered knowledge systems. 𝐓𝐞𝐜𝐡 𝐒𝐭𝐚𝐜𝐤: OpenAI, LangChain, RAG, Pinecone, Qdrant, Weaviate, FAISS, Chroma, Python, FastAPI, PostgreSQL, APIs.

3

346

proLahore, Pakistan

AI Agents & Automation That Ship | Voice AI, LLMs, .NET

New to Contra

AI Agents & Automation That Ship | Voice AI, LLMs, .NET

Cover image for Bagallery: 24/7 AI Sales and Support Chat

Bagallery: 24/7 AI Sales and Support Chat

0

3

Cover image for Haia: AI Agent for Banks, Crypto and Investments

Haia: AI Agent for Banks, Crypto and Investments

0

3

Cover image for 𝗖𝗮𝘀𝗲𝗣𝗮𝘁𝗵 — 𝗔𝗜 𝗖𝗮𝘀𝗲 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁

𝗖𝗮𝘀𝗲𝗣𝗮𝘁𝗵 — 𝗔𝗜 𝗖𝗮𝘀𝗲 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁 𝗳𝗼𝗿 𝗖𝗵𝗶𝗹𝗱 𝗪𝗲𝗹𝗳𝗮𝗿𝗲 & 𝗙𝗮𝗺𝗶𝗹𝘆 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀 Recently, I built a modern SaaS case management platform for social work agencies, centered on an AI case-summary engine. The system cut documentation time by 90%, sped up supervisor case decisions by 83%, and added 20% more caseload capacity — with no new hires. Designed to reduce administrative burden on caseworkers so they can focus on families, while giving supervisors faster, clearer visibility into case status and decisions. https://mycasepath.com/

0

113

Cover image for ERP Portal in ASP.NET Core with Secured Web API

ERP Portal in ASP.NET Core with Secured Web API

0

0

Lahore, Pakistan

AI Developer | RAG Chatbots, AI Agents & Next.js SaaS

New to Contra

AI Developer | RAG Chatbots, AI Agents & Next.js SaaS

Cover image for Meet AI is a video

Meet AI is a video conferencing SaaS where AI agents join live meetings as active participants and respond in real time. I built the full application stack. The hard part is the real-time layer. The backend provisions an AI agent the moment a meeting starts and keeps it running for the full call. Speech runs through a transcript pipeline and generates responses through the OpenAI API in near real time, so the agent replies while the conversation is still moving, not minutes later. After the meeting, the backend writes a structured summary through the same API, handled async by Inngest so nothing blocks the live app. The stack is Next.js 15 and React 19 with the Stream Video and Stream Chat SDKs, tRPC and Drizzle ORM on Neon PostgreSQL, and Better Auth across the stack. The platform runs 30 simultaneous live sessions, each with its own active AI agent, with no backend slowdown. What the client gets: live AI agents that take part in real meetings, plus automatic summaries, on a stack built to hold many sessions at once.

2

3

242

Cover image for Nodebase is a workflow automation

Nodebase is a workflow automation SaaS where users build AI workflows visually with no code, backed by a custom execution engine. I built the full product end to end, alone. The visual builder runs on React Flow inside Next.js 15. Users connect trigger nodes, AI nodes, API nodes, and conditional logic into full pipelines. The backend engine uses topological sort to resolve node dependencies before running each step, so nothing fires out of order. Inngest handles background jobs, retries, and scheduled triggers. Webhooks let outside services start a workflow by hitting an endpoint. This is AI automation in practice. OpenAI, Claude, and Gemini run as built-in AI nodes next to Slack, Discord, and Stripe. A user can route data through an LLM, act on the result, and pass it to the next step, all without code. Credentials are encrypted and pulled at runtime, so keys never sit in plain text. Prisma with Neon PostgreSQL handles workflow ownership, execution history, and job logs. tRPC connects frontend and backend with full type safety. What the client gets: a no-code platform where non-technical staff build their own AI workflows, on an engine reliable enough to run them on a schedule without supervision.

2

2

218

Cover image for Echo is a multi-tenant SaaS

Echo is a multi-tenant SaaS for AI customer support with realtime chat, an AI voice agent, and AI automation. I was the primary developer on the full build, frontend, backend, and the AI layer. The AI is the core. It runs OpenAI, Claude, Gemini, and Grok through one multi-model setup, so a client can switch providers without a rewrite. A RAG pipeline connected to a vector database grounds every answer in the client's own content, so the chatbot never returns generic output. VAPI powers the voice agent, so customers can speak to support on a live call. Each tenant gets its own AI agent built on its own documents. The stack is Next.js 15 and React 19 inside a Turborepo monorepo, with separate apps for the dashboard, the embeddable chat widget, and backend services. Realtime chat runs on Convex. Clerk handles auth. API keys are encrypted per tenant through AWS Secrets Manager, so no two clients share credentials or data. Launch day held 60 live conversations at once with zero dropped sessions. What the client gets: an AI chatbot and voice agent that answer from their own content, work across multiple LLM providers, and stay isolated and secure per tenant.:

3

2

257

Cover image for I designed and built a

I designed and built a Sentry-style error tracking SaaS from scratch as the Next.js developer and AI integration developer behind it, to prove out multi-tenant architecture and AI integration. Admins manage sub-users with per-project access control. Each admin attaches their own OpenAI, Claude, or Gemini key, encrypted with AES-256-GCM, and picks a model per project for AI fix suggestions. I built two SDKs (Node.js and browser, with a React error boundary) plus a CLI that uploads source maps on build. Errors resolve to original source code, not minified output, the same technique Sentry uses.

2

208