Freelance AI Agent Engineers in DelhiFreelance AI Agent Engineers in Delhi
AI Agent Developer & Engineer | MCP, LLM apps, automation
    1x
    Hired
    5.0
    Rating
    64
    Followers
AI Agent Developer & Engineer | MCP, LLM apps, automation
Mobile App Architect • React Native Expert • 50+ App Shipped
    $5k+
    Earned
    1x
    Hired
    5.0
    Rating
    27
    Followers
Mobile App Architect • React Native Expert • 50+ App Shipped
Cover image for PromptOT – AI Prompts Get
PromptOT – AI Prompts Get Refined, Versioned, Evaluated & Shipped PromptOT is a prompt management platform designed to help AI teams treat production prompts as production code. It lets teams author prompts in structured, typed blocks, version every change with full history and rollback, evaluate versions against saved test cases across multiple models, and deliver the compiled, variable-driven prompt to their application via a single API call or native MCP integration, with no redeploy required. We built a compilation engine solid enough for production use, an AI co-pilot for conversational prompt editing with inline diffs and scoring, and native support for the tools AI teams already use daily - Claude Desktop, Cursor, ChatGPT, Codex CLI, Windsurf, and Zed. Key Features - Typed Prompt Blocks Semantic Versioning with Rollback Evaluations Across Models API & MCP Delivery AI Co-Pilot for Prompt Editing AI teams often struggle with - Prompts scattered across a Google Doc, a Slack thread, someone's Notion, and hard-coded strings in the codebase No version history, no diffs, no way to know which version is actually live No way to evaluate a prompt rewrite before shipping it to production Legal and brand review happening informally in DMs, if at all PromptOT delivers a single source of truth for every production prompt, shipped by API or MCP. It bridges the gap between prompt experimentation and reliable, production-grade delivery, turning prompts from fragile prose into managed, versioned infrastructure.
2
1
382
Cover image for SolJoy is an AI-powered tarot
SolJoy is an AI-powered tarot chat app that gives users personalized, context-aware guidance through a real-time conversational interface, "Conversations With Your Soul." Users start new readings, get real-time AI card interpretation grounded in their actual question and history (not generic card meanings), revisit past readings with saved insights, and reflect through a personal journal. The app also connects users to a real human coach for 1:1 sessions, blending AI-driven reflection with human support. We built a calm, trust-first experience that turns tarot from a one-off card pull into an ongoing, personal practice, users pick up exactly where they left off, track recurring themes across readings, and can escalate to a real coach when they want deeper guidance. Key Features Real-Time AI Card Interpretation Context-Aware, Personalized Guidance Reading History with Saved Insights Personal Journal Private 1:1 Coach Connection Blog Section Users often struggle with -: Getting tarot guidance that feels generic or disconnected from their actual question No way to track recurring themes or patterns across multiple readings Wanting deeper human guidance beyond what AI alone can offer SolJoy delivers a calm, personalized experience that treats tarot as an ongoing relationship with yourself, backed by AI for daily reflection and a real coach for deeper support. The app bridges AI conversation, personal journaling, and human coaching into one continuous self-discovery practice.
0
237
Cover image for The most expensive thing I've
The most expensive thing I've ever lost wasn't money. It was ideas. The ones that came during a walk. In the middle of a conversation. While rushing to the next meeting. Not because they weren't good. Because opening Notes, typing everything out, and organizing it felt like too much work. I've been trying OneKey lately, and it's made capturing thoughts ridiculously simple. Just tap, talk, and keep going. It transcribes everything, cleans up the text, extracts action items, and organizes it automatically. It's the kind of app that quietly removes friction from your day and that's what makes it useful. Some ideas deserve more than becoming another forgotten voice memo. Link - https://onekeynotes.onelink.me/CF08/contra
2
463
Founding AI Engineer, Agents, Automation, Cloud, Full-Stack
    $1k+
    Earned
    9x
    Hired
    4.7
    Rating
    63
    Followers
Founding AI Engineer, Agents, Automation, Cloud, Full-Stack
AI Engineer | Conversational AI, Agents & Backend Automation
New to Contra
AI Engineer | Conversational AI, Agents & Backend Automation
Cover image for Where most Sales Manager go
Where most Sales Manager go wrong isn't lack of data, it's getting overwhelmed with numbers and targets. What actually matters is not numbers, but "why" behind it. So we built an Agentic AI Sales Engine that sits on your Telegram, dissects the "why" behind what's happening in your sales team. It doesn't just throws number but tells you why someone is falling short while another pulling ahead, surfaces the operational bottlenecks underneath the numbers, and suggests what can actually be done better, all in real time at 0 infrastructure cost. Problem: A Sales Manager needed a fast way to check teams performance, calls, leads, conversions, pipeline value, but without opening spreadsheets or chasing manual reports. But raw numbers alone don't tell you what to do. Two reps can have identical conversion rates for completely different reasons. The manager needed something that could reason about the data, not just report it but by answering questions like "who needs attention today?" or "why is Rahul underperforming?" What We Built A fully automated Telegram bot, powered entirely by a self-hosted n8n workflow, that reads live data from Google Sheets and combines two layers: hard KPI reporting on demand, and an AI reasoning layer that interprets those numbers into a story a manager can act on. The "Why Layer" This is a part that makes it more than a dashboard, instead of just telling Rahul 12% conversion, the engine reasons over calls, leads pipeline and conversion patterns together and drives an analysis thereby providing the right suggestive next steps. Skills Demonstrated :Workflow automation & API orchestration (n8n) :OAuth 2.0 debugging and Google Cloud API setup :Data processing / aggregation logic (JavaScript in Code nodes) :LLM integration with grounded, hallucination-resistant prompting :Conversational bot design (Telegram Bot API) :Building production-usable tools on a strict zero-cost budget
1
223
Cover image for What happens when your assistant
What happens when your assistant turns into your creative partner? This is what we built few months back, a Conversational AI Design Assistant that could generate designs using natural conversation. The goal was to bypass traditional prompt engineering and replace it with natural conversation The experience was fulfilling, with learning failure and overcoming everyday challenges. Looking forward to share more such project If anyone is working on exciting projects, and believe I can contribute in any capacity, let's have a chat
2
1
230
Cover image for Competitor Price Monitor | n8n
Competitor Price Monitor | n8n + Google Sheets Keeping track of competitor prices becomes repetitive when a retailer manages several product categories and regularly adds new SKUs. I built this automation around TechNest Accessories, a simulated electronics retailer, with a practical brief: monitor comparable competitor products while keeping the solution affordable and easy to manage. The budget shaped the approach. Product discovery and matching stayed manual: the retailer enters its own SKU, selling price and chosen competitor URL in Google Sheets. This keeps control over which products are compared and reduces the complexity of the build. Once a listing is selected, the repeated checking is automated. The workflow reads active listings, retrieves competitor prices and availability, and compares each result with both the retailer’s price and the previously recorded competitor price. It then updates the Current Prices tab and appends a timestamped record to Price History. The retailer can manage everything from the sheet—add listings, update selling prices, or pause monitoring with a Yes/No dropdown. The workflow also handles failed page requests and price extraction. It records the error, preserves the last valid price and continues to the next listing. A successful later check clears the error. I tested the build with two Portronics charger listings, confirming price comparisons, historical records and recovery after a deliberately failed check. The workflow supports scheduled daily checks and manual runs. The result is a working prototype that brings selected competitor prices into one place, highlights meaningful differences and preserves a record for review—while leaving product selection and pricing decisions with the retailer. Built with: n8n, JavaScript, HTTP requests and Google Sheets. Independent portfolio project based on a simulated client brief. Images show recorded test data and simplified views of the working system.
1
140
Cover image for How I Built My Own
How I Built My Own Telegram Lead Capture System in n8n. The goal was simple: create a Telegram-based lead capture system that could collect enquiries in a structured way, remember where each user was in the conversation, validate the information, normalize budgets across different currencies, classify leads, and finally store everything cleanly in Google Sheets. I come from a Python background, so writing the chatbot logic in code would have been the easier route for me. But for this project, I deliberately chose to build the conversational flow using native n8n nodes instead of relying on a Code node. I wanted to understand how state management, branching, routing, and multi-step conversations could be handled visually inside n8n. I only used code later where it made more sense—validating lead data, parsing budget information, detecting currencies, converting values to USD, and classifying higher-value leads. At the moment, this system does exactly what I need it to do. If the volume of leads grows in the future, I’d extend it further—for example, automatically sending myself an email notification whenever a high-ticket lead comes in. For now, though, I wanted to keep it practical rather than over-engineer it. Built with: Telegram, n8n, JavaScript, Google Sheets, n8n Data Tables, and a currency conversion API.
1
173
AI Voice Agents for US Mortgage & Real Estate | Vocorix
AI Voice Agents for US Mortgage & Real Estate | Vocorix
Cover image for I built an AI voice
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
73
Cover image for Stop Prompting, Start Orchestrating: The
Stop Prompting, Start Orchestrating: The 2026 Freelance Shift The "AI-assisted freelancer" is now a standard baseline. To stay in the top 1% on Contra this year, you need to transition into an AI Orchestrator. We are seeing a massive shift toward Multi-Agent Systems (MAS). Instead of you manually prompting a tool to write a caption, then another to generate an image, 2026 is about building "Agentic Workflows" that handle the entire project lifecycle autonomously, with you as the creative director. Top independent pros are now using specialized agents that don't just "write" proposals but analyze a client's past project history and "agent-readiness" to pitch automated solutions. Clients are no longer paying for "AI-generated" work; they are paying for verified orchestration. The value is in your ability to govern the AI’s output and ensure it meets brand-specific compliance. The "Shadow AI" Cleanup: Enterprise clients are moving away from messy, unmanaged AI tools. They want freelancers who can integrate into their governed AI Gateways. Don’t just sell a deliverable. Sell a self-optimizing system that saves your client time.
0
51
Cover image for I built an AI engine
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
38
Cover image for One of my financial consulting
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
76
AI Web Developer | Video Generator & Editor
AI Web Developer | Video Generator & Editor
Cover image for Now, meet the one I
Now, meet the one I already told you all my project jarvis which is complete now. Here's the details - JARVIS is a production-grade, privacy-first AI desktop assistant designed to operate fully locally on standard hardware. Built to rival modern desktop AI systems, JARVIS seamlessly integrates natural voice interaction, real-time screen vision comprehension, deep Windows OS automation, and intelligent document/presentation generation. Unlike basic wrappers around cloud APIs, JARVIS features a hybrid architecture combining zero-latency regex intent routing, local LLM fallbacks, Win32 API shell controls, and active VLM screen verification. Key Capabilities of Jarvis - 🎙️ Multimodal Voice & Audio Intelligence Bilingual STT & Dynamic Query Cleaning: Real-time speech recognition tuned for Hinglish, Hindi, and English with automatic phonetic filler word stripping. Expressive Local TTS & Emotion Effects: Low-latency neural speech synthesis powered by Piper ONNX and Edge TTS with adaptive prosody and emotional modulation. Hands-Free Media & Non-API Automation: Full hardware media key automation for Spotify and browser video playback without requiring paid API tokens. 👁️ Vision AI & Live Screen Comprehension VLM Window & Screen Verification: Captures active window frames using OpenCV and local vision models (Moondream / Qwen-VL/Mistral) to verify OS tasks (e.g., verifying opened folders, app states, or UI elements). Camera Emergency Sentinel: Real-time visual distress sentinel using multimodal vision checks before initiating priority emergency calls. 🖥️ Deep OS & File System Automation Subfolder Inspection & Bulk Purging: Inspects complex nested folder structures (e.g., Pictures/Screenshots), calculates storage footprints, and executes secure file/folder purges via Win32 shell calls. OneDrive-Aware Name-Based Resolution: Intelligent 3-tier lookup engine resolving standard paths (Desktop, Downloads, Pictures) across native paths and OneDrive redirects without needing absolute user paths. Silent Recycle Bin Clean & Disk Optimization: Win32 API integration (SHEmptyRecycleBinW) for 100% silent, error-free disk maintenance. 📄 Productivity & AI Document Generation Automated Presentation Engine: Generates styled PowerPoint presentations (.pptx) with custom slide themes, topic summaries, and automated asset downloads. Markdown & PDF Document Compiler: Built-in Marp compilation engine converting voice notes to polished PDF slides and documents. And not only that I have open-sourced the entire github repo you can install it, check it and run it to your laptop as your assistant too, and don't forget to give the star, and if you face any issue kindly dm me or message in github too. Here's the link - "https://github.com/darshitp091/Jarvis "
2
325
Cover image for Kintsugi — the Japanese art
Kintsugi — the Japanese art of repairing the broken with gold. A self-initiated dark cinematic concept video exploring transformation, resilience, and the beauty found in restoration. Produced entirely using CapCut AI Video Generation.
0
52
Cover image for A self-initiated spec ad crafted
A self-initiated spec ad crafted to demonstrate high-end visual storytelling for consumer electronics. The goal was straightforward: make a product feel like a luxury experience no talent, no voiceover, just the product and light. The spot runs 20 seconds, built around five cinematic scenes macro leather texture, golden-hour marble staging, a mid-air slow-motion float, and a clean brand close. Every shot was art-directed with intention: warm rose and cream color grading to mirror the product's blush-gold finish, shallow depth of field to isolate detail, and a soft ambient piano score chosen to complement the product's aesthetic rather than overpower it. Produced entirely using CapCut AI Video Generation from prompt engineering to final output this project reflects how I approach AI-powered ad creative: product-first, visually led, and built to perform on short-form platforms like Instagram Reels and TikTok.
1
109
Cover image for Glad to share you that
Glad to share you that I've updated my portfolio recently not much animated, but is looks nice with perfect color combinations, fonts and normal animations. Here's the Link of the portfolio, kindly visit it - "https://darshitpatel.me"
2
3
172