Freelance AI Agent Orchestrators in Islamabad
Freelance AI Agent Orchestrators in Islamabad
Sign Up
Post a job
Sign Up
Log In
Filters
2
Projects
People
Armughan Shahid
pro
Islamabad, Pakistan
AI SaaS Dev | LLMs, Agents, Voice & Automation | Web, Mobile
New to Contra
Follow
Message
AI SaaS Dev | LLMs, Agents, Voice & Automation | Web, Mobile
0
AI Operations Agent: RAG-Powered Retail Intelligence & Task Automation This project was built for large-scale restaurant groups and multi-unit retail operators who manage high volumes of data across dozens or hundreds of locations. Specifically designed for Regional Managers and Operations Directors, the system serves as an enterprise-grade "Digital Consultant" that bridges the gap between fragmented POS/inventory data and daily on-the-ground execution. By transforming millions of rows of restaurant performance metrics into high-priority tasks, it provides a centralized platform for leadership to monitor KPIs, approve AI-suggested corrective actions, and ensure operational consistency across their entire portfolio. 1. What We Built We developed a production-ready Autonomous AI Operations Agent designed to bridge the gap between complex retail data analysis and daily execution. The system acts as a digital consultant for regional managers, transforming raw KPIs into actionable tasks. Analytical AI Chat: A free-form conversational interface where users can query performance data (e.g., "Show me the top 5 worst profitable stores in Istanbul for the last 3 months"). Task Management Dashboard: A structured workflow where AI-suggested actions are automatically logged for manager approval or rejection. Automated Action Logic: The agent uses an "Action Suggestion Map" to identify specific defects (like low audit scores or high food waste) and suggest precise corrective measures. Persistent Memory: Includes both short-term memory for the current chat session and long-term RAG memory to maintain context over time. 2. How We Built It (The Stack) The system was engineered for scalability and reliability using a modern, containerized stack:AI Orchestration: LangGraph was used to manage complex, multi-turn reasoning and agentic workflows. Frontend: React/Next.js 14 for a responsive, real-time user interface. Backend & Data: Node.js paired with a PostgreSQL database capable of handling 1M+ records. LLM Access: Integrated via OpenRouter to allow for flexible model selection and switching. Infrastructure: Fully Dockerized to ensure consistent deployment across environments. 3. Challenges We Faced As the system scaled from prototype to processing millions of records, we encountered several critical engineering hurdles: Response Latency: The initial monolithic prompt architecture led to response times exceeding 60 seconds, far slower than the required "ChatGPT-like" speed. Prompt Verbosity & Errors: Complex questions involving multiple variables caused the LLM to lose focus, leading to "reasoning errors" and incorrect SQL generation. Hallucination Risks: In multi-branch queries, the model occasionally fabricated data points, particularly around manager hours and performance metrics. Context Switching Bugs: The agent sometimes struggled to "let go" of a previous topic, continuing to reference an old store when the user had asked about a new city. 4. How We Solved It We re-engineered the core pipeline to transition from a single, heavy agent into a Modular Multi-Step Architecture: 75% Latency Reduction: By decomposing the main logic into smaller, task-specific nodes, we dropped processing time from 60s down to 15s. Task Decomposition & Specialized Models: We stopped using a "one-size-fits-all" model. Instead, we implemented a router that uses lighter, specialized models for SQL generation and action identification, and flagship models only for final reasoning. Granular SQL Generation: Breaking the metadata analysis into narrow sub-steps eliminated SQL hallucinations. The model now only "sees" the specific schema needed for the current sub-task, ensuring 100% accuracy. 10-Point Testing Protocol: We implemented a rigorous QA protocol that specifically verified bug fixes for context switching, task duplication, and chart coverage before final delivery.
0
150
1
BudgetNest — AI-Powered Personal Finance SaaS Most people don't track their finances because the friction is too high. BudgetNest removes that friction entirely, every transaction captured automatically, categorised intelligently, and surfaced through analytics that actually help people make better decisions. The core problem it solves: Manual expense logging fails because people forget, get lazy, or simply don't have time. BudgetNest built an automated capture layer that works across every channel a user already operates in i.e. SMS alerts, bank emails, receipt photos, WhatsApp messages, and voice notes in English and Urdu. The system deduplicates intelligently across all input sources so nothing gets logged twice regardless of how it came in. What was built: A complete AI finance platform with five distinct automated capture modes SMS and email parsing for bank transaction alerts, PDF and image bank statement upload with AI extraction, OCR receipt scanning via camera, a WhatsApp bot that accepts text, images, and voice notes, and multilingual voice input for manual cash payments. Every transaction flows through an LLM-powered categorisation engine that auto-assigns categories and subcategories, recognises vendors, and learns from behaviour over time. Beyond capture, the system includes smart budgeting with AI-driven suggestions based on spending patterns, subscription detection for recurring transactions, shared expense and split-bill tracking, fraud detection for unusual transactions, and forecasting that projects deficit against income. Dashboards surface everything through charts, trend lines, and weekly and monthly summaries. Technical architecture: React Native across iOS and Android, Node.js and FastAPI backend, PostgreSQL and MongoDB, AWS infrastructure with EC2, S3, and RDS, Python-based NLP and OCR pipeline using Transformers and Tesseract, Twilio WhatsApp integration, Gmail API for email parsing, and Firebase for push notifications. Business model built in from day one: Freemium with premium automation features, B2B white-label capability for microfinance institutions and NGOs, and the OCR and SMS parsing logic architected as standalone APIs for third-party licensing meaning the AI layer has revenue potential independent of the consumer app.
1
176
0
Share the Light - Role-Based Tutoring Platform
0
4
0
We Step Together - Step-to-Donation Mobile App
0
5
AI Agent Orchestrator
(2)
Follow
Message
Ali Zafar
Rawalpindi, Pakistan
AI Automation Expert | Workflows & Voice AI
New to Contra
Follow
Message
AI Automation Expert | Workflows & Voice AI
0
InventoryPilot AI — Multi-Tenant RAG Copilot & Demand-Forecasting Platform InventoryPilot AI is a production-grade AI copilot designed to securely manage enterprise data and automate supply-chain forecasting. It serves businesses and retailers by fusing dense vector search and keyword retrieval into a secure hybrid RAG system. This ensures absolute data isolation and prevents leaks in multi-tenant environments. It utilizes advanced Anthropic Claude tool-use agents for structured, real-time data streaming while maintaining strict security via content fencing to block injections. By incorporating WAPE-based mathematical logic, it delivers 80% accurate demand prediction intervals. This helps retailers avoid costly overstock and dangerous stockouts, transforming reactive data management into proactive, efficient, and cost-effective operations.
0
16
0
Title DealzoneAI — AI-Powered Sales & Deal Intelligence Platform Tagline Analyze, score, and optimize sales opportunities with AI-driven insights and workflow automation. Description DealzoneAI is an AI-powered platform that helps businesses manage, analyze, and optimize sales opportunities through intelligent automation. The system centralizes deal management, provides AI-generated insights, automates repetitive workflows, and enables teams to make faster, data-driven decisions.
0
18
0
"AI Voice Receptionist & Appointment Booking for Immigration Services" Designed and developed an AI-powered voice receptionist that answers inbound calls, qualifies potential clients, responds to common immigration inquiries, and automatically books appointments into the firm's calendar. The system reduces manual call handling while ensuring leads are captured and scheduled efficiently.
0
24
0
AetherMark AI — AI-Powered Marketing Campaign Generation Platform
0
31
AI Agent Orchestrator
(1)
Follow
Message
Khakan Hayder
Islamabad, Pakistan
Framer Expert
$1k+
Earned
1x
Hired
5.0
Rating
10
Followers
expert
Follow
Message
Framer Expert
3
Voicecon AI delivers AI Voice Agents and AI Text Chatbots to automate customer support and inbound/outbound calls, driving efficiency and business growth.
1
3
263
2
Currently building: Voicecon An AI voice agent platform. Voice to voice, then voice to action. Agents that hold a real conversation and then actually do the task across your tools. Status, honestly: voice engine is working. Workflows, integrations and the app UI are in progress. Domain is live with a waitlist while we finish. Ruby on Rails backend, multi provider voice orchestration, attachable knowledge bases per agent. This is my own product. Client work runs through Vconekt, Framer, Webflow, WordPress and Shopify. voicecon.ai (http://voicecon.ai)
1
2
18
0
Diamant versatile
0
1
0
This is something, I really liked to work on... https://www.framer.com/community/marketplace/templates/peakcoaching/
0
14
AI Agent Orchestrator
(1)
Follow
Message
Explore people
