AI Agent Engineer Projects in LahoreAI Agent Engineer Projects in Lahore
Projects
People
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
228
Cover image for Built a personalized LinkedIn post
Built a personalized LinkedIn post generator, and it's actually working end to end now. Most AI writing tools just take a prompt and spit out generic content. I wanted something different, a tool that understands who you are before it writes anything, and checks what's genuinely working on a topic right now instead of guessing. Here's what it actually does: → Personalized profile setup — set your niche, profession, key skills, and preferred tone once, it's reused for every post after that → Real-time research before writing — searches how people are actually discussing your topic right now, and extracts real patterns: hook style, structure, tone, without ever copying anyone's actual words → Fully personalized generation — combines your profile with the research patterns to write something original that sounds like you, not a generic AI voice → Editable output — every generated post is editable before you copy it, plus you get a breakdown of exactly which patterns informed the draft → Post history — every post you've generated is saved and browsable anytime → Fully self-contained build — Python, Streamlit, SQLite, no Supabase or external auth provider, just OpenRouter for generation and Serper for real-time research, with proper password hashing for authentication Still early, and currently invite-only while I manage access and costs on the research side. Link below, drop a comment or DM me for access. 🔗 https://post-pilot-ai.streamlit.app/ #AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) #Python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED) #Streamlit (https://www.linkedin.com/search/results/all/?keywords=%23streamlit&origin=HASH_TAG_FROM_FEED) #BuildInPublic (https://www.linkedin.com/search/results/all/?keywords=%23buildinpublic&origin=HASH_TAG_FROM_FEED) #OpenSource (https://www.linkedin.com/search/results/all/?keywords=%23opensource&origin=HASH_TAG_FROM_FEED) #MachineLearning (https://www.linkedin.com/search/results/all/?keywords=%23machinelearning&origin=HASH_TAG_FROM_FEED)
2
80
Cover image for ⚖️ Built a French Legal
⚖️ Built a French Legal AI Assistant powered by advanced RAG and LLM technology. The system enables users to ask complex legal questions and receive accurate, context-aware answers grounded in French legal documents. Key features include: 🔹 Custom legal document ingestion and chunking 🔹 Metadata-based vector search 🔹 Hybrid retrieval and reranking 🔹 Agentic RAG workflows using LangGraph 🔹 Source-grounded answers with legal references 🔹 Private deployment on an Azure VM using locally hosted LLMs The main focus was improving retrieval accuracy, reducing hallucinations, and making large collections of legal documents easier to search and understand. #LegalAI #RAG #LLM #ArtificialIntelligence #LangGraph #Azure #GenerativeAI #MachineLearning
1
78
Cover image for Most founders believe building the product is the hardest pa...
Most founders believe building the product is the hardest part. The real challenge starts after that. That was the biggest lesson from a recent iOS app I shipped using RORK Max. The app came together quickly. But what really mattered was the launch process: App Store assets. Metadata. Submission checks. Publishing workflow. Those invisible steps can slow a product down just as much as the code itself. That is why I enjoy helping founders build production-ready products, not just features. If you're working on an AI product, mobile app, or MVP, I'd love to help you move from idea to launch. AI Engineering • Agentic AI • Product Engineering • iOS Development • Mobile App Development • AI-Native Development • App Store Deployment • Product Launch • MVP Development • Founder Support • Startup Technology • Production-Ready Products • Digital Product Development • Front-End Development • Automation #AIEngineering #ProductEngineering #iOSDevelopment #MobileAppDevelopment #Founder #Startup #MVP #DigitalProducts
1
1
129
Cover image for Enterprise AI Outbound Engine: Programmatic
Enterprise AI Outbound Engine: Programmatic Domain Auditing & Hyper-Personalized Lead Acquisition The Objective To eliminate the extremely low conversion rates associated with generic, high-volume cold email strategies. This asset was engineered to build an automated, zero-latency outbound prospecting infrastructure that conducts programmatic technical audits on target company websites in real time. By delivering immediate, hyper-personalized value to a prospect’s inbox, the system dramatically increases cold response rates and shortens sales pipeline velocity. System Architecture & Workflow Breakdown The underlying logic is built as an asynchronous, multi-stage agentic data pipeline that seamlessly processes targets from raw data cells to a finalized outbound delivery: Stage 1: Automated Data Ingestion & Polling: The system monitors a centralized data core (Google Sheets) via automated webhooks, continuously scanning for newly appended prospect leads and tracking operational states to prevent duplicate processing. Stage 2: Programmatic Web Scraping: The workflow executes custom HTTP GET requests to isolate, scrape, and ingest live front-end code, metadata, and structural configurations directly from the target company's domain. Stage 3: Multi-Layered LLM Synthesis: The raw web payload is dynamically passed through dual-stage Large Language Model (LLM) API completion nodes. The first node isolates optimization bottlenecks on the prospect's site. The second node acts as a context-aware copywriter, translating those raw gaps into a polished, bespoke audit tailored specifically to the business owner. Stage 4: Automated SMTP Deployment: The finalized custom audit and strategic pitch are formatted into an email payload and routed through an automated mail-server node to deliver the value statement directly to the decision-maker. Stage 5: Closed-Loop State Sync: Upon successful delivery, a final write-back module updates the primary database row with full timestamp logs and execution states, establishing a clean audit trail. Core Capabilities & Tech Highlights Context-Driven Hyper-Personalization: Completely bypasses basic name-merge fields by extracting live, domain-specific text to generate authentic, high-impact value statements unique to every recipient. Token-Optimized Payload Ingestion: Employs advanced parsing to strip out irrelevant source code before sending data to the LLM core, preserving maximum contextual relevance while drastically lowering API computational costs. Scale-Ready Asynchronous Architecture: Engineered to execute complex web audits and custom draft writing sequentially across hundreds of target leads simultaneously without causing operational bottlenecks or memory overloads. Inbound Funnel Multiplier: Directly interfaces with modern outbound deliverability systems, protecting domain authority by replacing blind spam with highly targeted, consultative tech audits.
0
49