You will get a custom AI agent using LangGraph and your API
Project details
Most "AI agents" on Upwork are glorified chatbots -- a prompt wrapped around an API call. That's not what I build.
I build production agent systems that actually execute tasks -- planning, tool use, error recovery, and real output. At GetHelpDesk.ai I built a Brain+Hand agent that operates dental software autonomously using Gemini vision + pywinauto. 355 passing tests. Live recorded demo. No human in the loop.
I also published LLM Diet on PyPI -- an MCP shadow server that cuts Claude Code token usage by 69-86% in live benchmarks. That's the kind of infrastructure-level thinking I bring to every project.
What you get with this service:
-- A working agent tailored to your use case
-- Clean Python code with tests
-- API/tool integrations you specify
-- A recorded demo showing it working
-- One round of revisions
Best fit for: startups and founders who need an agent that actually ships, not a prototype that breaks in week two.
I'm a first-year CS student at Thapar Institute, currently working full time as an AI Automation Engineer. I move fast and I don't disappear mid-project.
I build production agent systems that actually execute tasks -- planning, tool use, error recovery, and real output. At GetHelpDesk.ai I built a Brain+Hand agent that operates dental software autonomously using Gemini vision + pywinauto. 355 passing tests. Live recorded demo. No human in the loop.
I also published LLM Diet on PyPI -- an MCP shadow server that cuts Claude Code token usage by 69-86% in live benchmarks. That's the kind of infrastructure-level thinking I bring to every project.
What you get with this service:
-- A working agent tailored to your use case
-- Clean Python code with tests
-- API/tool integrations you specify
-- A recorded demo showing it working
-- One round of revisions
Best fit for: startups and founders who need an agent that actually ships, not a prototype that breaks in week two.
I'm a first-year CS student at Thapar Institute, currently working full time as an AI Automation Engineer. I move fast and I don't disappear mid-project.
AI Algorithms
Large Language Model, Multimodal Large Language Model, Transformer ModelAI Applications
AI-Generated Code, AIOps, Conversational AI, Natural Language Generation, Natural Language UnderstandingAI Development Language
PythonAI Models
ChatGPT, GPT-4, LLaMAWhat's included $150
These options are included with the project scope.
$150
- Delivery Time 7 days
- Number of Revisions 1
- AI Model Integration
- Database Integration
- Detailed Code Comments
- Natural Language Processing
- Prompt Engineering
- Source Code
Optional add-ons
You can add these on the next page.
Fast 3 Days Delivery
+$30Frequently asked questions
About Shresth
AI Agent Engineer | LangGraph, MCP, RAG & Production LLM Systems
Patiala, India - 3:24 am local time
Most "AI developers" on here are wrapping APIs and calling it an agent. I've been in the mud -- shipping systems that fail in interesting ways and fixing them under real pressure.
At GetHelpDesk.ai, I built a Brain+Hand system from scratch -- a Gemini vision model paired with GUI automation to operate dental practice management software with zero human input. Not a demo. 355 passing tests, a recorded production run, and a pile of hard-won lessons about what actually breaks when an agent meets legacy software.
I also shipped LLM Diet -- an open-source MCP shadow server on PyPI that intercepts Claude Code file reads and feeds agents compressed call-graph representations instead of raw source. 69-86% token reduction in live benchmarks. Built because I was annoyed at how wasteful standard file reads are for agentic workflows. That's the kind of problem I notice.
What I actually build --
-- AI agent systems using LangGraph, CrewAI, or custom architectures depending on what the problem needs
-- MCP servers and agent-native infrastructure
-- RAG pipelines built for production -- hybrid retrieval, reranking, eval loops, not just a Pinecone quickstart
-- LLM integration into real business workflows
-- Desktop and GUI automation driven by vision models
I'm a first-year CS student at Thapar Institute, currently working full-time as an AI Automation Engineer. I move fast, I write tests, and I don't disappear mid-project.
If your agent system needs to actually ship -- let's talk.
Steps for completing your project
After purchasing the project, send requirements so Shresth can start the project.
Delivery time starts when Shresth receives requirements from you.
Shresth works on your project following the steps below.
Revisions may occur after the delivery date.
Discovery & scoping
Review your requirements, ask clarifying questions, confirm scope and deliverables
Build & test
Develop the agent, integrate APIs, write tests, record a demo