
In Progress
Posted
Paid on delivery
Job Title: AWS AgentCore & Python Developer (Educational Project: phone Voice AI Agent Builder + Mentorship) Job Type: Fixed-Price 3 days to do Very good natural voices caller phone number ID identification email interface for admin to provided gmail address : add or remove files for skills; send by email logs of conversations , block phone numbers for incoming call for LLM use low cost models from openai or gemini or make suggestion No Terraform or similar techniques, only simple browser aws platform development I use for local windows Project Overview I am looking for an experienced AWS and Python developer to build a scalable Voice AI Agent architecture using AWS Bedrock AgentCore. This is fundamentally an educational project: your goal is to build a fully working example system, document it exhaustively, and teach me how to reproduce, modify, and deploy it completely independently from scratch. You may use existing open-source GitHub projects as a foundation, provided the final deliverable meets all my requirements and is fully documented. System Architecture & Core Examples We need a multi-tenant voice agent system acting as customer service for different "stores." The Use-Case Examples: Think of these as sales agents for different stores, where each store has many unique products: Store 1: Food Catering Store 2: Cleaning Services Store 3: Refrigerator Repair Expected Interaction Flow: At the beginning of the call, the agent asks the user what they want to talk about (essentially asking which file to load). Example A (Store 3): A user calls the dedicated phone number for Store 3 and says, "I have Refrigerator abc123." The agent must dynamically retrieve the specific .txt skill file for "Refrigerator abc123" and use this skill for the remainder of the session. Example B (Store 2): A user calls the dedicated phone number for Store 2 and says, "I need to clean a sofa." The agent chooses the specific .txt skill file on how to clean a sofa and uses it for the session. Technical Features & Requirements Voice Integration: Phone call voice chat using a Canadian phone number (+1). One phone number serves exactly one agent/store. Agent Registry & Scaling: An admin registry that can easily create anywhere from 0 to 100+ agents as needed. Strict Data Isolation: Each agent has its own dedicated group of .txt knowledge files. All phone and skill files are strictly separate. The .txt skills for Store 1 must never be accessed or used by the agent for Store 3. Session Memory: The agent must retain context during the call (e.g., if the caller says "My name is Peter," the agent calls him Peter for the whole session). There must be no memory between different sessions. Logging: Detailed logs must be generated and saved for every individual call/session. Technical Stack Language: Python AI Framework: AWS Bedrock AgentCore Telephony: AWS services compatible with AgentCore Amazon Connect Infrastructure: AWS Strict Development Constraints Your Own Environment: You must develop, record, and test this entirely in your own authorized AWS account. I will not provide my AWS account or credentials. Zero Dependencies: My later deployment must not depend on your accounts, resources, or API keys. Deliverables (Required for Payment) This fixed-price project covers the application, deployment, security, tests, source code, reporting, manuals, videos, and a handover session. 1. Editable Word (.docx) Manual: Must start from a totally clean environment. Every actionable setup/configuration step needs a real, readable screenshot. Numbered instructions with copyable commands/settings. Explain the purpose of the step, the expected result, and how to verify it. Clearly distinguish between Windows and Server commands and explain any placeholders (e.g., [YOUR_BUCKET_NAME]). Must cover: Prerequisites, code structure, AgentCore setup, memory/RAG routing, telephony settings, database/logs, AWS IAM/security, tests, monitoring, recovery, updates, cost breakdown, and complete environment cleanup. Include exact software/library versions and architecture details. Do not include real secrets/passwords in the doc. Include a section on common errors and fixes. 2. Narrated MP4 Videos: Follow the exact section/step numbers of the .docx manual. Include a timestamp index. Show the actual, complete setup from scratch (no skipped prerequisites or undocumented pre-configuration). Demonstrate application features, parallel-dialogue tests, and a security assessment showing the strict .txt file isolation. Note: Videos, screenshots, and code must match perfectly. 3. Handover & Teaching: A session (or clear video guidance) teaching me how to modify both the Python application codebase and the Python test suite. Acceptance Criteria The project will be considered successful and complete only when I am able to reproduce the entire project by myself, from scratch, in my own AWS account, relying entirely on your .docx manual and videos without needing to ask you for missing steps.
Project ID: 40755491
65 proposals
Remote project
Active 5 days ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs

Hi, I read the full requirements carefully. I can build this as a clean, reproducible Python/AWS project not just a demo. The implementation will include the Bedrock AgentCore voice agent, Canadian phone integration, dynamic .txt skill routing, per-call session memory, strict knowledge isolation, detailed logging, and reproducible deployment with no dependency on my AWS account after handover. I’ll also provide the editable step-by-step .docx manual with real screenshots, tests, troubleshooting, security/IAM setup, cost/cleanup instructions, plus narrated videos matching the documentation. For the voice layer, I can evaluate Twilio vs AWS-native options and use the most practical low-cost approach while keeping the architecture easy to reproduce. Estimated effort for the complete scope: approximately 50–70 hours. I’m comfortable with Python, AI agents, APIs, AWS architecture, RAG/routing logic, and production-style testing/documentation.
$20 CAD in 3 days
0.0
0.0
65 freelancers are bidding on average $180 CAD for this job

Hi, I can build your AWS Bedrock AgentCore voice agent in Python: a phone number per store, caller ID detection, the agent asking what the caller needs and then loading the matching .txt skill file (e.g. "Refrigerator abc123" for Store 3), and low-cost OpenAI or Gemini models behind it. I'll add the Gmail admin flow for adding or removing skill files, emailed conversation logs and incoming-number blocking, all set up through the AWS console with no Terraform, as you asked. Since this is educational, you'll get step-by-step documentation and walkthrough sessions so you can rebuild and deploy it yourself from your Windows machine. To be upfront, the full scope is larger than this budget, so I'd suggest we agree on a working core first and plan the rest in milestones. I build AI agent and RAG systems, including my own DocSense document AI platform. Manoj Synetal Solutions
$30 CAD in 14 days
6.6
6.6

Hi, I'm Denis, a full-stack developer with experience building voice AI systems on AWS, including multi-tenant routing and dynamic knowledge retrieval. You need an educational voice agent system where stores run their own phone-based AI assistants with strict isolation between skill files and call data. Each agent loads the right knowledge files based on caller input, maintains context during calls, and logs everything. The core challenge is teaching you to build and modify this yourself from a clean AWS account. I would start by confirming scope and budget, then build the Python application using AWS Bedrock AgentCore and Amazon Connect for telephony. The system includes agent registry setup, session memory handling, and file isolation enforcement. I'll provide a complete .docx manual with numbered steps, screenshots, and clear explanations. Then I'll record narrated videos following the manual exactly, demonstrating setup from scratch and testing isolation and memory features. Finally, I'll create a teaching video on modifying the application code and test suite. Documentation quality is critical—unclear or missing steps mean you cannot reproduce it alone. I'll build this step-by-step with your feedback, testing the manual and videos myself to catch gaps before delivery. I can start immediately. Let's discuss the details. Thanks, Denis.
$30 CAD in 1 day
6.1
6.1

Hi there, I am excited about the opportunity to work on your AWS AgentCore Python Voice AI Agent project. With extensive experience in AWS, Python, and AI voice applications, I am well-equipped to deliver a robust and scalable solution tailored to your educational needs. Understanding your requirements, I will build a multi-tenant voice agent system using AWS Bedrock AgentCore, designed to handle diverse customer service scenarios across multiple stores. By integrating AWS services such as Amazon Connect, I will ensure seamless voice interaction, while maintaining strict data isolation for each agent. My approach will focus on creating a system that not only meets your technical specifications but also serves as a comprehensive learning tool, empowering you to reproduce, modify, and deploy the solution independently. I am committed to providing detailed documentation and instructional videos, ensuring each setup step is clearly illustrated and easy to follow. This will include a thorough walkthrough of the Python codebase and test suite modifications, enabling you to customize the application as needed. Your project's success is my priority, and I am dedicated to delivering a solution that aligns with your objectives and provides lasting value. I look forward to collaborating with you and achieving your project goals. Best Regards,
$10 CAD in 2 days
5.4
5.4

Hey, I understand that you want a fully working, multi-tenant Voice AI Agent platform where each Canadian phone number maps to one store/agent and dynamically loads only the relevant .txt skill for the caller’s request. I’d build this in Python with AWS Bedrock AgentCore, Amazon Connect, AWS storage/database services, and an appropriate low-cost LLM such as OpenAI or Gemini, keeping each tenant’s data isolated through explicit authorization and scoped resource access. I’ll keep the infrastructure simple and browser-manageable as requested, avoid Terraform, and provide automated tests for routing, session memory, concurrent calls, permissions, phone identification, and strict .txt skill isolation. Questions: For dynamic skill selection, how should the system identify the correct .txt file when a caller's request could match multiple skills? Should the agent use semantic search/RAG to select the best match, or do you want a more deterministic skill registry where each file has predefined keywords, descriptions, or metadata? How should the caller phone-number identification work when a caller’s number is hidden, unavailable, or not previously registered? Should the system simply identify and display the incoming number, or should it also maintain caller profiles/history that administrators can view and manage? Let's connect for a brief chat or call to discuss your project in detail. **Budget and Duration are placeholders. Kind Regards, Royal Design
$2,000 CAD in 7 days
5.0
5.0

Hello, I can build the voice AI agent using AWS Bedrock AgentCore with strict data isolation and session memory, avoiding common pitfalls like shared knowledge files or lost context. I’ve set up a similar multi-tenant system for a client using separate S3 buckets for each tenant’s knowledge files and DynamoDB for session tracking—this kept data isolated while maintaining fast responses. I’d approach this by creating dedicated Lambda functions for each store’s knowledge files, using DynamoDB for session memory, and routing calls through Amazon Connect with unique phone numbers. Proper isolation will ensure Store 1’s skills never leak into Store 3’s sessions, and session memory will keep context during calls. I’ll also log all interactions to CloudWatch for debugging. This setup will let you scale from 0 to 100+ agents without cross-contamination, and the strict separation will make future updates easier. Once the project is done, I’ll review the manual and videos with you to confirm everything works as expected. If this aligns with your needs, I’d be happy to discuss the details further. Thanks, Lazar.
$10 CAD in 1 day
4.1
4.1

Is the agent meant to run on Lambda or EC2, and are you using Bedrock or OpenAI under the hood for the voice model? I have built phone IVR flows with AWS AgentCore and Python before, handling the Linux deployment side too. Can start today and have a working test agent ready in 3 days. Budget and timeline here are rough based on the post, we will lock them in once we talk through the full scope. Let me know and I will send a plan.
$30 CAD in 4 days
4.1
4.1

I WANT TO DO THIS TO KEEP IN MY PORTFOLIO noticed your requirement and here is my understanding - A multi-tenant voice AI agent system on AWS using Amazon Connect and Bedrock AgentCore with dynamic RAG routing, strict data isolation, and email-based admin controls. Python, AWS Bedrock AgentCore, Amazon Connect, OpenAI/Gemini APIs. I've gone through your requirement for a voice AI agent builder and mentorship project. I can build this with your preferred stack - Python, AWS Bedrock AgentCore, Amazon Connect - with clean, scalable codebase within 7 days. Milestone 1: Core Architecture & Telephony Setup (AWS Console configuration, Amazon Connect Canadian phone number provisioning, S3 data isolation structure, and Bedrock AgentCore integration). Milestone 2: Dynamic Skill Routing, Admin Email Interface & Documentation (Contextual .txt skill loading per store, Gmail admin integration for file management/logs, and creation of the exhaustive .docx manual and narrated MP4 video suite). Let's review target timelines and map core milestones. I may have few questions before suggesting full architecture. Lets hit CHAT and discuss now ! Gaurav P. 15 yrs experience in debugging systems :)
$49 CAD in 2 days
4.2
4.2

Hi, I see you're looking to build a Voice AI Agent using AWS Bedrock AgentCore, and I think the key challenge here is ensuring strict data isolation between agents, so I'd approach this by setting up separate AWS resources for each agent. I'll use Python to develop the agent's core functionality, and I'll integrate it with Amazon Connect for telephony services. I'll also make sure to use low-cost models from OpenAI or Gemini for the LLM. I've worked on similar projects where the common mistake is not properly handling session memory, so I'll make sure to implement a solution that retains context during the call, but doesn't retain any information between sessions. I'll also set up detailed logging for every individual call, and I'll provide a manual and videos that cover every step of the setup and configuration process, so you can easily reproduce the project in your own AWS account. You can expect a fully working example system, exhaustively documented, and a handover session that teaches you how to modify and deploy it independently.
$20 CAD in 7 days
4.1
4.1

Hello there, I am excited about the opportunity to develop the AWS Voice AI Agent architecture for your educational project. With extensive experience in AWS services, Python development, and voice integration, I am well-equipped to build the scalable multi-tenant system you envision. I understand the importance of a detailed and user-friendly documentation process, and I will create a comprehensive manual with actionable steps, clear screenshots, and videos that mirror each section of the guide. I will ensure the architecture maintains strict data isolation and that each agent operates independently with its context retained only during the call. I have successfully worked on similar projects, utilizing AWS Bedrock AgentCore and Amazon Connect, ensuring a smooth user experience while adhering to your project constraints. My approach will prioritize testing and security, providing you with a reliable system that you can modify and deploy independently. I would love to discuss the project scope further and how I can help bring your vision to life. Thank you for your time, Ihsan.
$20 CAD in 7 days
3.3
3.3

Hello, Please share the exact AgentCore/Connect configuration you want demonstrated, preferred low-cost LLM, and any existing architecture or GitHub references so I can start immediately. I can build the Python voice-agent prototype with isolated per-store knowledge, dynamic skill routing, session memory, caller identification, call logging, admin file management, phone blocking, and AWS-based deployment. I can deliver the agreed prototype within your budget and timeline, with clean source code and clear setup guidance for independent deployment. Best Regards, Sara
$170 CAD in 1 day
3.4
3.4

With a stringent focus on understanding and delivering the client's requirements, I have successfully built various scalable Voice AI architectures powered by AWS such as your project entails. My profound expertise includes Python development and making the best use of Amazon App Development services to create functional, efficient, and user-friendly systems. As your educational project aims at not just developing an AI Agent but also documenting the process to ensure complete self-reliance post-hire, I'm confident that my communication skills and thoroughness in preparing detailed documentations - be it through videos or comprehensible instruction manuals - will prove a valuable asset for this project. My technical stack deeply resonates with yours: Python for backend development; AWS infrastructure for deployment; and Amazon Connect integration for telephony purposes. Moreover, having excelled in creating zero-dependency applications that don't require my credentials after deployment, I assure you that your AWS account and API keys will remain confidential while delivering impeccable results. Let's chat further to discuss harnessing all my skills to make this educationally-focused endeavor an absolute success!
$10 CAD in 7 days
2.8
2.8

Hi there I can help build your educational Python + AWS Bedrock AgentCore voice AI system, integrating Amazon Connect for Canadian phone numbers and natural-sounding voice responses. I’ll design a multi-tenant agent registry with isolated store-specific `.txt` skill files, dynamic skill selection, session-only memory, detailed call logs, and secure access controls. For low-cost LLMs, I’d evaluate suitable OpenAI or Gemini models alongside AWS Bedrock options based on latency, quality, and integration requirements. I’ll focus on reproducible deployment through the AWS Console and local Windows development, without Terraform, and provide the source code, automated tests, editable Word manual with screenshots, narrated setup videos, cost guidance, and a structured handover session. All resources and credentials will be replaceable with your own, and I’ll include security tests proving that agents cannot access another store’s knowledge files. We can agree on milestones after confirming the phone integration and documentation scope. Best regards, Abdul Rehman
$25 CAD in 7 days
2.6
2.6

Hi there! You need a fully reproducible AWS voice AI system where each store has strict data isolation, dynamic skill loading, natural phone conversations, and clear teaching material. The biggest challenge is making the whole setup easy to rebuild from a clean AWS account without hidden dependencies. I have experience with Python, AWS, AI integrations, voice agent workflows, Amazon Connect, Bedrock, IAM, logging, testing, and cloud application development. I can build the project with low-cost OpenAI or Gemini models where suitable and focus on natural voice quality. I will build the multi-tenant agent registry, phone routing, session memory, dynamic TXT skill selection, strict file isolation, call logging, and security testing. I will use simple AWS console based deployment as requested, without Terraform, and test the complete flow in my own authorized environment. I will also prepare the Word manual with screenshots, commands, versions, verification steps, troubleshooting, costs, cleanup, and security details. The narrated videos will follow the same numbering and demonstrate setup, testing, isolation, and modification so you can reproduce everything yourself. check our work https://www.freelancer.com/u/ayesha86664 Would you like the first prototype to focus on one store and one phone agent before expanding to the 100+ agent architecture? Let me know if you’re interested & we can discuss it. Best Regards Ayesha
$20 CAD in 3 days
2.5
2.5

Hello, there. Good to meet you. I’m excited about your educational project focused on building a scalable Voice AI Agent using AWS Bedrock AgentCore. I can help you create a multi-tenant voice agent system with strict data isolation and a detailed logging mechanism, ensuring each agent only accesses its dedicated knowledge files. This project aligns perfectly with my skills in AWS and Python development, and I can deliver it within your timeline while ensuring 100% accuracy. I encourage you to review my profile to see my relevant experience. To recap, you need a robust voice AI agent system for various stores, with the ability to dynamically load skill files based on user input. Additionally, the system must handle session memory and logging for each call, ensuring a smooth user experience. I will provide comprehensive documentation, including a detailed manual and narrated videos, to facilitate your understanding of the setup process. I’m eager to collaborate with you on this project, as timely communication will be key to our success. Thank you for your time, Predrag
$20 CAD in 7 days
1.9
1.9

Building a scalable Voice AI Agent architecture with AWS Bedrock AgentCore is well within my expertise as a Full-Stack Software Engineer. I have significant experience with Python, AWS services, and cloud infrastructure setups, which will ensure a robust solution for your multi-tenant voice agent system. My approach will involve designing an architecture that meets your requirements for voice integration, strict data isolation, and session memory. I will document the entire process in a clear manual and create screencast videos to ensure you can independently reproduce the deployment. For a similar project, I developed an AI-powered assistant with stringent data handling, and you can view that in my portfolio. I would start by outlining the project scope and system architecture to ensure we achieve your vision effectively. What is your preferred method of voice integration for the phone system?
$10 CAD in 1 day
1.5
1.5

Hello, I understand you need an educational AWS Bedrock AgentCore + Python voice AI system supporting multiple isolated store agents, Canadian phone numbers, dynamic TXT skill selection, session memory, detailed logging, and complete from-scratch documentation. The goal is to make the architecture fully reproducible in your own AWS account without dependency on my resources. Here’s what I can provide: Python + AWS AgentCore voice-agent architecture with Amazon Connect and natural voice integration. Multi-tenant agent registry with strict per-store TXT knowledge isolation, session-only memory, dynamic skill routing, logging, security, and scalable agent management. Complete testing, AWS deployment, security validation, clean source code, step-by-step DOCX manual, narrated setup videos, and handover training. I bring over 4+ years of experience in Python, AWS, AI integrations, cloud architecture, and automation, focusing on secure, scalable, and well-documented systems. Just to clarify a few things: Do you have a preferred low-cost OpenAI/Gemini model, or should I benchmark suitable options? Should the 100+ agent registry be managed through a simple web-based admin interface? Please come to the chat box to discuss more about your project. Best regards Indresh Kushwaha
$20 CAD in 7 days
1.6
1.6

Hello, I checked your project "AWS AgentCore Python phone Voice AI Agent" and already have a clear understanding of your requirements and how to deliver them efficiently. I have solid experience in Python, and I've successfully completed similar projects by delivering high-quality, scalable, and reliable solutions. Why choose me? * Strong expertise in Python * Clean, optimized, and scalable implementation * Fast communication and regular progress updates * Focused on delivering results, not just completing the task I'm ready to start immediately and would be happy to discuss the details. Best regards, Umer
$25 CAD in 1 day
1.2
1.2

With over 15+ years of hands-on experience in building scalable applications and automating complex workflows, I am confident that I possess the skills and expertise required to execute your educational AWS AgentCore Python project successfully. Having delivered 150+ projects, I have honed my ability to transform ideas into powerful digital products. My core skills in Artificial Intelligence, Python and AWS are an ideal match for your requirements. My proficiency with AWS services, could be used to develop and deploy a multi-tenant voice agent system tailored to your unique needs while ensuring strict data isolation. I'm conversant with the AWS Bedrock AgentCore that as the AI framework of choice for this project. Regards Yasir A
$20 CAD in 7 days
1.0
1.0

Dear Client, I can see the challenge is to build a scalable Voice AI Agent architecture using AWS Bedrock AgentCore, with strict data isolation and zero dependencies on external accounts or resources. I will implement this using a modular architecture with clear data flow and logic, ensuring that each agent has its own dedicated group of .txt knowledge files and strict data isolation. I will use AWS services compatible with AgentCore, such as Amazon Connect, and Python as the programming language. I will also implement session memory to retain context during the call and generate detailed logs for every individual call/session. The deliverables will include an editable Word manual, narrated MP4 videos, and a handover session teaching you how to modify both the Python application codebase and the Python test suite. I have extensive experience with AWS and Python, and have successfully implemented similar projects in the past. I can start immediately. Best Regards.
$10 CAD in 7 days
0.0
0.0

Hello, I'm Justin, your Senior Full-Stack Engineer with extensive experience in Python, making me the ideal candidate to tackle your AWS AgentCore Python phone Voice AI Agent project. As you can see from my repeated mention of Python, it is a language I have mastered and applied in numerous projects throughout my career. My expertise in this language will enable me to build a highly efficient and scalable Voice AI Agent architecture using the AWS Bedrock AgentCore. Moreover, the educational nature of your project resonates deeply with my passion for knowledge sharing. Over the years, I've consistently demonstrated my ability to not only deliver high-quality projects but also effectively train others on how to independently reproduce and modify these systems. This aligns perfectly with your goal of me building a fully-working example system and then mentoring you on how to use and deploy it from scratch. Another area where I excel is in documentation. As part of your essential deliverables, I will provide an editable Word manual that will be thorough, concise, and easy to follow. It will cover every critical aspect from setup to cost breakdown, without compromising On security by disclosing real secrets or passwords. When you choose me for this project, rest assured that I'll exceed your expectations on all fronts; coding, documentation, training, and handover session! Thanks!
$10 CAD in 2 days
0.0
0.0

Downsview, Canada
Payment method verified
Member since Nov 29, 2017
$10-30 CAD
$10-30 USD
$30-250 CAD
$10-30 USD
$10-30 CAD
₹1500-12500 INR
€30-250 EUR
₹75000-150000 INR
$750-1500 AUD
₹12500-37500 INR
$250-750 USD
min $10 USD
$30-250 USD
$10-30 USD
$30-250 USD
₹2500000-5000000 INR
₹600-1500 INR
$30-250 USD
₹37500-75000 INR
$30-250 USD
₹37500-75000 INR
₹1000-3000 INR
$250-750 USD
$250-750 USD
$30-250 USD