
Closed
Posted
Paid on delivery
Summary Job Title: phone voice AWS AgentCore agent coded in Python 5 days to do Job Type: Fixed-Price Very good natural voices for LLM use low cost fast models from openai or gemini or make suggestion **** No Terraform or similar techniques, only simple browser aws platform development *** use AWS from local windows Project Overview **** Develop Voice Real Estate agent (sell homes) **** For testing provide realistic properties descriptions from [login to view URL] or [login to view URL] or [login to view URL] etc. convert property web page to text extract Neighbourhood description and statistics Like example https://www.realtor.ca/real-estate/30180444/829-55-stewart-street-toronto-waterfront-communities-waterfront-communities-c1#view=stats https://www.realtor.ca/real-estate/30180444/829-55-stewart-street-toronto-waterfront-communities-waterfront-communities-c1#view=neighbourhood [login to view URL] 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. looking for a multi-tenant Voice AI platform where 0-10 separate store agents can be created and managed, each with its own Canadian phone number, isolated skill files, call memory/logs, and admin management, built on AWS Bedrock AgentCore + Python, along with complete documentation, videos, testing, and handover. You may use existing open-source GitHub projects as a foundation, provided the final deliverable meets all my requirements and is fully documented. agent answer questions about properties and persuade user to buy and book viewings intergrade some useful booking service and send message by email and sms text to both user and realtor full log such call is transcribed and session logs System Architecture & Core Examples We need a one Canadian phone voice agent system acting as customer service 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 The Use-Case Examples: Think of these as sales agents for stores or services , where store has many unique products, for example : Or Case 1: Food Catering Or case 2: Cleaning Services Or case 3: Refrigerator Repair Or case 4 : Real Estate agent (sell homes) 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 add to system prompt ). Example A (Case 3): A user calls 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 (Case 2): A user calls 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. Example C (Case 3) : user wants to talk about specific home for sale . Find skills file with specific address what user tells you . Each .txt file has header with description what is this file about , then agent find which file header matches the beset to user request , if bad matching happen then during conversation with user it should be found correct match , etc . Usual skills router implementation Technical Features & Requirements Voice Integration: Phone call voice chat using a Canadian phone number (+1). One phone number serves exactly one agent/store. Strict Data Isolation: agent has its own dedicated group of .txt knowledge files. 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: use Amazon Connect - low cost AWS services compatible with AgentCore , I am open to discuss other options like Chime SDK, or Twilio Phone call with interruption option 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 LLM credentials (openai or gemini ). Zero Dependencies: My later deployment must not depend on your accounts, resources, or API keys. Use openai or gemini for LLM (I am open for suggestions for other good LLM providers ) 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. just idea Phone provider: Twilio can't connect directly to AgentCore, because its stream address doesn't allow the login signature AgentCore needs. Vonage can, and AWS and Vonage have a sample that works with real phone calls, so I planned to use Vonage. Voice code: the Pipecat library (version 1.12) has everything we need in Python. It handles Vonage audio, Transcribe, Polly and OpenAI, and it can change the system prompt during a call, which is what your situation-based prompt needs. OpenAI on AWS: GPT-5.6 Luna can be called through Bedrock from Canada (Central). Requests go to Canada or US regions. Deploy tool: AWS has replaced the old Python agentcore command with a new one installed through npm (@aws/agentcore). [login to view URL]
Project ID: 40755654
109 proposals
Remote project
Active 5 hours ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
109 freelancers are bidding on average $112 CAD for this job

Hello I checked your project and the main point is to build a reproducible Python voice real estate agent on AWS Bedrock AgentCore, with Canadian telephony, dynamic TXT skill routing, isolated store data, call memory, transcripts, booking, and complete training materials. In the past I built Python and AI systems involving document processing, data extraction, session-based workflows, and OpenAI integrations. I can also work with property page content, extracting neighbourhood descriptions and statistics into structured knowledge files. I would build the voice flow with AgentCore, Python, Vonage or Amazon Connect, and Pipecat, then connect transcription, natural voice responses, interruption handling, and a low-cost LLM. Each call would receive isolated session memory, while the router selects the best matching property or service TXT file and stores detailed logs securely in AWS. I’ll also prepare the Windows setup, IAM configuration, tests, security checks, editable DOCX manual, screenshots, narrated videos, and clean deployment handover so the system can be recreated in your own AWS account. Could we have a short conversation to confirm the preferred telephony path, the booking service, and whether property data should be imported manually or refreshed from the selected real estate pages? Best regards
$20 CAD in 5 days
7.6
7.6

Hi, I'm Denis, a full-stack developer. I've built voice AI systems on AWS handling multi-tenant routing, dynamic knowledge retrieval, and session logging at scale. You need a working voice agent for real estate calls that routes to the right property files, books viewings, logs everything, works from a Canadian number, isolates caller data, and lets you rebuild it independently later. I'd start by setting up AWS Bedrock AgentCore with Amazon Connect for phone integration, then build a Python application with dynamic skill file routing based on caller intent. Next, I'd add session memory persisting only during calls, integrate email and SMS booking confirmations, and build transcription and logging. Finally, I'd test end-to-end and create complete documentation. The core challenge is the skill file router: when callers mention a property or service, the agent must find and load the right .txt file and use it throughout that session. I'd parse caller input, match it against file headers, and confirm during conversation if needed. One realistic risk is that property data may be incomplete or change frequently, so I'd build the system around manually curated files you control. I can start immediately. Let's discuss the details. Thanks, Denis.
$30 CAD in 1 day
6.0
6.0

Hi — I reviewed your project “phone voice AWS AgentCore agent coded in Python” and it lines up well with my hands-on work in AI agents, LLMs, RAG and OpenAI. I build AI agents, LLM/RAG pipelines, and document/OCR workflows with clean APIs and practical automation. DocSense-style document intelligence experience may apply here. Happy to align on scope, timeline, and a first milestone as soon as you are ready. Manoj, Synetal Solutions
$30 CAD in 3 days
5.7
5.7

With my rich knowledge and proficient skills in Amazon Web Services and Python, the completeness of your project suggestions resonates deeply with my experience. Having worked in the backend development sector for half a decade, I am well-versed in executing AWS projects, developing serverless applications and adopting containerized frameworks with ease. Hence, using AWS from a local Windows environment would not be any problem for me. My DevOps expertise will come in handy for ensuring complete data isolation for each agent's dedicated .txt knowledge files. Proposing a multi-tenant Voice AI platform where as many as 10 separate agents can be managed simultaneously aligns seamlessly to my previous work of deploying high-traffic containerized applications on platforms like AWS EKS. Lastly, my AI/ML Integration skills will help integrate low-cost fast models as per your choice or suggest suitable models from open AI or Gemini for "simple browser AWS platform development." Efficiently exploiting AWS AI/ML services such as Textract, Comprehend, Kendra, and Rekognition is another standout factor to bring more intelligence into your Voice Real Estate Agent system. To sum it all up, I am well-equipped to ensure an excellently-developed architecture,detailed project documentation and most importantly offer knowledge transfer so that you can independently modify and utilize this system in future without any hitches. Let's get started and build an efficient Voice AI Agent together!
$30 CAD in 7 days
5.6
5.6

Hi there, I am excited to submit my proposal for your project on developing a phone voice AWS AgentCore agent coded in Python. With extensive experience in Python and AWS services, I am well-equipped to create a scalable Voice AI Agent architecture tailored to your needs. I understand that this project is fundamentally educational, aiming to build a robust system while documenting every step for easy reproduction and independent deployment. My approach will utilize AWS Bedrock AgentCore, ensuring strict data isolation and efficient session memory handling. By leveraging low-cost, fast models from OpenAI or Gemini, I will ensure optimal performance while keeping costs manageable. I am familiar with integrating telephony solutions like Amazon Connect and am open to discussing alternatives like Chime SDK or Twilio for seamless voice interactions. I will focus on creating a multi-tenant platform where each agent can manage its unique skill files, call logs, and communication channels. The system will allow for dynamic skill file retrieval, ensuring accurate and contextually relevant interactions with users. Detailed logging and comprehensive documentation will guarantee transparency and ease of use. My deliverables will include an exhaustive manual with clear instructions and narrated videos to guide you through the entire setup and modification process. I am committed to providing a solution that meets your requirements and empowers you to manage and expand the system independently. Best Regards,
$10 CAD in 2 days
5.4
5.4

Hi. To build this educational voice real-estate agent, I would structure a Python service around AWS Bedrock AgentCore, Vonage audio streaming, Pipecat, Amazon Transcribe, Polly, and a cost-efficient LLM provider. The system would route each caller to an isolated store and dynamically select the correct property or service skill file, while preserving session-only memory and complete transcripts. I would implement booking, email/SMS notifications, caller blocking, admin file management, tenant isolation, and searchable call logs using practical AWS services configured through the console. As a Senior AI Engineer, I have mastered Python, AWS Bedrock, AgentCore-style agent orchestration, RAG routing, telephony integrations, and secure multi-tenant systems, with strong experience in voice assistants, customer-service automation, and technical handover projects. The deliverable would include reproducible source code, tests, security validation, an editable Word manual, narrated setup videos, cost guidance, cleanup procedures, and a handover lesson focused on independent deployment. I am sure I can deliver high-quality results within the requested five-day timeline for a focused working example and clearly staged educational handover. Let’s get in touch and discuss more. Thanks.
$30 CAD in 5 days
5.1
5.1

Hello, I can build the Python-based AWS Bedrock AgentCore voice real-estate agent with the documented, reproducible architecture you require. I understand the key requirement is not only a working phone agent, but a complete system you can independently recreate, modify, test, and deploy from a clean AWS environment. I can implement the Canadian phone integration, natural voice conversation with interruption handling, property knowledge routing, per-store .txt skill isolation, session-only memory, call transcription/logging, booking workflow, and email/SMS notifications. Python with AgentCore and Pipecat can provide a practical foundation, with the telephony layer selected around AgentCore compatibility. I will also structure the project for multi-tenant agents, secure IAM, isolated knowledge files, blocked numbers, admin management, testing, monitoring, and cleanup. The documentation and videos will follow the actual implementation step-by-step, including screenshots, commands, versions, troubleshooting, security testing, and complete handover within the 5-day target. Looking forward to work with you. Thanks
$15 CAD in 7 days
5.0
5.0

Hi, Thank you for posting your project. Your phone voice AWS AgentCore agent coded in Python is exactly the type of project I excel at. I have the experience and dedication to make it a complete success. I've completed 50+ projects involving Python, Amazon Web Services. I'd love to share case studies that demonstrate my ability to deliver on phone voice AWS AgentCore agent coded in Python. Thank you for the opportunity to bid on phone voice AWS AgentCore agent coded in Python. I'm confident we can create something amazing together. Regards, Manisha
$20 CAD in 1 day
4.3
4.3

With my extensive experience spanning over 8 years in the realm of Full-Stack Software Engineering and Applied AI development, I possess the required skills in both AWS and Python to deliver exceptional work for your Voice AI Real Estate Agent project. Over the years I have successfully completed several complex projects like e-commerce and food-delivery platforms along with developing cloud storage systems, car-sharing applications and property rental platforms. These projects required me to build scalable solutions while ensuring reliable and optimized performance - exactly what you need for your multi-tenant Voice AI platform. In particular, my AI prowess extends to working with low-cost fast models from OpenAI and similar platforms that match the type of voice model you require. A notable example is my experience with LLM applications using Hugging Face, OpenAI's Text-to-Speech TTS-service, allowing for a seamless integration of a natural, realistic voice within your architecture. Lastly, what sets me apart is my strong emphasis on documentation through videos, exhaustive documentation and handover which will ensure that you can independently reproduce, modify, and deploy the system whenever necessary in the future. So let's bring our ideas together, leverage my expertise in AWS Bedrock AgentCore+Python configuration, and build an impressive system that gives you complete control over your Voice AI agents.
$20 CAD in 1 day
4.1
4.1

Hello, I can build a scalable voice agent system using AWS Bedrock AgentCore and Python, with strict data isolation and session memory for multi-tenant use cases like real estate or catering. I built a similar system for a SaaS client—used Amazon Connect for telephony and DynamoDB for session logs, which reduced call processing time by 30% while keeping costs low. I’d approach this by structuring the agent with isolated .txt knowledge files per tenant, using AgentCore’s built-in routing to dynamically load the correct skill file based on user input. The biggest challenge will be ensuring seamless memory between calls while preventing data leaks between tenants. Proper setup will reduce support requests by 70% by making the system self-documenting through clear logs and error handling. I’ll provide a detailed manual with screenshots and videos covering every step, including error recovery and cost optimization. After delivery, I’ll walk you through modifying the code and tests to ensure full independence. If this aligns with your needs, I’d be happy to discuss the project further. Thanks, Lazar.
$10 CAD in 1 day
3.7
3.7

Phone voice agents on AgentCore are still fresh enough that most bids here are guesswork. I have built Python backends wired into AWS services before and can set up the AgentCore runtime, hook in the voice pipeline, and get a working call flow tested within 3 days. Budget and timeline above are starting points based on the summary, we will lock in real numbers once I see the call flow you need. Want me to send a quick scope doc?
$30 CAD in 4 days
3.7
3.7

Hello, Thanks for sharing your project. I've strong technical skills and rich experiences as your needs. I'm delivering a high-quality result, on time, and as quickly as possible without cutting corners. I’ll work efficiently to complete your project perfectly. Let’s hop on a quick chat to clarify details and get started. Looking forward to building something great together! Best Regards.
$30 CAD in 30 days
3.2
3.2

Hello, Please share the preferred LLM, AWS/AgentCore configuration, property data sources, and booking/SMS/email services you want to use so I can start immediately. I can build the Python voice real-estate agent with Canadian phone integration, property-data extraction, intelligent skill-file routing, session memory, call interruption, booking notifications, full call transcription/logging, and strict knowledge isolation. I can deliver the agreed working prototype within your budget and 5-day timeline, with clean source code, testing, and deployment documentation. Best Regards, Sara
$120 CAD in 1 day
3.4
3.4

Hi - Adelman here from Texas "PHONE VOICE AWS AGENTCORE AGENT" - you need a reproducible Python voice agent with isolated property skills and clean call memory. I’d keep the first build simple: Amazon Connect handles calls, Python handles the AgentCore routing, and each session gets isolated skill context and logs. For the real estate test, I’d parse the property page into structured text so address, neighbourhood, statistics, and listing details can be matched reliably. The key edge case is wrong skill matching: the router should be able to reject a weak match and ask a short clarification instead of exposing another store’s files. I’d also test concurrent calls to verify tenant and session isolation. Which telephony option do you want me to use first, Amazon Connect or Twilio? Looking forward to work with you.
$20 CAD in 1 day
3.0
3.0

Hi Peter, Albert here, from Philippines. Building your phone voice AWS AgentCore agent coded in Python with Bedrock is doable; what matters most is answers people can trust, at a running cost that stays predictable. I'm a senior AI developer with 10+ years of experience working with Python and AI Automation. For your phone voice AWS AgentCore agent coded in Python, the real challenge is wrong answers and prompt injection. A common issue: launching without guardrails or a test set, so nobody knows how often it is wrong. My plan: first, collect real examples and write down the expected result for each. Then, build the AWS pipeline with guardrails and logging. Finally, score it against those examples and tune it before launch. I'd start with the core assistant and its test set as phase one. I've done AI work in Python. A few questions to better understand the scope: 1. Should it refuse questions outside your own data? That rule stops most of the made-up answers. 2. Hand off to a person when it is unsure? I'd recommend it, handoffs beat wrong answers. 3. Do users write in more than one language? Answer quality often drops outside of English. I can start right away. Happy to go over the details here in chat and suggest the best approach. Looking forward to hearing from you, Albert
$20 CAD in 1 day
2.7
2.7

Hi there! You need a reliable AWS Python voice agent that can handle real estate calls naturally, answer property questions, qualify buyers, and help book viewings. I have experience with Python, AWS, AI integrations, voice workflows, APIs, session memory, RAG, logging, and cloud deployment. I can build this with Bedrock AgentCore and use a cost-effective LLM such as OpenAI or Gemini based on speed, quality, and cost. I will create a skills router to identify the correct property file from the caller's request and keep that context during the call. Property data can be converted into structured text, with secure transcripts, caller IDs, session logs, and phone blocking. I will also connect booking, email, and SMS workflows for viewing requests and call summaries. The system will support interruptions, isolated agent data, and scalable multi-agent management. I will provide Windows setup, AWS configuration, testing, screenshots, documentation, videos, and handover so you can reproduce everything in your own AWS account. check our work https://www.freelancer.com/u/ayesha86664 Do you already have a preferred booking and SMS provider? Let me know if you’re interested & we can discuss it. Best Regards Ayesha
$20 CAD in 3 days
2.5
2.5

Hi, I’m a strong fit for this project with experience in Python, AI agents, RAG, embeddings/vector search, LLM APIs, FastAPI, PostgreSQL, webhooks, Docker, AWS, logging, testing, and knowledge-base processing. I understand the core architecture: each phone number maps to one store/agent, each agent has isolated .txt skill files, and every call gets isolated session memory and detailed logs. I can implement the skill-routing flow so the agent identifies the caller’s intent, selects the best matching knowledge file, and uses it throughout the session. I’m comfortable working with the proposed Python/Pipecat, telephony, AWS, Transcribe, Polly, and LLM architecture, while validating the actual integration rather than assuming compatibility. I’ll also focus on tenant isolation, webhook reliability, call transcription/logging, security, testing, deployment, and ensuring the final system does not depend on my AWS accounts or credentials. I can provide the source code, reproducible setup documentation, tests, screenshots, narrated videos, and handover required for independent deployment. I’m available to start immediately and can review the acceptance criteria before confirming the 5-day delivery plan. Best regards, Abdelhafid
$80 CAD in 7 days
2.0
2.0

Dear Client, I can build this as a Python-based AWS voice-agent reference system with the emphasis on reproducibility, isolation, testing, and teaching, not just a one-off deployment. My background is in Python, AI agents, APIs, RAG/workflow orchestration, AWS, logging, retries, and production automation. My approach would be to prove one complete real-estate agent first: Canadian phone number → voice conversation → skill-file routing by property/address → session-only memory → booking → SMS/email notifications → transcript/log storage. Then I’d generalize that into a multi-tenant structure where each store/agent has isolated skill files, phone identity, logs, admin controls, and configuration. AgentCore currently provides managed Runtime, Memory, Identity and Observability capabilities, including CloudWatch metrics/traces, which fits the architecture well. I’d use console-driven AWS setup as requested, avoiding Terraform. I’ve built 10+ multi-step AI workflows with tool execution, conditional routing, persisted state, retries, and observability. I have strong OpenAI/AWS experience, but I won’t claim a previous production AgentCore telephony project if I can’t document one. Deliverables would include source, tests, deployment, editable DOCX manual with screenshots, matching narrated videos, cost/cleanup sections, security/isolation tests, and a handover session. I’d estimate 3days for a complete educational-grade implementation. Best, Vadim
$20 CAD in 2 days
1.7
1.7

With over 9 years of solid programming experience including proficiency in Python, I am excited to bring my expertise to this project as it perfectly aligns with my skill set. Building a Voice AI Agent architecture is a challenge I have always enjoyed undertaking and your project is no exception. As requested for this project, I will use my extensive knowledge of AWS to create a scalable, fully documented multi-tenant Voice AI platform leveraging AWS Bedrock AgentCore that meets all your unique requirements. Moreover, having worked on similar projects in the past has equipped me with great problem-solving abilities. My approach is rooted in using existing open-source resources like GitHub projects as a foundation and then tailoring them to surpass your expectations, which I believe can expedite the timeline here without compromising on quality or robustness. In addition to programming skills, communication and documentation are equally important for seamless system integration. With this in mind, I would provide you with extensive documentation and comprehensive training sessions designed specifically for easier understanding and future troubleshooting or modification. Together, we can craft an intelligent Voice Agent that flawlessly sells houses by extracting property information
$120 CAD in 7 days
2.0
2.0

Hello, I understand you need a Python/AWS Voice AI real-estate agent using AWS Bedrock AgentCore, Canadian phone calling, dynamic .txt skill routing, session memory, call logging, booking, SMS/email notifications, and complete documentation/videos. The goal is to deliver a reproducible, secure, and fully documented multi-tenant voice agent. Here’s what I can provide: • Python voice agent with telephony, interruption handling, LLM integration, and dynamic skill routing • Isolated knowledge files, session-only memory, transcripts, logs, booking, email/SMS notifications • AWS deployment, security, testing, Word manual, videos, source code, and handover I bring over 4+ years of experience in Python, AWS, APIs, backend development, and automation, with a strong focus on reliable and scalable applications. I can build and document the system so it can be reproduced independently in your AWS account. Just to clarify a few things: • Should I proceed with Vonage + Pipecat as the initial telephony/voice architecture? • Which booking service and email/SMS provider do you prefer for the MVP? 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

Downsview, Canada
Payment method verified
Member since Nov 29, 2017
$30-250 USD
$10-30 USD
$10-30 CAD
$30-250 CAD
$30-250 CAD
₹1500-12500 INR
$30-250 CAD
₹12500-37500 INR
$250-750 USD
$750-1500 USD
₹12500-37500 INR
$3000-5000 USD
$30-250 USD
₹1500-12500 INR
€30-250 EUR
$10-30 USD
$10-30 USD
$10-30 USD
$250-750 USD
₹600-1500 INR
₹750-1250 INR / hour
₹12500-37500 INR
₹750-1250 INR / hour
$3000-5000 USD
$30-250 AUD