You will get an AI client-intake agent prototype for your law firm
Project details
Every lead your firm misses after hours is a matter that signed with someone else. This project gives you a working AI intake agent — not a slide deck about one.
The agent interviews prospective clients in natural conversation, asks the questions your intake staff would ask, qualifies each matter against your criteria, and outputs structured case data ready for your systems. You get a working prototype you can test with real scenarios before committing to a full build.
Why me: I built and shipped a production agentic intake platform for a US personal injury firm — AWS serverless with Claude on Amazon Bedrock, writing qualified matters directly into the firm's legal CRM. I also hold two law degrees, so the agent asks questions like someone who understands what makes a matter viable, not a generic chatbot with a legal skin.
Confidentiality first: the prototype needs no client data and no system access — it runs on fictional test matters until you decide to integrate.
The agent interviews prospective clients in natural conversation, asks the questions your intake staff would ask, qualifies each matter against your criteria, and outputs structured case data ready for your systems. You get a working prototype you can test with real scenarios before committing to a full build.
Why me: I built and shipped a production agentic intake platform for a US personal injury firm — AWS serverless with Claude on Amazon Bedrock, writing qualified matters directly into the firm's legal CRM. I also hold two law degrees, so the agent asks questions like someone who understands what makes a matter viable, not a generic chatbot with a legal skin.
Confidentiality first: the prototype needs no client data and no system access — it runs on fictional test matters until you decide to integrate.
AI Algorithms
Large Language ModelAI Applications
AI Chatbot, Conversational AIAI Models
GPT-4What's included
| Service Tiers |
Starter
$499
|
Standard
$899
|
Advanced
$1,499
|
|---|---|---|---|
| Delivery Time | 10 days | 14 days | 21 days |
Number of Revisions | 1 | 1 | 1 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | - | - |
Detailed Code Comments | - | - | - |
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | - |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | - | - | - |
Setup File | - | - | - |
Source Code | - | - | - |
Frequently asked questions
About Masego
AI & Data Engineer | Python, AWS Serverless, Automation
Johannesburg, South Africa - 9:55 pm local time
Recent work: an AI intake agent for a US personal injury law firm — it interviews leads 24/7, qualifies the matter, and writes structured case data straight into the firm's CRM with zero manual entry. A lead capture and enrichment system that lifted lead-source conversion by 22.6%. A multi-tenant SaaS backend of 24 Lambda functions behind a Next.js admin dashboard, where new client organisations onboard through configuration rather than code changes.
What I build: AI agents and LLM integrations (Anthropic Claude, Amazon Bedrock), AWS serverless backends, data pipelines, and workflow automation with n8n, Make and Zapier.
I also hold two law degrees, which is why legal and professional-services workflows — intake, matters, retainers, document handling — are ones I can scope without needing a translator.
My stack: Python, SQL, AWS (Lambda, API Gateway, DynamoDB, S3, Bedrock, EventBridge, Cognito), Next.js, React, TypeScript, AWS CDK.
I scope honestly, communicate clearly, and build systems that hold up after handover. Available 30+ hours per week, remote worldwide.
Tell me what you're trying to automate and what it costs you today. I'll tell you straight whether it's a two-day fix or a two-month build — and whether I'm the right person for it.
Steps for completing your project
After purchasing the project, send requirements so Masego can start the project.
Delivery time starts when Masego receives requirements from you.
Masego works on your project following the steps below.
Revisions may occur after the delivery date.
Discovery call - intake criteria and practice-area questions
Build and refine the agent on fictional test matters