This position is offered through the ANU Computing Internship ([COMP4820] / [COMP8830])
Company
Overflow Solutions provides the highest converting inbound sales management solution for Trades and Service based businesses.
Project
AI Managed Service
Job lifecycle:
- Enquiry (answering a Call, understanding the problem)
- Quote (calculating the cost and proposing the solution)
- Booking (finding a slot in the clients schedule and then allocating the work to the best qualified and positioned resource)
- Delivery Management (Courtesy calls to the Client to ensure readiness for service, reorganising resource allocation based on schedule clashes)
- Follow up (For payment if required, reviews and referrals)
Currently Client calls are received by a Client Sales Representative (Rep) and all details related to the call are entered manually in to the Job Card in Service M8.
The Rep then relies on their experience to be able to connect the Client with the right solution, book the job, and dispatch the resource to rectify.
During the delivery Management Phase, the Rep provides a Courtesy Call to the Caller, communicates any finer details and changes if required.
During the Follow up phase the Rep has to manually go through each of their customer accounts in Service M8 to review completion status of jobs, know who to call for payment, reviews and which job cards were not complete.
The project is to deliver the following:
Preliminary:
- Experiment with AI voice to text and AI knowledge base to understand which solution will meet the intent.
Outcomes:
- Automate the entry of client data in to the software based on Voice to Text.
- Prompt the operator on the right next step on the call by pre populating knowledge base articles based on the customer described issue.
- Provide a consolidated task list for the operator based on the status of their current jobs.
Required/Preferred Technical Skills
Integrations between Service M8 and Atlassian use Rest API.
Overall web app will most likely leverage elements of the following, however are open to other methods of implementation:
- Stack: React, Python (Django), PostgreSQL
- Frameworks: Tailwind CSS
- Services: CI/CD Pipeline, ECS, ECR, AWS Textract (OCR), Load Balancer, Auto Scaling, Route 53, CloudWatch, S3 Bucket, EC2, RDS
We have no preference for Voice to Text or knowledge base, we currently use GPT for the Knowledge base but anticipate that we will need to investigate tools in a preliminary phase.
Delivery Mode
• Hybrid (Project can be undertaken in-person or remote)
Type of internship
Paid internship. The intern/s will be engaged as a casual employee.
How to apply
Applications are invited from students who have already passed the eligibility checks for the Computing Internship courses COMP4820 or COMP8830. Further information about the Computing Internships can be found on the Computing Internship page.
You can nominate multiple preferred Internship projects and host organisations through the one application form.