One of our customers called 7Targets offers AI Sales Assistant with lead nurturing and email writing capabilities. These sales assistants read the received responses and follow up accordingly within minutes.
Being an email-based AI Assistant, 7Targets wanted to make sure that a scalable and working solution is created to send and receive the emails. The received email is read, categorized, understood and entities extracted from. So that further action can be taken by the assistant.
But 7Targets wanted to scale the AI Assistants with the following abilities:
- To send email evenly distributed over time to avoid sudden spike.
- To read the email received and decide the next action to be taken by the ‘AI Sales Assistant’ after proper categorization of the received email.
- To extract entities like date, phone number, title, etc from the email received.
- To Set up a pipeline for continuous deployment with proper testing in the pipeline.
This is how we offered the following solutions to enhance the abilities of the AI Assistants:
- Created the step functions (state machines process-lead, process-lead-response, etc.) with various lambda functions for each step.
- Where the received email is accepted in the s3 bucket using SES.
- Process the received response and categorize based on sentiment and certain properties available in the response like date, etc.
- Handle any bounce and complaint email responses.
This has helped 7Targets to solve the problem of sending the email and then the follow-up email. The right categorization of the received email, based on which lead state was updated and the action ahead was decided by a state machine.
Along with categorization from the email text, there was also a need for entity detection like date, phone number, etc. which was done as part of this implementation. For example, if an email was received and categorized to be ‘Out of Office’ then the return date was identified from the email so that the assistant can follow up after the leads return to the office instead of following up in the Out of office period.
We used the following third-party applications:
- Debounce and Zerobounce APIs are used to validate the emails of each lead. This is the first step in the process-lead step function
- 3rd party CRM like Hubspot, ZohoCRM is used and the 7Targets AI Assistant solution interacts with that solution
With our solutions, 7Targets achieved the following results:
- Able to grow per day email sending from 1K to like 10K and per day and can still grow more with the present solution.
- Able to process the response at a similar level but the responses are not as high as email sending.
- Will proper limits and thresholds be set and with continuous monitoring of failure for lambda and step functions the limits and thresholds are changed.
- The container in Fargate is auto-configured to scale up and down.
- The Continuous deployment pipelines are helping with automated zero-downtime deployments to QA and then production setup
Empower your chatbot with us
At AAIC, we are instrumental in offering AI-powered automation inclined with AWS cloud services. Our AWS certified team closely sits with you to understand all your requirements to offer you the best solutions. We make your solutions scalable and affordable. And also with us, you can significantly reduce your software development time.
We used the following technologies to help 7Targets:
AWS Stepfunctions, AWS Lambda, AWS RDS, AWS Comprehend, AWS S3, AWS SES, AWS ECR, AWS Fargate, AWS SNS, AWS SQS, AWS API Gateway, AWS Cloudwatch, AWS ELB, AWS Cognito, AWS WAF, AWS CloudFormation, AWS DMS, AWS Route53
Need AWS consultation? Book a free consultation call.
