Sold by: MphasisÂ
Deployed on AWS
The solution understands the goal from a user's service request and provides a plan by composing the business services (APIs)
Overview
GenAI based chatbots require planning to orchestrate APIs (or tools) to accomplish a user's request. Traditionally user journeys and dialogue designs were fixed with NLP models indentifying user intents. With Generative AI models, the ability to create diagloue flows on the go is possible. This requires undersaning user's goals and breaking them down to steps to execute. Users can leverage our solution to create dynamic plans of execution. Our solution leverages the capabilities of Anthropic's Claude to determine required APIs and the order in which they have to be called to achieve user's request to the LLM chatbot. The model takes OpenAPI schema and the given user query as input. Users benefit from streamlined, accurate API interactions, saving time and effort while ensuring efficient, reliable responses to complex queries. It also allows users to customize plans by providing specific instructions and counter examples for the model to follow.
Highlights
- Users can leverage our solution to customize workflows to their specific requirements and orchestrate dynamic workflows without having to manually create rules and logic flows of the services involved. This provides flexibility in executing business-specific workflows reducing manual overhead. Users can also handle complex workflows seamlessly, allowing for scalable solutions that can adapt to different requirements and changes in the API schema.
- Our solution enhances reliability by ensuring accurate responses because it enables structured data retrieval. Integration with external tools via JSON Schema facilitates seamless interactions. By generating a plan for API calls, the solution minimizes the risk of errors that can occur from incorrect sequencing or missing dependencies between API calls. This approach improves user experience by providing more relevant responses. Additionally, automating tasks saves time and costs by reducing manual intervention.
- The Mphasis AI for Software Development service enables enterprises to build customized no-code/low-code solutions to accelerate development and deployment of software. We leverage our patented AI/ML platforms and frameworks to engage with clients across multiple use cases: intelligent code recommendation, rapid prototyping etc. We help enterprises target impactful AI/ML interventions that drive business benefits. Our Assessments, Workshops and Implementations identify the most relevant use cases in software engineering and outline the potential benefits such as efficiency, cost and innovation
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost |
|---|---|---|
ml.m5.2xlarge Inference (Batch) Recommended | Model inference on the ml.m5.2xlarge instance type, batch mode | $2.00/host/hour |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $2.00/host/hour |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $2.00/host/hour |
inference.count.m.i.c Inference Pricing | inference.count.m.i.c Inference Pricing | $0.05/request |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Latest version
Additional details
Inputs
- Summary
The input file 'input_zip.zip' should contain two files, namely:
- config.json
- openAPI_schema.json
config.json - This file contains credentails to Amazon Bedrock key details ("region_name","aws_access_key_id", "aws_secret_access_key"), file_path of APIs ("file_path"), useful information to generate correct response ("instructions", "examples", "extra_tasks" ). Also provide the query in the config file.
openAPI_schema.json - This file contains the openAPI schema of APIs
- Limitations for input type
- The input file 'input_zip.zip' should contain two files, namely: 1. config.json 2. openAPI_schema.json
- Input MIME type
- application/zip
https://github.com/Mphasis-ML-Marketplace/Goal-oriented-service-composition/blob/main/input_zip/input_zip.zip
https://github.com/Mphasis-ML-Marketplace/Goal-oriented-service-composition/tree/main/input_zip
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Goal management and performance tracking in Salesforce
Empower your team by training with EnterOne - An Advanced Tier Training Partner named the AWS Global Training Partner of the Year for 2022, 2023, and 2024!
Our AWS Training Credits provide a streamlined way to invest in training now and choose from a wide range of AWS-authorized learning options when you're ready.
- Virtual or In-Person Instructor-Led Training
- AWS Authorized Digital, On-Demand, or Self-Paced Courses
- AWS Certification Exam Vouchers
- Individual or Group Training Sessions
- Custom Learning Paths and Programs
zeb designs and deploys custom Agentic AI solutions in Amazon Connect, enabling proactive, goal-driven virtual agents that collaborate across systems. Deliver sophisticated self-service experiences and intelligently escalate to live agents when needed.
The AWS Learning Needs Analysis (LNA) identifies workforce skill gaps and aligns training to organizational goals. AWS Skill Builder provides scalable, role-based training paths, including certification prep and hands-on labs, to ensure teams acquire the skills needed for effective cloud operations.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.