Sold by: Software Sushi
Deployed on AWS
Free Trial
Classify support tickets in Spanish, Portuguese, and English. Returns intent, urgency, sentiment, language, and model scores on CPU, without runtime downloads.
Overview
Bring order to your support inbox
Turn Spanish, Portuguese and English tickets into consistent signals for your support workflow. Support Ticket Classifier identifies the request category, urgency, sentiment and language, helping your team sort incoming requests, organize queues and prioritize review. Send ticket text or a subject and body through a single API, and keep the original ticket ID in the response.
Get started with nine categories: billing, technical issues, account access, cancellations, shipping and delivery, refunds, complaints, sales inquiries and other requests. Ranked category candidates, model scores and review flags support assisted triage and integration with your existing tools. Deploy on CPU using SageMaker real-time endpoints for incoming tickets or batch transform for larger collections.
Inference runs inside your AWS account, with the model and tokenizer included in the container and no external API calls or runtime downloads. Enable SageMaker network isolation and configure your own access, encryption and logging policies. Before automating routing, validate with representative tickets and keep a human review path: scores are uncalibrated, review flags can miss errors, and long text is limited to the first 128 tokenizer tokens. Custom categories are experimental. The model does not redact personal data. See the linked Evaluation scope for measured results, data provenance and limitations, and the Buyer guide for examples and deployment instructions.
Watch the product workflow
See Spanish, Portuguese and English examples classified by the actual published model. The English walkthrough shows an illustrative review interface, real response fields and the model's limitations.
Watch the English product video on YouTube . The interface is an illustrative integration rather than an included product UI. The examples are fictional; model responses are real.
Highlights
- Spanish, Portuguese, and English support tickets
- Intent, urgency, sentiment, language, model scores, and review flags
- CPU image with baked weights and no runtime network
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
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
Free trial
Try this product free for 14 days according to the free trial terms set by the vendor.
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/host/hour |
|---|---|---|
ml.c5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.c5.xlarge instance type, real-time mode | $0.70 |
ml.c5.xlarge Inference (Batch) Recommended | Model inference on the ml.c5.xlarge instance type, batch mode | $0.70 |
Dimensions summary
You pay by the hour for each hour the model inference container runs on an ml.c5.xlarge CPU instance. Two usage dimensions set the price by processing mode. Real-time inference serves tickets one request at a time through a live endpoint. Batch inference processes groups of tickets in a single transform job. You choose the mode that fits your workflow and pay only for the hours used. AWS infrastructure, data transfer, and any connected services are billed separately from these software charges.
Top-of-mind questions for buyers
One host-hour covers one running ml.c5.xlarge CPU container for one hour. The container runs inside your own AWS account with network isolation. Billing meters the time the inference container is active, not the number of tickets processed. Partial hours and compute specifics follow the AWS Marketplace metering.
Real-time billing meters hours a live endpoint stays running, so it accrues while the endpoint is up even between requests. Batch billing meters hours a transform job runs across a group of tickets, then stops when the job finishes. Real-time suits steady request flow; batch suits scheduled bulk processing.
AWS infrastructure such as EC2 and EBS, data transfer, and any connected services are billed separately from the software fees. You also configure your own SageMaker execution role and private S3 bucket. These resources and any outbound integrations your team builds carry their own charges.
cdn.softwaresushi.com+1
Helpful?
Vendor refund policy
Software charges stop when the endpoint is deleted or a batch job ends. If the product did not work as described, email info@softwaresushi.com within 30 days with your AWS account ID and endpoint or job name. Software Sushi will refund the software charges for that use. AWS infrastructure charges are separate and are not covered.
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) .
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
Initial release. Frozen multilingual-e5-small encoder, development-selected ES/PT/EN intent heads, separate natural-language training data, and a 2000-case synthetic diagnostic. Includes review signals, input limits, a buyer notebook and offline CPU runtime.
Additional details
Inputs
- Summary
UTF-8 ticket text, or a subject and body, as JSON or JSON Lines. Plain text and a text CSV column are also accepted. JSON ticket IDs are preserved. Optional labels override the intent, urgency, or sentiment set.
- Limitations for input type
- Requests contain at most 32 records and 6 MiB total. Each ticket is at most 100000 characters. Blank tickets are rejected. The encoder uses the first 128 tokenizer tokens, including prefix and special tokens.
- Input MIME type
- application/json, application/jsonlines, text/plain, text/csv
{"text": "The card statement shows the subscription fee two times this month. Please fix this duplicate today, it is really frustrating."}
{"text": "The card statement shows the subscription fee two times this month. Please fix this duplicate today, it is really frustrating."}
{"text": "El paquete debía llegar ayer y el repartidor no pasó. Lo necesitamos urgente."}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
text | One customer support ticket. | At most 100000 characters. Truncated to 128 tokens. | No |
subject | Ticket subject; joined with body when text is not provided. | String. Combined ticket is at most 100000 characters and truncated to 128 tokens. | No |
body | Ticket body; used with subject as an alternative to text. | String. At least one of text or a non-empty subject/body is needed. | No |
id | Optional ticket ID returned unchanged with the prediction. | Non-empty string of at most 200 characters. JSON or JSON Lines only. | No |
labels | Optional override for intent, urgency, or sentiment labels. | Each task is a list of 1 to 32 strings, each at most 64 characters. | No |
Resources
Vendor resources
Support
Vendor support
Email Software Sushi at info@softwaresushi.com with the product version, instance type, and request id. Do not include ticket contents or credentials. No response-time SLA is advertised.
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
Machine learning based service desk ticket triaging model to improve accuracy of ticket assignments and thereby improve FCR and MTTR.
Machine learning based customer complaint ticket triaging model to improve accuracy of ticket assignments and thereby improve FCR and MTTR.
Machine learning based help desk ticket triaging model to improve accuracy of ticket assignments and thereby improve FCR and MTTR.
Machine learning based application ticket triaging model to improve accuracy of ticket assignments and thereby improve FCR and MTTR.
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.