Skip to content

On AWS

on AWS

Buy NeuralSeek on AWS Marketplace. Run it as SaaS or as a container in your own AWS account, with the Amazon Bedrock models you already use.

Start nowAsk about your setup

Buy onAWS Marketplace

How to buy

Buy on the marketplace or run your own

Subscribe on AWS Marketplace to start fast, or run the container inside your own AWS account. Both give you the same product.

Every deployment has the same features, however you buy it.

  • AWS Marketplace listing

    SaaS with your own model. Subscribe from your AWS account and start with the free trial.

    Open the listing

  • A container in your own AWS account

    The same software as containers on Kubernetes or OpenShift, in the account, VPC and region you choose, under a container license. Talk to us to set it up.

    Ask about deployment

Native AWS integrations

The AWS services NeuralSeek uses

Built-in integrations, so you can run NeuralSeek without leaving AWS.

NeuralSeek

  • Amazon Bedrock · models

    A supported model provider. Pick a Bedrock model at setup, or a different one for each step of an agent, and change it later in configuration.

  • Kendra and Bedrock · knowledge

    Supported knowledge bases for managed vector search, with chunking, embeddings and indexing on the AWS side. Kendra's filters limit a query to what each user may see.

  • Amazon Lex · virtual agent

    When a Lex bot has no answer for a question, NeuralSeek answers from your knowledge base. Curated answers export into Lex and are flagged when their sources change.

  • Amazon S3 · files

    An agent step reads a file from a bucket or writes one back, using the bucket, region and IAM credentials you give it.

Inside an agent

AWS services as agent steps

Add an AWS service to an agent as a step and set the service, credentials and scope. These are the cards your engineers see in the console.

S3 Read FileReads an object from an S3 bucket into the workflow, with the bucket, region and IAM keys set on the node. S3 Write File puts one back.

Bedrock in the model layer

Use Bedrock models your way

Add a Bedrock model as a card in the configuration, choose the functions it serves, and add a second provider beside it if you like. When prices or models change, you update the configuration and your agents keep running.

console › neural config › llm details
The LLM Details panel in the console: an Add an LLM button, a note on load balancing, and two model cards side by side, each with its connection info and a grid of platform functions ticked per model.
Each model is a card, with the jobs it handles checked.

Where it runs

Your account, your region, your controls

Run NeuralSeek as SaaS or in the AWS account and region you choose.

NeuralSeek on Azure and IBM Cloud runs the same container with the same features.

  • One container, the same features

    Managed through the listing or self-hosted in your own account, it's the same software with the same controls.

    Deployment options

  • A region you choose

    Stored data can be kept in a region, and the container route puts the whole deployment in the account and region you pick.

    Data and AI sovereignty

Security review answers

Short answers for your security review.

  1. Is data encrypted?

    Yes, in transit and at rest. Everything that flows to or through the service is encrypted over TLS, and everything stored is encrypted too.

  2. Is our data used to train anything?

    No. Neither NeuralSeek nor any of its subprocessors use customer data to train models or systems, and generated answers belong to the customer.

  3. What happens to personal data in a request?

    Content flagged as personal data is handled by the action you configure: flag, mask, hide or delete. Requests that carry personal data for a personalized answer are handled the same way.

Audited and compliant

On the container route NeuralSeek runs inside an AWS account you already approved, under your VPC, key management, logging and incident process.

Audited

SOC 2 Type II

Audited every year.

NeuralSeek is SOC 1 and SOC 2 Type II audited and HIPAA compliant.

See certifications for details.

Next step

Docs, support and terms

The documentation, support and license terms the AWS listing links to.

Deploying in your own AWS account? Talk to us and we'll help you set it up.

Start building with NeuralSeek today.

Sign up online and start with a two-week trial, or talk to a NeuralSeek expert about running it in your own cloud.

Start nowRequest a demo