IT Brief Asia - Technology news for CIOs & IT decision-makers
Asia
AWS opens Step Functions to AI agents in Bedrock

AWS opens Step Functions to AI agents in Bedrock

Tue, 17th Nov 2026 (Today)
Sofiah Nichole Salivio
SOFIAH NICHOLE SALIVIO News Editor

Amazon Web Services has made AWS Step Functions workflows available as tools for AI agents through Amazon Bedrock AgentCore Gateway, allowing existing workflows to be called by agents without being rebuilt.

OpenAI GPT-6.1 Terra is also now generally available on Amazon Bedrock, adding a lower-cost GPT-6 family model to the managed AI service.

The Step Functions update lets AI agents invoke workflows that organisations already use across AWS services, while Step Functions continues to execute each step in the original order. This allows companies to expose established operational processes to agents without changing the underlying workflow logic.

Under the setup, an agent decides when to run a workflow and what input to pass, and Step Functions then executes the sequence. Both existing Standard and Express workflows can be used as connector targets, and agents can also look up workflow runs.

The integration is delivered through Bedrock AgentCore Gateway, which connects agents to tools over the Model Context Protocol. The feature is available in all regions where AgentCore Gateway operates and is billed at standard rates.

The launch reflects a broader market push to connect AI agents to software and internal systems without large redevelopment projects. AWS highlighted a separate example involving an engagement platform that exposed about 400 internal API operations to agents using the same approach.

Model pricing

Alongside the workflow update, AWS expanded Bedrock's model options with GPT-6.1 Terra. OpenAI positions the model as the everyday-workload line in the GPT-6 family, and AWS highlighted its pricing against neighbouring models on the platform.

Input and output tokens for GPT-6.1 Terra are priced at least 50% lower than GPT-6.1 Sol and GPT-5.6 Terra. The model supports up to 1 million input tokens, accepts text and image input, and can be accessed through Bedrock APIs as well as through ChatGPT Work and Codex.

AWS cited OpenAI figures showing GPT-6.1 Terra scored 15 percentage points higher than GPT-5.6 Terra in the Agents' Last Exam evaluation, performed on par with GPT-6 Astra, and completed tasks more than three times faster than both. AWS noted the figures came from OpenAI rather than an independent test.

Security updates

AWS also announced two post-quantum security developments. AWS Key Management Service now supports ML-KEM for post-quantum key encapsulation, allowing customers to establish a shared secret using a post-quantum algorithm with KMS keys whose private keys remain in FIPS 140-3 Level 3-validated hardware security modules.

The service supports all three NIST FIPS 203 parameter sets through Encapsulate and Decapsulate functions. AWS framed the addition around the risk often described as "harvest now, decrypt later", in which encrypted traffic collected today could be exposed once quantum computing becomes strong enough to break current methods.

Amazon Aurora PostgreSQL has also added post-quantum TLS key exchange on version 18 and higher. Together, the two launches reflect growing efforts by cloud providers to give customers tools to prepare systems for future cryptographic changes, even though no fixed deadline has been set for widespread quantum threats.

Broader platform changes

Elsewhere, AWS IAM Identity Centre now supports cross-region trusted identity propagation, allowing a user's identity to travel with a request to AWS services in another region. This removes the earlier restriction that services using trusted identity propagation had to remain in the same region.

Amazon ECS has added GPU sharing with NVIDIA Multi-Process Service, enabling multiple ECS tasks to run concurrently on a single NVIDIA GPU. The feature is intended for workloads such as small-model inference and multi-model serving, where one task may not fully use a GPU.

AWS Lambda now supports Seekable OCI lazy loading for Lambda Managed Instances, allowing functions to fetch only the files needed at each stage of startup rather than pulling an entire container image first. AWS said this can cut container startup time by as much as 70%.

The same lazy-loading method has also been extended to Amazon SageMaker AI training and processing jobs. AWS cited internal benchmark figures showing lazy loading stayed between three and 11 seconds regardless of image size, compared with a median of three minutes and 42 seconds for a 13.2 GB image.

Amazon EKS Auto Mode has also added support for the Kubernetes Gateway API, allowing customers to define traffic routing for applications without installing a separate controller. Existing Ingress workloads continue to operate alongside the new support, making the change additive rather than a migration.

Taken together, the announcements show AWS focusing on practical changes in AI integration, model cost, security and infrastructure efficiency, with Step Functions and Bedrock at the centre of the latest updates.