Apply fine-grained entry management with Bedrock AgentCore Gateway interceptors

As enterprises quickly undertake AI brokers to automate workflows and improve productiveness, they face a important scaling problem: managing safe entry to hundreds of instruments throughout their group. Fashionable AI deployments now not contain a handful of brokers calling a couple of APIs—as a substitute, enterprises are constructing unified AI platforms the place a whole lot of brokers, shopper AI purposes, and automatic workflows have to entry hundreds of Mannequin Context Protocol (MCP) instruments spanning totally different groups, organizations, and enterprise items.

This improve in scale creates a elementary safety and governance downside: How do you be certain every calling principal—whether or not it’s an AI agent, consumer, or software—solely accesses the instruments they’re licensed to make use of? How do you dynamically filter device availability primarily based on consumer identification, agent context, the channel by which entry is requested, and always evolving permissions? How do you defend delicate information because it flows by multi-hop workflows from brokers to instruments to downstream APIs? And the way do you accomplish all of this with out sacrificing efficiency, creating operational bottlenecks, or forcing groups to deploy separate MCP server situations for each tenant or use case?

To handle these challenges, we’re launching a brand new characteristic: gateway interceptors for Amazon Bedrock AgentCore Gateway. This highly effective new functionality supplies fine-grained safety, dynamic entry management, and versatile schema administration.

Wonderful-grained entry management for device entry

Enterprise clients are deploying hundreds of MCP instruments served by a unified AgentCore Gateway. These clients use this single MCP gateway to entry instruments from totally different groups, organizations, shopper AI purposes, and AI brokers, every with their corresponding entry permissions assigned to the calling principal. The problem is securing MCP device entry primarily based on the calling principal’s entry permissions and contextually responding to ListTools, InvokeTool, and Search calls to AgentCore Gateway.

Instrument filtering should be primarily based on a number of dynamic components, together with agent identification, consumer identification, and execution context, the place permissions may change dynamically primarily based on consumer context, the channel by which the consumer is accessing the brokers, workspace entry ranges, and different contextual attributes. This requires security-conscious filtering the place permission adjustments instantly have an effect on device availability with out caching stale permission states.

The next diagram supplies an instance of consumer primarily based device filtering and units the context for the way the gateway evaluates identification and context earlier than returning the allowed instruments.

Schema translation and information safety between MCP and downstream APIs

Clients face advanced challenges in managing the contract between AI brokers and downstream APIs whereas sustaining safety and adaptability. Organizations should dynamically map MCP request schemas to corresponding downstream API schemas, enabling important information safety capabilities akin to redacting or eradicating delicate information like personally identifiable data (PII) or delicate private data (SPI) that customers may ship as a part of prompts to brokers. This prevents delicate information leakage to downstream APIs when such data isn’t wanted for the API name.

Moreover, clients require schema translation capabilities to deal with API contract adjustments whereas conserving the MCP schema intact and decoupled from downstream implementations. This decoupling permits smoother API evolution and versioning with out breaking the AI agent and gear contracts, so backend groups can modify their API implementations, change area names, restructure payloads, or replace authentication necessities with out forcing adjustments to the agent layer or requiring retraining of AI fashions which have realized particular device schemas.

Tenant isolation for multi-tenant SaaS

Organizations providing brokers as a service or instruments as a service face advanced multi-tenancy necessities. Clients should deploy their MCP servers for all their customers whereas sustaining correct tenant isolation, requiring each tenant ID and consumer ID to be handed and validated. Multi-tenant MCP server architectures require totally different clients and workspaces to stay utterly remoted, with device entry strictly managed primarily based on tenant boundaries. The problem extends to figuring out whether or not separate gateways are wanted per tenant or if a single gateway can safely deal with multi-tenant situations with correct isolation ensures.

Dynamic device filtering

Clients want real-time, context-aware device filtering that adapts to altering permissions and consumer contexts. Organizations require unified MCP servers that may filter instruments in two levels: first by agent permissions and workspace context, then by semantic search—with important necessities that no caching happens for dynamically filtered device lists as a result of permissions may change at any time.

Customized header propagation and identification context administration

AI brokers are essentially totally different from conventional microservices in that they’re autonomous and non-deterministic of their habits. In contrast to conventional microservice-to-microservice authorization approaches that usually depend on service-to-service belief and authorization strategies, AI brokers have to execute workflows on behalf of end-users and entry downstream instruments, APIs, and assets primarily based on consumer execution context. Nevertheless, sending the unique authorization tokens to downstream companies creates important safety vulnerabilities, akin to stolen credentials, privilege escalation, and the confused deputy downside, the place a extra privileged service is tricked into performing actions on behalf of a much less privileged attacker.

Impersonation vs. act-on-behalf approaches

Clients face a elementary safety resolution in how identification context propagates by multi-hop workflows (agent to agent to device to API): utilizing an impersonation strategy or an act-on-behalf strategy.

With an impersonation strategy, the unique consumer’s JWT token is handed unchanged by every hop within the name chain. Though easier to implement, this strategy creates important safety dangers. We don’t advocate this strategy as a result of following dangers:

• Downstream companies obtain tokens with broader privileges than needed
• Elevated danger of privilege escalation if any element is compromised
• Token scope can’t be restricted to particular downstream targets
• Susceptible to confused deputy assaults, the place compromised companies can abuse overly privileged tokens

In an act-on-behalf strategy, every hop within the workflow receives a separate, scoped token particularly issued for that downstream goal, and JWT is used for propagating the execution context all through. This strategy is the really helpful strategy as a result of it supplies the next advantages:

• Precept of least privilege – Every service receives solely the permissions it must entry particular downstream APIs
• Diminished blast radius – Compromised tokens have restricted scope and may’t be reused elsewhere
• Higher auditability – A transparent chain of custody reveals which service acted on behalf of the consumer utilizing AgentCore Observability
• Token scope limitation – Every downstream goal receives tokens or credentials scoped particularly for its APIs
• Safety boundaries – Correct isolation is enforced between totally different companies within the name chain
• Confused Deputy prevention – Restricted-scope tokens and credentials stop companies from being tricked into performing unauthorized actions

The act-on-behalf mannequin requires the gateway to extract execution context from incoming requests, generate new scoped authorization tokens for every downstream goal, and inject applicable headers whereas sustaining the consumer’s identification context for auditing and authorization selections—all with out exposing overly privileged credentials to downstream companies. This safe strategy makes positive AI brokers can execute workflows on behalf of customers whereas sustaining strict safety boundaries at each hop within the name chain.

The next diagram compares the workflows of impersonation vs. act-on-behalf approaches.

Within the impersonation strategy (high), when Consumer A connects to the agent, the agent passes Consumer A’s full identification token with full scopes ("order: learn, promotions:write") unchanged to each the Order device and Promotions device, which means every device receives extra permissions than it wants. In distinction, the act-on-behalf strategy (backside) reveals the agent creating separate, scoped tokens for every device—the Order device receives solely the "order: learn" scope, the Promotions device receives solely the "promotions:write" scope, and every token contains an "Act: Agent" area, which establishes a transparent chain of accountability displaying the agent is appearing on behalf of Consumer A. This demonstrates how delegation implements the precept of least privilege by limiting every downstream service to solely the precise permissions it wants, decreasing safety dangers and stopping potential token misuse.

AgentCore Gateway: Safe MCP integration for AI brokers

AgentCore Gateway transforms your present APIs and AWS Lambda features into agent-compatible instruments, connects to present MCP servers, and supplies seamless integration with important third-party enterprise instruments and companies (akin to Jira, Asana, and Zendesk). This unified entry level permits safe integration throughout your enterprise methods. With AgentCore Id, brokers can securely entry and function throughout these instruments with correct authentication and authorization utilizing OAuth requirements.

With the launch of gateway interceptors, AgentCore Gateway helps organizations implement fine-grained entry management and credential administration by customized Lambda features at two important factors:

• Gateway request interceptor – The request interceptor Lambda operate processes incoming requests earlier than they attain their goal instruments, enabling fine-grained entry controlling primarily based on consumer credentials, session context, and organizational insurance policies, audit path creation, schema translation, and extra.
• Gateway response interceptor – The response interceptor Lambda operate processes outgoing responses earlier than they return to the calling agent, permitting for audit path creation, instruments filtering, schema translation, and fine-grained entry controlling the search and record instruments.

The next diagram illustrates the request-response circulation by gateway interceptors.

Let’s study the precise payload constructions that customized interceptors obtain and should return at every stage of the request-response cycle. The gateway request interceptor receives an occasion with the next construction:

{
  "interceptorInputVersion": "1.0",
  "mcp": {
    "gatewayRequest": {
        "headers": { "Authorization": "Bearer eyJhbG...", ... },
        "physique": { "jsonrpc": "2.0", "methodology": "instruments/record", ... }
    },
    "requestContext": { ... }
  }
}

Your gateway request interceptor Lambda operate should return a response with the transformedGatewayRequest area:

{
  "interceptorOutputVersion": "1.0",
  "mcp": {
    "transformedGatewayRequest": {  // <-- This area should be added by your code
        "headers": { ... },
        "physique": { ... }
    }
  }
}

After the goal service responds, the gateway response interceptor is invoked with an occasion containing the unique request and the response:

{
  "interceptorInputVersion": "1.0",
  "mcp": {
    "gatewayRequest": { ... },
    "requestContext": { ... },
    "gatewayResponse": {  // <-- This area comprises the goal's response
        "statusCode": 200,
        "headers": { ... },
        "physique": { 
            "jsonrpc": "2.0",
            "outcome": { "instruments": [ ... ] }
        }
    }
  }
}

Your gateway response interceptor Lambda operate should return a response with the transformedGatewayResponse area:

{
  "interceptorOutputVersion": "1.0",
  "mcp": {
    "transformedGatewayResponse": {  // <-- This area should be added by your code
        "statusCode": 200,
        "headers": { ... },
        "physique": { ... }
    }
  }
}

Understanding this request-response construction is important for implementing the customized interceptor logic we discover later on this publish. Gateway interceptors present important capabilities for securing and managing agentic AI workflows:

• Header administration – Cross authentication tokens, correlation IDs, and metadata by customized headers
• Request transformation – Modify request payloads, add context, or enrich information earlier than it reaches goal companies
• Safety enhancement – Implement customized authentication, authorization, and information sanitization logic
• Wonderful-grained entry management – Safe MCP device entry primarily based on the calling principal’s entry permissions and contextually responding to ListTools, InvokeTool, and Search calls to AgentCore Gateway
• Tenant isolation for multi-tenant MCP instruments – Implement tenant isolation and entry controls primarily based on calling consumer, agent, and tenant identities in a multi-tenant atmosphere
• Observability – Add logging, metrics, and tracing data to watch agentic workflows

Gateway interceptors work with AgentCore Gateway goal sorts: together with Lambda features, OpenAPI endpoints, and MCP servers.

Use instances with gateway interceptors

Gateway interceptors allow versatile safety and entry management patterns for agentic AI methods. This publish showcases three approaches: implementing fine-grained entry management for invoking instruments, dynamic instruments filtering primarily based on consumer permissions, and identification propagation throughout distributed methods.

Implementing fine-grained entry management for invoking instruments

AgentCore Gateway exposes a number of backend instruments by a unified MCP endpoint. Customers with totally different roles require totally different device permissions. You’ll be able to implement fine-grained entry management utilizing JWT scopes mixed with gateway interceptors to verify customers can solely invoke licensed instruments and uncover instruments that belong to their position or workspace. Wonderful-grained entry management makes use of JWT scope values issued by Amazon Cognito (or one other OAuth 2 supplier). You may also implement this utilizing a YAML file or a database with mapped permissions. We observe a easy naming conference: customers obtain both full entry to an MCP goal (for instance, mcp-target-123) or tool-level entry (for instance, mcp-target-123:getOrder). These scopes map on to device permissions within the scope declare as a part of the incoming OAuth token, making the authorization mannequin predictable and easy to audit.

The next diagram illustrates this workflow.

The request interceptor enforces permissions at execution time by the next steps:

1. Extract and decode the JWT to retrieve the scope declare.
2. Determine which device is being invoked (utilizing instruments/name).
3. Block the request if the consumer lacks both full goal entry or tool-specific permission primarily based on the configuration file or entry coverage information retailer.
4. Return a structured MCP error for unauthorized invocations, stopping the backend device handler from executing.

The core authorization operate is deliberately minimal:

def check_tool_authorization(scopes, device, goal):
    if goal in scopes:
        return True
return f"{goal}:{device}" in scopes

This sample permits predictable enforcement for each invocation and discovery paths (mentioned additional within the subsequent part). You’ll be able to prolong the mannequin with extra claims (for instance, tenantId and workspaceId) for multi-tenant architectures.

For operational safety, hold interceptors deterministic, keep away from advanced branching logic, and rely solely on token claims reasonably than giant language mannequin (LLM) directions. By implementing authorization on the gateway boundary—earlier than the LLM sees or executes any device—you obtain robust isolation throughout roles, tenants, and domains with out modifying device implementations or MCP targets.

Dynamic instruments filtering

Brokers uncover accessible instruments by two major strategies: semantic search capabilities that enable pure language queries (like “discover instruments associated to order administration”) and commonplace (instruments/record) operations that present an entire stock of obtainable instruments. This discovery mechanism is key to agent performance, nevertheless it additionally presents important safety concerns. With out correct filtering controls, MCP servers would return a complete record of all accessible instruments, whatever the requesting agent’s or consumer’s authorization degree. This unrestricted device discovery creates potential safety vulnerabilities by exposing delicate capabilities to unauthorized customers or brokers.

When a goal returns an inventory of instruments in response to semantic search or MCP instruments/record requests, the gateway response interceptor can be utilized to implement fine-grained entry management. The interceptor processes the response earlier than it reaches the requesting agent, so customers can solely uncover instruments they’re licensed to entry. The workflow consists of the next steps:

1. The goal validates the incoming JWT token and returns both the entire device record or a filtered set primarily based on semantic search, regardless of fine-grained entry management.
2. The configured response interceptor is invoked by AgentCore Gateway. The response interceptor extracts and decodes the JWT from the payload, retrieving the scope claims that outline the consumer’s permissions.
3. For every device within the record, the interceptor evaluates the consumer’s authorization primarily based on the JWT scopes.
4. Instruments that the consumer isn’t licensed to entry are faraway from the record.
5. The response interceptor returns a reworked response containing solely the licensed instruments.

The next diagrams illustrate this workflow for each instruments.

The next is a code snippet of the response interceptor Lambda handler that performs JWT token extraction, device record retrieval, and permission-based filtering earlier than returning the reworked response with licensed instruments:

def lambda_handler(occasion, context):
    # Extract gateway response and authorization header
    gateway_response = occasion['mcp']['gatewayResponse']
    auth_header = gateway_response['headers'].get('Authorization', '')
    token = auth_header.substitute('Bearer ', '')

    # Extract scopes from JWT token
    claims = decode_jwt_payload(token)
    scopes = claims.get('scope', '').break up()
    
    # Get instruments from gateway response (for record instruments)
    instruments = gateway_response['body']['result'].get('instruments', [])
    # from structuredContent(in case of semantic search)
    if not instruments:
        instruments = gateway_response['body']['result'].get('structuredContent', {}).get('instruments', [])
    
    # Filter instruments primarily based on scopes
    filtered_tools = filter_tools_by_scope(instruments, scopes)
    
    # Return reworked response with filtered instruments
    return {
        "interceptorOutputVersion": "1.0",
        "mcp": {
            "transformedGatewayResponse": {
                "statusCode": 200,
                "headers": {"Authorization": auth_header},
                "physique": {
                    "outcome": {"instruments": filtered_tools}
                }
            }
        }
    }

The filter_tools_by_scope operate implements an authorization test for every device towards the consumer’s allowed scopes:

def filter_tools_by_scope(instruments, allowed_scopes):
    """Filter instruments primarily based on consumer's allowed scopes"""
    filtered_tools = []
    for device in instruments:
        goal, motion = device['name'].break up('___')
        # Test if consumer has full goal entry or particular device entry
        if goal in allowed_scopes or f"{goal}:{motion}" in allowed_scopes:
            filtered_tools.append(device)
            
    return filtered_tools

The entire implementation could be discovered within the GitHub repo.

Customized headers propagation

As AI brokers work together with a number of downstream companies, sustaining consumer identification throughout service boundaries turns into important for safety, compliance, and audit trails. When brokers invoke instruments by AgentCore Gateway, the unique consumer’s identification should circulation from the agent to the gateway, and from the gateway to focus on companies. With out correct identification propagation, downstream companies can’t implement user-specific authorization insurance policies, keep correct audit logs, or implement tenant isolation. This problem intensifies in multi-tenant environments the place totally different customers share the identical agent infrastructure however require strict information separation.

Gateway request interceptors extract identification data from incoming request headers and context, remodel it into the format anticipated by downstream companies, and enrich requests earlier than they attain goal companies by following these steps:

1. The gateway request interceptor extracts authorization headers from incoming requests and transforms them for downstream companies.
2. AgentCore Gateway orchestrates the request circulation and manages interceptor execution.
3. The goal invocation receives enriched requests with correctly formatted identification data.

The gateway request interceptor helps organizations acquire end-to-end visibility into consumer actions, implement constant authorization insurance policies throughout service boundaries, and keep compliance with information sovereignty necessities.

The workflow consists of the next steps:

4. The MCP consumer calls AgentCore Gateway.
5. AgentCore Gateway authenticates the inbound request.
6. AgentCore Gateway invokes the customized interceptor.
7. The gateway request interceptor transforms the incoming request payload by including an authorization token as a parameter to ship to the downstream Lambda goal. (We don’t advocate sending the incoming JWT as-is to downstream APIs as a result of it’s insecure as a result of danger of privilege escalation and stolen credentials. Nevertheless, there may be exceptions the place the agent must name the MCP server with an entry token for downstream APIs.) Alternatively, you’ll be able to take away the inbound JWT coming from the request and add a brand new JWT with a least-privileged scoped-down token for calling related downstream APIs.
8. AgentCore Gateway calls the goal with the reworked request. The goal has the authorization token handed by the interceptor Lambda operate.
9. AgentCore Gateway returns the response from the goal.

The next diagram illustrates this workflow.

The next is a code snippet of the interceptor Lambda handler that performs customized header propagation:

import json
import uuid

def lambda_handler(occasion, context):
    # Extract the gateway request from the proper construction
    mcp_data = occasion.get('mcp', {})
    gateway_request = mcp_data.get('gatewayRequest', {})
    headers = gateway_request.get('headers', {})
    physique = gateway_request.get('physique', {})
    extended_body = physique
    
    # Cross by the Authorization header
    auth_header = headers.get('authorization', '') or headers.get('Authorization', '')
    if "arguments" in extended_body["params"]:
        extended_body["params"]["arguments"]["authorization"] = auth_header
    # Return reworked request with Authorization header preserved
    response = {
        "interceptorOutputVersion": "1.0",
        "mcp": {
            "transformedGatewayRequest": {
                "headers": {
                    "Settle for": "software/json",
                    "Authorization": auth_header,
                    "Content material-Sort": "software/json"
                },
                "physique": extended_body
            }
        }
    }
    return response

No auth and OAuth primarily based authorization

Many enterprises want versatile authorization fashions that stability discoverability with safety. Think about a situation the place you need to enable AI brokers and purposes to find and search accessible MCP instruments with out requiring authorization, enabling seamless device exploration and semantic search throughout your device catalog. Nevertheless, with regards to really invoking these instruments, you want strict OAuth-based authorization to verify solely licensed brokers and customers can execute device calls. You may even want per-tool authorization insurance policies, the place some instruments require authentication whereas others stay publicly accessible, or the place totally different instruments require totally different permission ranges primarily based on the calling principal’s identification and context.

AgentCore Gateway now helps this flexibility by the introduction of a “No Auth” authorization sort on the gateway degree for all inbound calls. When configured, this makes all targets and instruments accessible with out authentication for discovery functions. To implement OAuth authorization on the methodology degree (ListTools vs. CallTools) or implement per-tool authorization insurance policies, you need to use gateway interceptors to look at the inbound JWT, validate it towards the necessities in keeping with RFC 6749 utilizing your authorization server’s discovery URL, and programmatically enable or deny entry to particular strategies or device calls. This strategy provides you fine-grained management: open discovery for ListTools and SearchTools requests whereas implementing strict OAuth validation for CallTools requests, and even implementing customized authorization logic that varies by device, consumer position, execution context, or different enterprise logic your group requires—all whereas conserving your MCP calls safe and compliant along with your safety insurance policies.

The next diagram illustrates this workflow.

The method begins with a ListTools name with No Auth to the AgentCore Gateway, which is configured with basic no-auth for all inbound calls. With this configuration, customers can uncover accessible instruments with out authorization. Nevertheless, when the consumer subsequently makes a CallTool request to invoke a selected device, authorization is required. AgentCore Gateway invokes the customized request interceptor Lambda operate, which validates the JWT token from the authorization header and checks the consumer’s scopes and permissions towards the precise device being invoked. If licensed, the interceptor transforms and enriches the request with the required authorization context, and AgentCore Gateway forwards the reworked request to the goal service. The goal processes the request and returns a response, which AgentCore Gateway then returns to the consumer, implementing strict OAuth-based authorization for precise device execution whereas sustaining open discovery for device itemizing.

To create a gateway configured with No Auth for inbound calls, use authorizerType as NONE, as proven within the following CreateGateway API:

{
  "title": "no-auth-gateway",
  "protocolType": "MCP",
  "protocolConfiguration": {
    "mcp": {
      "supportedVersions": ["2025-03-26"]
    }
  },
  "authorizerType": "NONE",
  "roleArn": 
}

Observability

Complete observability offered by AgentCore Observability is important for monitoring, debugging, and auditing AI agent workflows that work together with a number of instruments and companies by AgentCore Gateway. Gateway interceptors implement authorization, remodel requests, and filter information earlier than downstream companies execute, making the observability layer a important safety boundary. This presents the next key advantages:

• Safety resolution visibility – Interceptors generate authoritative logs for authorization outcomes, together with enable/deny selections and the evaluated JWT scopes. This supplies a transparent audit path for reviewing rejected requests, validating coverage habits, and analyzing how authorization guidelines are enforced throughout device invocations.
• Request and response traceability – Interceptors seize how MCP requests and responses are modified, akin to header enrichment, schema translation, and delicate information redaction. This delivers full traceability of payload adjustments and helps safe, compliant information dealing with throughout agent workflows.
• Downstream device observability – Interceptors log downstream device habits, together with standing codes, latency, and error responses. This creates constant visibility throughout targets, serving to groups troubleshoot failures, determine reliability points, and perceive end-to-end execution traits.

These logs additionally seize identification and context attributes, serving to groups validate authorization habits and isolate points in environments the place a number of consumer teams or tenants share the identical gateway. Gateway interceptors robotically combine with AgentCore Observability, offering the next options:

• Actual-time monitoring of authorization selections
• Efficiency bottleneck identification by length and invocation metrics
• Finish-to-end traceability throughout multi-hop agentic workflows
• Id and context attributes for validating authorization habits in multi-tenant environments

The next screenshot reveals pattern metrics from Amazon CloudWatch log teams for a gateway interceptor.

The metrics exhibit wholesome gateway interceptor efficiency with a 100% success fee, minimal latency (4.47 milliseconds common), and no throttling points, indicating the system is working inside optimum parameters.

The next screenshot reveals pattern logs from CloudWatch for a gateway interceptor.

AgentCore Observability integration helps you monitor authorization selections in actual time, determine efficiency bottlenecks, and keep end-to-end traceability throughout multi-hop agentic workflows.

Conclusion

AgentCore Gateway with gateway interceptors addresses the basic safety and entry management challenges organizations face when deploying agentic AI methods at scale. The three patterns demonstrated—fine-grained entry management for device invocation, dynamic device filtering, and identification propagation—present foundational constructing blocks for safe agentic architectures that bridge authentication gaps, keep credential isolation, and implement customized safety insurance policies. By offering programmable interception factors for each requests and responses, organizations can implement fine-grained entry management with out modifying underlying device implementations or MCP server architectures. As organizations scale to a whole lot of brokers and hundreds of instruments, gateway interceptors present the pliability and management wanted to keep up safety, compliance, and operational visibility throughout advanced agentic AI deployments whereas aligning with enterprise integration patterns and safety greatest practices. AgentCore Gateway with gateway interceptors supplies a versatile basis for implementing enterprise-grade safety controls throughout agentic AI architectures. To be taught extra about how one can apply gateway interceptors to resolve widespread enterprise challenges, seek advice from the next code samples:

For full documentation on gateway interceptor configuration and deployment, seek advice from Wonderful-grained entry management for Amazon Bedrock AgentCore Gateway.

In regards to the Authors

Dhawal Patel is a Principal Generative AI Tech lead at AWS. He has labored with organizations starting from giant enterprises to mid-sized startups on issues associated to agentic AI, deep studying, and distributed computing.

Ganesh Thiyagarajan is a Senior Options Architect at AWS with over 20 years of expertise in software program structure, IT consulting, and answer supply. He helps ISVs remodel and modernize their purposes on AWS. He’s additionally a part of the AI/ML Technical area neighborhood, serving to clients construct and scale generative AI options.

Avinash Kolluri is a Sr Options Architect at AWS. He works with Amazon and its subsidiaries to design and implement cloud options that speed up innovation and operational excellence. With deep experience in AI/ML infrastructure and distributed methods, he focuses on serving to clients use AWS companies for constructing foundational fashions, workflow automation, and generative AI options.

Bhuvan Annamreddi is a Options Architect at AWS. He works with ISV clients to design and implement superior cloud architectures and helps them improve their merchandise by utilizing AWS companies. He’s obsessed with serving to clients construct scalable, safe, and progressive methods, with a robust curiosity in generative AI and serverless structure as enablers for delivering significant enterprise worth.

Mohammad Tahsin is a Generative AI Specialist Options Architect at AWS, the place he works with clients to design, optimize, and deploy trendy AI/ML options. He’s obsessed with steady studying and staying on the frontier of recent capabilities within the area. In his free time, he enjoys gaming, digital artwork, and cooking.

Ozan Deniz works as a Software program Growth Engineer in AWS. He and his staff concentrate on enhancing the vendor capabilities by generative AI. When not at work, he enjoys exploring the outside.

Kevin Tsao is a Software program Growth Engineer throughout the AgentCore Gateway staff. He has been at Amazon for six years and has been working within the conversational AI and agentic AI house because the starting of his tenure, contributing to companies akin to Bedrock Brokers and Amazon Lex.