GIDS news media, articles, insights and virtual events educate and illuminate its audiences so they can be fully prepared to deal with the new realities at work and in their professions.
Get the latest event updates, and insights from today's leading voices.
< session />
Tue, April 27AI-Native SoftwarePlatform Engineering & DevOpsReliability, Observability & Security
As organisations deploy more agents, individual guardrails become difficult to govern consistently. Different teams may define tool permissions, evidence rules, approval paths, evaluation thresholds, and spending limits differently, resulting in fragmented control, uneven auditability, and no reliable way to reduce autonomy across the organisation when conditions change.
In this session, you will explore a reference architecture for an AI control plane, with identity, authorization, evidence admission, tool governance, evaluation, observability, cost budgets, human approval, and incident response operating as shared platform capabilities. Through a representative service agent attempting to answer a customer, modify an order, and issue a refund, you will examine what happens as its evidence, policy version, and retry budget change. You will also explore which controls belong in a common platform, which remain with the application, how policy versions and budgets are enforced, and how incidents can change the permissions of affected capabilities.
What You Will Learn
How to identify the shared capabilities required to govern agents across applications and teams
How to separate platform controls from application-specific authority and workflow policy
How to connect evidence, permissions, budgets, approvals, and incident response in a common operating model
Who Should Attend
Enterprise and Software Architects, AI Platform Owners, Security Architects, and Engineering Leaders responsible for multiple agent deployments. Experience with platform architecture, identity and authorization, or enterprise AI governance is recommended.
< speaker_info />
Rohit Bhardwaj is a Director of Architecture working at Salesforce. Rohit has extensive experience architecting multi-tenant cloud-native solutions in Resilient Microservices Service-Oriented architectures using AWS Stack. In addition, Rohit has a proven ability in designing solutions and executing and delivering transformational programs that reduce costs and increase efficiencies.
As a trusted advisor, leader, and collaborator, Rohit applies problem resolution, analytical, and operational skills to all initiatives and develops strategic requirements and solution analysis through all stages of the project life cycle and product readiness to execution.
Rohit excels in designing scalable cloud microservice architectures using Spring Boot and Netflix OSS technologies using AWS and Google clouds. As a Security Ninja, Rohit looks for ways to resolve application security vulnerabilities using ethical hacking and threat modeling. Rohit is excited about architecting cloud technologies using Dockers, REDIS, NGINX, RightScale, RabbitMQ, Apigee, Azul Zing, Actuate BIRT reporting, Chef, Splunk, Rest-Assured, SoapUI, Dynatrace, and EnterpriseDB. In addition, Rohit has developed lambda architecture solutions using Apache Spark, Cassandra, and Camel for real-time analytics and integration projects.
Rohit has done MBA from Babson College in Corporate Entrepreneurship, Masters in Computer Science from Boston University and Harvard University. Rohit is a regular speaker at No Fluff Just Stuff, UberConf, RichWeb, GIDS, and other international conferences.
