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 />
Thu, April 29Reliability, Observability & SecurityAI-Native SoftwareArchitecture & Distributed Systems
An AI agent can be authenticated, permitted to call a tool, and still take an action the organisation cannot defend. Retrieved instructions may be malicious, evidence may be stale, and a broadly authorized tool may allow an agent to cross a business boundary that no model should decide on its own.
In this session, you will explore how policy becomes part of the runtime path for consequential agent actions. Following a representative service workflow, you will trace a recommendation through evidence checks, tool permissions, business rules, and human review. You will examine where the system moves from suggesting an action to making a commitment, how least authority limits the tools available to an agent, and how denied or uncertain actions can be deferred rather than forced through. You will also learn how to separate model reasoning from business authority, qualify evidence before it supports an action, and create decision receipts that record what the agent knew, which policy applied, and why an action was allowed, limited, or escalated.
What You Will Learn
How to identify the commitment boundary where an agent moves from recommending an action to creating a business obligation
How to apply least authority, evidence admission, and human approval to consequential tool calls
How to design decision receipts that make agent actions reviewable and defensible
Who Should Attend
AI and Software Architects, Platform and Security Engineers, and Senior Backend Developers designing agents that can change business state. Working knowledge of APIs, agent tool calling, and application authorization 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.
