Khushan Adatiya
I am a Senior Software Engineer at Google who has spent over a decade turning complex ideas into systems that operate at massive scale. From AWS to Google, I have built and evolved distributed platforms serving hundreds of thousands of transactions per second. As a judge, I am passionate about recognizing ideas that combine bold innovation with strong engineering fundamentals and real-world impact.
Research Areas
-
Algorithms and Theory
-
Data Management
-
Data Mining and Modeling
-
Distributed Systems and Parallel Computing
-
Human-Computer Interaction and Visualization
-
Information Retrieval and the Web
-
Machine Intelligence
-
Natural Language Processing
-
Quantum Computing
-
Responsible AI
-
Security, Privacy and Abuse Prevention
-
Software Engineering
-
Software Systems
Authored Publications
Sort By
Securing the Agentic Enterprise
Amazon Kindle (2026)
Preview abstract
Securing the Agentic Enterprise: Threat Modeling, Anomaly Detection, and Governing Autonomous Multi-Agent Systems addresses the critical security and governance gaps emerging as enterprises transition from human-supervised copilots to autonomous agentic workflows. As software processes gain the ability to reason, decompose natural language objectives, and execute multi-step tool calls at machine speed, traditional syntactic security boundaries (like firewalls and static analysis) become obsolete.
This book provides security architects, CISOs, and platform engineers with a practical, architecture-level blueprint for securing this new paradigm. It explores novel attack vectors such as indirect prompt injections and consumption-based economic threats and provides frameworks for robust mitigation. Key topics include modernizing agentic identity, implementing semantic firewalls, transition-state anomaly detection, and applying zero-trust principles to autonomous execution contexts. Bridging the gap between high-level ethical guidelines and isolated model safety, this guide prepares practitioners to confidently deploy and govern enterprise-grade autonomous systems.
View details
Preview abstract
As AI agents increasingly operate with system-level privileges across cloud environments, they face significant security vulnerabilities—most notably prompt injection and unauthorized command execution. With 72% of agent deployments experiencing security incidents within 90 days, there is a critical need for robust, defense-in-depth strategies. This article introduces "Bottom-Up AI Agent Security," a comprehensive 14-layer framework designed to secure AI agents from the foundation up. The strategy covers five essential domains: code-level security, container hardening, cloud IAM, runtime monitoring, and human oversight. By providing actionable implementation templates (including Java, YAML, and GitHub Actions) and a structured 4-week deployment roadmap, this framework enables cloud architects to transform vulnerable AI deployments into hardened, production-ready systems with measurable reductions in risk and operational costs.
View details
Preview abstract
Large-scale software systems frequently suffer from architectural rigidity caused by monolithic designs, tightly coupled integrations, and legacy technology stacks. Backend-forFrontend (BFF) architectures are increasingly adopted to address these challenges by decoupling frontend-specific requirements from backend domain services. However, designing a BFF layer requires a series of irreversible technology decisions across compute platforms, traffic routing, programming languages, frameworks, and API protocols. These decisions directly influence system latency, scalability, operational complexity, and long-term maintainability. This paper proposes a structured, metrics-driven decision framework to guide architects through foundational technology choices when designing BFF architectures. The framework decomposes the decision space into independent sub-problems, introduces weighted evaluation criteria, and applies quantitative scoring models to enable objective trade-off analysis. The approach is validated through a representative modernization scenario, demonstrating how systematic evaluation reduces architectural risk, resolves stakeholder disagreement, and improves performance and developer efficiency. The proposed framework is generic, repeatable, and applicable to a wide range of cloudnative system modernization efforts.
View details
Preview abstract
The rise of agentic AI systems is fundamentally altering the nature of vendor relationships, moving beyond traditional counterparty models where vendors are singular, known organizations. This article explores how AI-mediated workflows create porous organizational boundaries, with vendors' autonomous systems often invoking other undisclosed third-party systems. This shift introduces new risks and failure modes, including counterparty drift, cross-organizational hallucinations, fragmented audit trails, and reviewer fatigue. We argue that existing procurement and third-party risk management frameworks are insufficient for this new reality. Drawing on emerging best practices and converging regulatory trends (e.g., DORA, EU AI Act), the article proposes revisions to governance practices. These include mandating disclosure of autonomous system chains, negotiating cross-organizational audit trail access, and explicitly defining human override and accountability points. The article concludes by highlighting unresolved challenges in cross-organizational liability, trust frameworks for machine-speed coordination, and vendor concentration risk, urging procurement and risk leaders to adapt their strategies for an era of networked autonomous systems.
View details
The Manager's Job Has Already Changed, Most Companies Haven't Noticed
AI Journal (2026)
Preview abstract
The traditional role of a manager, focused on overseeing people performing tasks with software tools, is undergoing a profound shift due to the rise of autonomous AI systems. Across functions like customer support, sales, and finance, software is no longer just a tool but is increasingly executing work end-to-end. This article examines the implications of this transition for the managerial role, arguing that the manager's job is evolving from an "operator-of-operators" to a "designer-of-boundaries." Key new responsibilities include defining the scope of autonomous systems, codifying implicit human judgment into explicit rules and policies, and designing effective human-in-the-loop escalation paths. This shift also impacts team structures, performance management conversations, and even professional identity, as experienced operators' roles are renegotiated. The article contends that companies must recognize and address these cultural and organizational changes to successfully leverage autonomous systems, and that board-level oversight needs to adapt to this new operational reality. The cultural work of redefining management and supporting the workforce through this transition is paramount and will ultimately determine the long-term value derived from these technological advancements.
View details
Preview abstract
Serverless platforms offer compelling economics for low-traffic inference of small language models (SLMs), but cold start latency remains a critical barrier. We present a systematic empirical study of cold start performance for quantized SLMs served via llama.cpp on Google Cloud Run’s CPU-only infrastructure. We benchmark five models (270M– 3.8B parameters) across two memory tiers (4 GiB and 8 GiB), with a quantization sweep spanning five GGUF formats (Q2_K through Q8_0) for LLaMA 3.2 1B and three-point validation on Gemma 3 270M and Qwen3 0.6B. Our results reveal that model loading dominates cold start time (55–70%), the 8 GiB tier provides a hidden 2× vCPU advantage that nearly halves warm inference time, and Q4_K_M quantization achieves a Pareto-optimal tradeoff across latency, throughput, and model quality (confirmed via WikiText-2 perplexity). A threepredictor latency model (R 2 = 0.97) and break-even cost analysis provide practitioners a quantitative framework for SLM deployment decisions. Index Terms—small language models, serverless computing, cold start, quantization, llama.cpp, Cloud Run, GGUF, inference optimization
View details
OpenClaw in Practice: Building Laptop-Less Engineering Workflows with an Agent Harness
Hackernoon (2026)
Preview abstract
This article introduces OpenClaw, an AI-powered workflow harness designed to reduce operational friction for developers. Unlike traditional chatbots, OpenClaw manages and persists context across complex engineering tasks, enabling asynchronous operations and mobile-first interactions. The post explores practical use cases, including incident triage from mobile, asynchronous pull request reviews, quick infrastructure scripting, and automating routine operational tasks. It also delves into the key architectural layers of an OpenClaw-like system—Connectors, Gateway/Session Manager, Agent Runtime, Memory/Configuration, and Skills/Tools. The article emphasizes the importance of security, observability, and proper integration with existing developer ecosystems, positioning OpenClaw as a shift towards reducing context switching and enhancing developer productivity by automating the workflows around coding.
View details
The End of SaaS Dashboards: Why 2026 Belongs to Agents-as-a-Service
Hackernoon (2026)
Preview abstract
The traditional SaaS model, centered on human-operated dashboards, is being supplanted by Agents-as-a-Service (AaaS), where autonomous agents orchestrate outcomes. This article explores the architectural shift from request-response to reason-act loops, a reference "Agentic Stack," the rise of Agent-to-Agent (A2A) communication, and the implications for business models and system design, emphasizing the transition from User Experience (UX) to Agent Experience (AX).
View details
Preview abstract
The Agent-to-Agent (A2A) protocol is an open, vendor-neutral standard proposed by Google to enable seamless collaboration between independent AI agents. A2A allows agents to discover each other via standardized Agent Cards, exchange structured Tasks and messages over JSON-RPC/HTTP, and stream updates for long-running work. This paper details the A2A protocol, including its technical building blocks, security model based on OAuth2/OIDC, and contrasts it with existing agent interaction models. We illustrate its utility through real-world multi-agent workflows, demonstrating how A2A, in conjunction with Model Context Protocol (MCP), can form a robust and interoperable ecosystem for scalable, enterprise-grade autonomous processes across different organizations and platforms.
View details
Preview abstract
This article presents a novel approach to automating operations tasks, particularly incident triage, by using AI agents defined entirely in Markdown. These agents orchestrate actions across various observability tools (e.g., Datadog, Splunk) and use the file system for state and communication, mimicking the Unix philosophy. The system enables parallel investigations, cross-tool validation, and structured reporting without traditional coding frameworks.
View details
