Ravish Gupta

Ravish Gupta, Saket Kumar, Shreeya Sharma et al.

Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip it entirely. We built a six-agent AI system where each agent handles one analytical stage: profiling the organization, mapping assets, analyzing threats, evaluating controls, scoring risks, and generating recommendations. Agents share a persistent context that grows as the assessment proceeds, so later agents build on what earlier ones concluded -- the mechanism that distinguishes this from standard sequential agent pipelines. We tested it on a 15-person HIPAA-covered healthcare company and compared outputs to independent assessments by three CISSP practitioners -- the system agreed with them 85% of the time on severity classifications, covered 92% of identified risks, and finished in under 15 minutes. We then ran 30 repeated single-agent assessments across five synthetic but sector-realistic organizational profiles in healthcare, fintech, manufacturing, retail, and SaaS, comparing a general-purpose Mistral-7B against a domain fine-tuned model. Both completed every run. The fine-tuned model flagged threats the baseline could not see at all: PHI exposure in healthcare, OT/IIoT vulnerabilities in manufacturing, platform-specific risks in retail. The full multi-agent pipeline, however, failed every one of 30 attempts on a Tesla T4 with its 4,096-token default context window -- context capacity, not model quality, turned out to be the binding constraint.

Ravish Gupta, Saket Kumar

This paper extends the Acemoglu-Restrepo task exposure framework to address the labor market effects of agentic artificial intelligence systems: autonomous AI agents capable of completing entire occupational workflows rather than discrete tasks. Unlike prior automation technologies that substitute for individual subtasks, agentic AI systems execute end-to-end workflows involving multi-step reasoning, tool invocation, and autonomous decision-making, substantially expanding occupational displacement risk beyond what existing task-level analyses capture. We introduce the Agentic Task Exposure (ATE) score, a composite measure computed algorithmically from O*NET task data using calibrated adoption parameters--not a regression estimate--incorporating AI capability scores, workflow coverage factors, and logistic adoption velocity. Applying the ATE framework across five major US technology regions (Seattle-Tacoma, San Francisco Bay Area, Austin, New York, and Boston) over a 2025-2030 horizon, we find that 93.2% of the 236 analyzed occupations across six information-intensive SOC groups (financial, legal, healthcare, healthcare support, sales, and administrative/clerical) cross the moderate-risk threshold (ATE >= 0.35) in Tier 1 regions by 2030, with credit analysts, judges, and sustainability specialists reaching ATE scores of 0.43-0.47. We simultaneously identify seventeen emerging occupational categories benefiting from reinstatement effects, concentrated in human-AI collaboration, AI governance, and domain-specific AI operations roles. Our findings carry implications for workforce transition policy, regional economic planning, and the temporal dynamics of labor market adjustment

Ravish Gupta, Saket Kumar, Maulik Dang

Outpatient departments (OPDs) in Indian public hospitals face severe overcrowding, with daily volumes reaching 200--8,000 patients~\cite{aiims2020annual}. The prevailing First-Come-First-Served (FCFS) token system treats all patients equally regardless of clinical urgency, leading to dangerous delays for critical cases. We present an agentic AI framework integrating six components: voice-based multilingual symptom capture (modeled), LLM-powered severity prediction, load-aware physician assignment, adaptive queue optimization with urgency drift detection, a multi-objective orchestrator, and a Patient Memory System for longitudinal context-aware triage. Evaluated through discrete-event simulation of a District Hospital in Jabalpur (Madhya Pradesh) with 368 synthetic patients over 30 runs, the framework achieves 94.2\% critical patients seen within 10 minutes (vs.~30.8\% under FCFS), detects $\sim$236 simulated urgency drift events per session (modeled via stochastic deterioration probabilities), identifies $\sim$11.9 additional hidden-critical cases via patient memory, and recomposes queue urgency distribution from 13/36/158/161 (Critical/High/Medium/Low) to $\sim$25/178/115/50 through continuous reassessment, while maintaining comparable throughput ($\sim$40.4 patients/hour).