Mehul Marvania

🚀 Reimagining Prior Authorization on Insurer side with AI Agents The traditional pre-authorization process is slow, manual, and error-prone — involving multiple teams and fragmented data. Here’s how Agentic AI can streamline it 👇 🧠 PreAuth Intake Agent – Handles forms in any format and validates data. 📑 Policy Coverage Validator – Checks member eligibility and policy limits. ⚕️ Medical Necessity Evaluator – Reviews guidelines and maps diagnosis to treatment. 💰 Cost Impact Assessor – Estimates costs and applies pricing rules. ⚖️ Final Decision Maker – Synthesizes all inputs and delivers an instant approval or denial. With this modular design, insurers can automate 80%+ of pre-auth reviews — cutting decision time from days to minutes. #AIinHealthcare #AgenticAI #PriorAuthorization #HealthTech #Automation #InsuranceInnovation

6

Eval is not unit testing. If you treat evals like static pass/fail scripts, you’re missing their real purpose. Think of evals as a PRD for your AI agent’s behavior: a living, evolving contract for what “good” means in production. And like any PRD, it should have observability built in so you can track outcomes, pinpoint weaknesses, and refine in an automated, continuous loop. Improvement without measurement is limited and imprecise. Evals give you the clarity you need to systematically improve your app, not limited at the feature level, but across the full agent lifecycle. They tell you where you’re drifting from the product’s intent, why performance is slipping, and how to course-correct with precision. Instead of snapshot testing, you’re running a feedback engine that constantly learns from both successes and failures. In the application layer, it’s about setting big-picture goals, like “help a customer dispute a fraudulent transaction” or “recommend the right investment product for their profile.” Then you throw everything at it half-filled forms, conflicting details, urgent time limits and see if it still gets the job done. The point isn’t to check if it spits out a canned line, it’s to see if it can solve the problem accurately, fast, and in a way that stays within compliance and cost boundaries. My recommendation approaches to make evals work for AI agents: 1. Define capabilities, not scripts – Focus on what success looks like rather than exact matches. 2. Simulate real-world variability – Feed in unpredictable, noisy, and edge-case inputs. 3. Instrument for observability – Capture reasoning traces, model calls, and decision trees for explainability. 4. Automate refinement loops – Turn eval failures into direct triggers for retraining, prompt tuning, or guardrail updates. 5. Score across multiple dimensions – Measure accuracy, latency, cost efficiency, compliance, and user experience impact in parallel. When done right, evals validate your AI agents and steer them. They transform from a passive QA step into the heartbeat of your improvement cycle, ensuring every release moves the agent closer to its ideal, measurable definition of “good.”

40

3 Comments

Ed Donner, Sachin Chandrashekhar 🇮🇳 Building an Agentic AI Email System: I have been experimenting with Agentic AI and the OpenAI SDK to automate email workflows, and it’s been an amazing hands-on learning experience. Here is what I did: 1. Built agents that can draft emails automatically. 2. Created tools to generate email subjects and convert plain text into HTML emails. 3. Implemented a handoff system so the best draft gets selected and sent automatically. Learned how important tool prompting and agent instructions are to make the workflow smooth. It’s exciting to see AI agents working together, almost like a small team, to get a task done. This project really helped me understand how to orchestrate AI for real-world automation, like email campaigns or notifications. Next, I want to explore connecting this system to LinkedIn posts and automated data pipelines—bringing end-to-end automation to life. #OPENAI Agentic SDK #OPENAI #GPT Models # GEMINI #Python #Automation #DataEngineering #AWS Pipelines. Code Snippet: emailer_agent = Agent( name="Email Manager", instructions=instructions, tools=email_tools, model="gpt-4o-mini", handoff_description="Convert an email to HTML and send it") tools = [hr_tool1, hr_tool2] handoffs = [emailer_agent] hr_instructions = ''' You are an HR agent at Cognizant. You are responsible for recruiting Data Engineers. Steps you must follow: 1. Use the HR tools such hr_tool1 and hr_tool2 to generate candidate email drafts. 2. Evaluate all drafts and choose exactly one best draft. 3. Handoff only this single best draft to the emailer_agent for formatting and sending. Critical Rules: - You must always use the HR tools to generate drafts (never write the drafts yourself). - You must never output more than one draft. - You must always handoff exactly one draft to the emailer_agent. - Do not ask clarifying questions or request more input. - Produce the final result in one step with a single handoff.''' hr_manager = Agent( name='hr manager', instructions=hr_instructions, tools = tools, handoffs= handoffs, model = 'gpt-4o-mini' ) with trace('Hr agent'): try: response = await Runner.run(hr_manager, "Send out a Recruiting email addressed to Dear Applicant from OPENAI") except : response = {"final_output": "Could not complete in 2 turns, please retry with higher max_turns."}

3

Regulatory uncertainty surrounding the H-1B visa program is creating a significant talent crunch for U.S. companies, particularly for Indian-led AI startups. According to a recent Linkedin News report, the current climate is causing H-1B holders to hesitate leaving stable Big Tech jobs for startups, fearing instability. This is even affecting lateral hires, who are reportedly backing out of offers. In response, startups are adapting their hiring strategies: 🔹 Prioritizing recruitment of U.S. citizens, green card holders, and F-1 student visa holders. 🔹 Shifting to a bifurcated model: hiring go-to-market roles in the U.S. while sourcing tech talent directly from India. A key point of clarification from USCIS on the new $100,000 H-1B fee: ✅ Applies to: Only new H-1B petitions for workers currently outside the U.S. who do not have a valid visa. ❌ Does NOT apply to: Status changes (e.g., F-1 to H-1B), amendments, or extensions for individuals already within the U.S. This distinction may benefit Indian students currently in the U.S. on F-1 visas, as they are exempt from this fee. Overall, these policy shifts are reshaping how U.S. companies approach international hiring and visa sponsorship. #H1B #USTech #Startups #TalentAcquisition #Immigration #HiringTrends #AI #India

1

A Thought Exercise : Context Engineering with LLMs is analogous to Feature Engineering in Classical ML What are the similatieties and differences ? Share in the thread #AImusings courtesy: Jim Hong :)

28

9 Comments