Suyash Dubey
I build production AI agents that automate real workflows
Profile in progress
Suyash is building their profile!
Built and maintained a HIPAA compliant production medical AI scribe system that uses multi-step LLM agents to extract clinical entities directly from physician-patient conversations and turn them into structured medical notes, cutting down the manual transcription work clinicians used to do after every visit.
Multi-stage clinical workflow: Documentation, coding, and review each have different logic and conditional paths, and the system needed to branch correctly between them without losing context.
Clinical accuracy: Generated notes had to be grounded in real patient history and clinical guidelines, not just plausible-sounding text.
Production reliability: As a live system handling real conversations, every agent run needed to be observable, debuggable, and monitored for cost and latency in real time.
Non-technical requirements gathering: Clinical needs had to be captured accurately from stakeholders without a technical background and translated into precise agent logic.
Approach:
Stateful agent orchestration with LangGraph
Designed LangGraph-based agent workflows with conditional branching, allowing the system to move correctly across documentation, coding, and review stages based on conversation content.
Context-grounded note generation with RAG
Built a RAG pipeline on AWS Bedrock with embeddings, so every generated note is grounded in the patient's actual history and relevant clinical guidelines rather than generic output.
Full production observability
Integrated Langfuse across all agent runs to track token usage, latency, and model KPIs, giving the team visibility into system health and cost in production, not just at build time.
Clinical stakeholder collaboration
Ran requirements sessions directly with clinical staff, converting their documentation needs into concrete agent behavior specs and validation criteria.
Results & Impact:
~40% reduction in manual transcription time for clinicians using the system.
Clinically grounded output, with notes tied to real patient history and guidelines instead of unsupported generation.
Full production observability, with token usage, latency, and model performance tracked continuously.
A workflow clinicians could trust, built through direct collaboration rather than a black-box handoff.
Provided Services & Solutions:
📌 AI Agent Development (LangGraph)
📌 RAG Pipeline Development (AWS Bedrock)
📌 LLM Observability (Langfuse)
📌 Cloud Infrastructure (AWS Lambda, S3, DynamoDB)
📌 Stakeholder Requirements Translation
📌 Production ML Systems
Tech Stack
Python · LangChain · LangGraph · AWS (Bedrock, Lambda, S3, DynamoDB) · Langfuse · TypeScript · REST APIs
1
9
Overview 📖
Built an end-to-end agentic content creation pipeline for a fast-growing AI-powered SEO platform. The system chains multiple LLM agents together to research, draft, and optimize content automatically, replacing what used to be a manual, multi-step editorial process with a single automated workflow.
Collaboration 🤝
Partnered directly with the platform's engineering team to design and ship the automation layer that now sits at the core of their content operations, turning a bottlenecked manual process into a scalable, always-on pipeline.
Key Challenges 🤔
Multi-step content logic: Research, drafting, and optimization each require different context and tone, but had to feel like one coherent pipeline, not three disconnected tools.
Consistency at scale: Every piece of generated content had to match brand voice and pass compliance checks, without a human reviewing each one manually.
Orchestration complexity: Content jobs needed to trigger reliably from webhooks and third-party APIs, run through multiple agents in sequence, and fail gracefully without stalling the whole pipeline.
Performance under load: The backend had to stay fast and stable as content throughput scaled up.
Approach 🔍
Agentic content pipeline design
Designed a multi-step LangChain agent chain with tool-calling, where each agent (research, drafting, optimization) has a clearly scoped role and hands off structured output to the next.
Workflow orchestration with n8n
Built n8n automation workflows to handle webhook triggers, third-party API integrations, and job routing, removing the need for manual intervention at almost every stage.
Brand voice & compliance enforcement
Layered in structured prompting and validation steps so generated content stays on-brand and passes compliance checks automatically, at scale.
Backend performance tuning
Optimized FastAPI endpoints and managed Azure-hosted PostgreSQL databases to keep latency low under high content-throughput conditions.
Results & Impact ✨
~60% reduction in manual intervention across the content pipeline, freeing the team to focus on strategy instead of babysitting workflows.
Consistent brand voice at scale, with compliance checks running automatically instead of manually.
Reliable, low-latency infrastructure validated under real content-throughput loads.
A reusable agentic architecture the platform can extend to new content types without rebuilding the pipeline.
Provided Services & Solutions ✅
📌 AI Agent Development (LangChain)
📌 Workflow Automation (n8n)
📌 LLM Integration (GPT-4, Claude)
📌 API Development (FastAPI)
📌 Cloud Database Management (Azure, PostgreSQL)
📌 Architecture Design & Consulting
Tech Stack
Python · FastAPI · LangChain · n8n · GPT-4 · Claude · Azure · PostgreSQL
1
23