Praneeth Paikray

Praneeth Paikray

Senior Generative AI Specialist

Manpower Group

Praneeth Paikray is a Senior Generative AI Specialist at Manpower Group, bringing 8 years of experience in data science across financial services, enterprise technology, and workforce solutions. His expertise lies in architecting AI solutions that directly impact business metrics, focusing on three key pillars: enhancing revenue through fine-tuned LLMs and recommender systems for upsell paths and margin gains; providing Board-Room Insights via aspect-sentiment analysis, forecasting, and conversational analytics for data-backed strategy; and enabling enterprise AI to Scale with Slides through cloud-native AI/ML pipelines and hands-on leadership, ensuring explainability for executives.

Praneeth's foundational education includes an MTech in Data Science from BITS Pilani (2021-2023) and a BTech in Electrical Engineering from OUTR (2013-2017), supplemented by continuous learning in Event-Driven Agentic Document Workflows and AI Agents Fundamentals. His career trajectory showcases a progression from Systems Engineer at TCS (2017-2019) and Data Science Developer at Dell (2019-2021), to Data Scientist and Senior Data Scientist at Fidelity (2021-2025), culminating in his current role leading GenAI initiatives at ManpowerGroup since 2025. This journey reflects his consistent ability to translate data science theory into measurable business outcomes and production deployments.

Your email AI agent works perfectly in demos but fails in production. It confuses client contexts, suggests outdated meeting times, and drowns in month-old thread history. You manually fix prompts after each failure, but the problems keep evolving.
 
The real issue? Static context management can't handle email's dynamic complexity.
 
In this 50-minute hands-on session, we'll build an email agent that combines context engineering with DSPy's self-optimization. You'll implement the four-move context framework: Write, Select, Compress & Isolate, but supercharged with optimizers that learn from every correction you make.
 
Instead of hardcoding rules for "include last 5 emails" or "summarize threads over 1000 tokens," your agent will learn what context actually matters for YOUR email patterns. When you correct a response, DSPy optimizers automatically adjust how the agent selects, compresses, and isolates context: with minimal prompt engineering.
 
The Adaptive Context Pipeline We'll Build:
 
  • Write + Learn: Persistent memory that evolves—DSPy learns which client details, project states, and communication patterns to remember based on your feedback
  • Select + Optimize: Move beyond static relevance scoring; BootstrapFewShot learns from your "this context was helpful/harmful" ratings to improve email thread selection
  • Compress + Adapt: Smart summarization that improves—MIPRO optimizes compression strategies based on which summaries led to accurate responses
  • Isolate + Protect: Dynamic guardrails that learn which email patterns cause context poisoning and automatically filter them based on past failures
Read More

Get ready for a high-stakes AI face-off as three leading multi-agent frameworks - AutoGen, CrewAI, and LangGraph, go head-to-head solving the same real-world AI problem: Building a Multi-Agent Helpdesk AI Assistant.

Watch top Agentic AI practitioners demonstrate how each framework tackles this challenge: from structuring agent teams to orchestrating decisions across multiple steps. This unique session combines live hands-on demos and a panel discussion. You’ll walk away with a clear view of what each framework does best, where they struggle, and how to pick the right one for your next Agentic AI project.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More
Book tickets View all speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details