Beyond the Prompt: Building Research Agents in Python
Speaker
Simona Skiotytė
As a Software Developer for the Generative AI platform at Nasdaq, Simona Skiotytė specializes in architecting the integration of Generative AI systems on AWS. Key projects include the integration of a research system that automates query generation, iterative web search, and multi-stage report synthesis, all orchestrated in AWS. Simona's foundation in data science comes from her time at ETH Zürich, where she applied statistical and mathematical models to large-scale biological datasets, utilizing dimensionality reduction, clustering, and regression modeling. This background provides a strong analytical lens through which Simona approaches the construction of Generative AI systems.
Abstract
LLMs can answer questions, but can they conduct research? Real research requires planning, data gathering, synthesis, and refinement. This talk explores Python patterns for orchestrating multi-step workflow to create autonomous research agents. We'll deconstruct the agentic architecture, from DAG-based planning to reflection loops, and show how to implement these concepts using practical Python patterns.
Description
While early LLM API calls were stateless and frozen in time, the landscape has evolved dramatically with the rise of "thinking models." OpenAI's o1 and Gemini's reasoning models stop, reflect, and follow logical steps before responding. With Gemini integrating Google Search, these models can access vast information and decompose complex problems in real-time. To harness this, we need to move beyond prompting to building autonomous, multi-step agents. This session covers:
- Agentic Shift - moving from prompts to agents, using Pydantic to enforce structured outputs, and giving LLMs tools, memory, and environment feedback.
- Decomposing the research process into specialised agent nodes: Planning Agent that breaks queries into a DAG of sub-tasks, parallel Executor Agents that search and evaluate sources, and a Synthesizer Agent that produces a coherent report.
- Reflection & Quality Control – implementing gap analysis where the system reads its own draft and formulates follow-up queries, plus the LLM-as-Judge pattern for evaluating source relevance and authority before synthesis.