AI Agents Conference 2025
who it's for
machine learning engineers, data engineers, ai product managers, platform engineers, security and compliance engineers, engineering managers, project managers
topics
guard-box architecture for financial AI; three-model consensus decisioning; agentic planning and reflection; retrieval-augmented agents; knowledge graph RAG; Neo4j vector plus graph retrieval; agentic web research assistants (Blazor .NET 9); production-ready code generation (SharpCoder); on-device policy enforcement and governance; architectural drift detection with agents; LLM hallucinations and mitigation
| title | author | length |
|---|---|---|
| From Black-Box to Guard-Box in Financial AI Security | Oleksandr Potapenko | 24m |
Claims a shift from opaque models to a regulator-ready Guard-Box architecture that wraps AI with four layers — input control, model governance, output control… | ||
| AI Agents as Financial Co-Pilots | AI-Driven Strategy & Decision Making | Sergei Nasibian | 26m |
Claims that agentic systems add reflection and planning plus tool access to LLMs, enabling conditional, multi-step workflows rather than single-prompt outputs… | ||
| AI Agents as Architectural Strategists | Aligning System Design with Business Goals | Avraam Tolmidis | 28m |
Claims an agent pipeline that continuously detects architectural drift, quantifies technical debt and business impact, and simulates recoveries using a Python… | ||
| SharpCoder Demo: AI Agents Powering Enterprise Vibe Coding | John Godel, Rohit Gupta, Kautilya Utkarsh | 23m |
SharpCoder generates production-ready apps from short prompts, auto-fixing grammar, inferring intent, and doing internal prompt engineering to add missing… | ||
| Designing Empathetic, Resource-Aware AI Agents at Scale | Rohan Mitra | 28m |
Argues for a concrete governance OS that wraps agents with a four-pillar governance model (policy, orchestration, feedback, override), describes an on-device… | ||
| Retrieval-Augmented AI Agents for Entity Matching at Scale | Sergey Polyashov | 28m |
Retrieval plus multi-stage LLM reasoning powers a scalable pipeline that builds a unified product graph in batch and matches new offers in real time via a… | ||
| What Are AI Hallucinations? | Maria Piterberg | 28m |
Defines hallucinations as LLMs and generative models producing convincing but fabricated outputs, with concrete failures: Dow Jones dropped 85 points in under… | ||
| Four Steps to Embed AI Agents into Workflow | Dmitry Bobolev | 26m |
Four concrete steps: pick a narrow task, build a fast prototype, add guardrails, and scale via a small lighthouse team. Example implementation uses… | ||
| Four Steps to Embed AI Agents into Workflow | Dmitry Bobolev | 26m |
Four practical steps: pick one narrow task (e.g., order-status queries), build a fast prototype in days or hours using speech‑to‑text + DB lookup + voice… | ||
| Will AI Replace Project Managers? | Sarah Abdelhady | 21m |
Claims that program managers spend 80% administrative overhead and that AI agents like Gemini Sheets plus document notebooks synthesize emails, spreadsheets… | ||
| Agentic RAG with Knowledge Graphs Explained | Siddhant Agarwal | 30m |
Argues that vector-only RAG fails at multi-hop reasoning and shows a production path where Neo4j stores vectors natively, exposes 70+ graph algorithms, and… | ||
| How to Build Agentic Web Research Assistants | Live Demo & Code | Frank Boucher | 30m |
Demo builds an Event Finder web research agent that searches live sites iteratively, aggregates results, and returns a validated JSON list with name, start/end… | ||
| nothing matches | ||