Building Reliable Agents - Evaluation Challenges
Exploring the challenges of evaluating agent reliability and LLM performance.
6 docs tagged with "evaluation"
View all tagsConference Brief
Briefing document for LangChain Interrupt 2025.
Conference Brief
Executive briefing on LangChain Interrupt 2026 — the deep-agents era, LangChain's platform launches, evals as infrastructure, and production agents across regulated industries.
From Pilot to Platform - Aladdin Copilot
BlackRock's approach to building Aladdin Copilot, a sophisticated assistant for investment management.
Multi-Agent Frontiers - Building Ask D.A.V.I.D.
JPMorgan Chase's multi-agent system for investment research that integrates structured data, RAG, and analytics.
Presentation Directory
Quick digest table summarizing the LangChain Interrupt 2025 conference presentations.