Oct 09, 2026

Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab

Felipe Blanes from the Amazon AGI Lab shares lessons from working directly with customers of Nova Act, Amazon's browser agent service, from research preview to general availability on AWS. He argues that static benchmarks leave teams hoping their evals match real usage, and proposes a customer-driven eval flywheel, the trust cliff around 90% reliability, the value of being open about limits, and principles for keeping evals fresh.

Oct 05, 2026

Agentic Search vs Vector Search for Coding Agents: We Ran the Eval — Braintrust

This talk by Jess Wang from Braintrust delves into the critical importance of evaluations (evals) in AI development, moving beyond subjective "vibes" to data-driven decision-making. She breaks down the four core components of an eval—dataset, task, scoring, and experiments—and illustrates the continuous improvement "eval flywheel" integrating observability. The central experiment compares agentic search against vector search for a coding agent tasked with finding buggy code in Microsoft's TypeScript Go repo. While both methods achieved identical accuracy, vector search proved four times more expensive due to its inability to capture surrounding context within code chunks, leading to excessive, inefficient searches. Wang concludes with practical caveats and best practices for conducting effective LLM evals.

Sep 26, 2026

The Loop Is the Product — Roland Gavrilescu, Introspection

Roland Gavrilescu, co-founder and CEO of Introspection and formerly at xAI, presents a blueprint for autoresearch in 2026 built on three ideas: the loop is the product, system distillation is the moat, and valued work per watt is the score to optimize. He illustrates these with the OpenClaw car-haggling loop, the concept of portable agent recipes, and a talent-sourcing agent example that shows how to spot patterns in traces, calibrate judges with humans, and A/B test taste in production.

Aug 19, 2026

Why Your Enterprise Tech Stack Isn’t Ready for AI Agents — Christopher Lovejoy & Saul Howard

Chris Lovejoy and Saul Howard discuss the critical challenges of deploying AI agents in highly regulated enterprise environments, particularly healthcare. They advocate for a "constraints-first" architectural approach, proposing three core primitives – an immutable event log for auditability, schema-driven object storage for sensitive data, and human-agent equivalency for seamless escalation – which collectively enable privacy-preserving evaluations as a fundamental byproduct of the system design, rather than being an afterthought.

Aug 11, 2026

How Companies Are Building Their Own Intelligence | Sonya Huang, Sequoia Capital

Sonya Huang of Sequoia Capital discusses the strategic imperative for companies to embrace "sovereign AI" by owning their AI models and weights. She identifies cost, speed, performance, and controlling destiny as the four driving forces behind this shift. Huang argues that the competitive landscape is moving towards owning the intelligence layer, positioning application companies as the new innovation labs. She provides a practical, opinionated framework covering strategy (what to own vs. rent), team building, ensuring external legibility of research, and a technical roadmap for implementation, emphasizing how open-weight models now enable frontier-level performance through ownership and customization.

May 15, 2026

Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase

Pedro Rodrigues from Supabase shares key lessons from building an agent skill to work with Postgres and Supabase. He explains why critical security rules must go in the main skill file, the importance of pointing to living documentation, and how providing opinionated workflow guidance closes the reliability gap for agents in production systems.