Dor Sasson argues that the 2026 AI pricing crises at Anthropic, OpenAI, and GitHub were infrastructure failures: usage was checked after invoicing rather than before inference. He proposes synchronous entitlement checks with asynchronous settlement, borrows banking concepts such as holds, double-entry bookkeeping, and credit sources, and outlines four patterns for selling AI at scale.
Varun Krovvidi of Resolve AI explains why AI excels at code generation but struggles with the complex, multi-domain problem of running and fixing software in production. He outlines five common failure modes for AI agents in production (anchoring bias, context issues, coherent vs. causal answers, guardrails, lack of learning) and introduces Resolve AI's six-pillar architecture: model orchestration, context engineering, causal reasoning, governed actions, learning systems, and multi-level evaluations. A demo illustrates how Resolve AI diagnoses a Grafana alert to its root cause, ruling out coincidental events and maintaining its causal reasoning.
Sheilah Kirui explains speculative decoding for LLMs, detailing how a small draft model proposes tokens for a larger target model to verify in a single pass, accelerating the decoding phase. She covers the memory costs of hosting two models, criteria for choosing an effective draft model, and demonstrates its benefits for structured output (1.6x faster with high acceptance) versus its limited gains for creative tasks. The talk concludes by outlining when speculative decoding is most advantageous, considering VRAM availability, batch size, workload type, and context length.
Ben Dicken of PlanetScale argues that teams can move fast without breaking production, combining isolation, redundancy, sharding, back pressure, and decoupling with AI agent workflows such as VSchema-driven sharding, Traffic Control budgets, schema branching, and one-click reverts. His core claim is that good developer experience produces good primitives for AI.
Jennifer Neville discusses her research into "surprising failures" in AI systems, where models, particularly LLMs, struggle with complexity in realistic user workflows. Her team focuses on practical evaluation for multi-turn conversations and agentic knowledge work, emphasizing the need for robust AI that understands context and user intent over time. She offers insights into bridging the gap between user expectations and AI capabilities, advocating for detailed user feedback and outlining the future of human-AI collaboration.
Dru Knox of Tessl discusses harness engineering, the discipline for building software factories with AI agents. He outlines a factory's three pillars—autonomy, automation, quality—and introduces inner, outer, and meta loops. Knox explains why this field is challenging and proposes a three-layer architecture: control plane, agent-ready stack, and improvement loops, concluding with key metrics to track progress towards an agent-driven software development future.