Rebecca Le and Zach Daniel, co-authors of the Ash Framework book, discuss how their Tunez-based guide was built to introduce concepts in the order a real project needs them, how writing it forced the addition of generator-based testing to Ash, and why Ash's extensibility, Cinder's rapid development, and AI-assisted onboarding make its steep but flattening learning curve worthwhile.
Martin Keen explains loop engineering as the next step beyond prompt engineering: designing systems where AI agents act, observe, adjust, and repeat toward verifiable goals. The discussion covers goal design, triggers, context and persistent state, tools via MCP and APIs, verifier subagents, and why humans must remain in the loop to manage comprehension debt, intent debt, and cognitive surrender.
Ryan Ahern of Exa presents Exa Snapshot, a point-in-time web search that lets agents query the web as it appeared on any past date, and shows how teams can backtest predictive signals and financial models without overfitting.
Ryan Ahern of Exa explains how version-controlled search through Exa Snapshot lets you view the web as it existed on a past date, enabling backtests of AI agents while avoiding look-ahead bias. A hands-on acquisition-prediction exercise illustrates feature tuning and the dangers of overfitting without holdout sets.
The OpenProse team presents a declarative approach to multi-agent workflows, where developers and domain experts write contracts in plain markdown that any harness can compile and run. The talk covers event-driven jobs triggered by webhooks and pull requests, a grumpy-senior PR reviewer demo, a bank model-documentation workflow, composing contracts, pinning successful runs into deterministic workflows, and how the approach contrasts with DSPy.
Emmanuel Ameisen, an interpretability researcher at Anthropic, explains how the team looks inside models like Claude to understand how they actually think. The conversation covers why next-token prediction hides real planning and conceptual representation, why models are grown rather than built, how intermediate activations reveal structure, why anthropomorphic framing can be useful, how smooth scaling produces sudden capability thresholds, and how interpretability ties into alignment, safety, and the broader question of what these systems are.