Tokenless

Agent infrastructure

Smarter Models Killed the Harness. Here's What's Left — Jediah Katz, SpaceXAI

Smarter Models Killed the Harness. Here's What's Left — Jediah Katz, SpaceXAI

Jedidiah Katz, longtime agent-harness engineer at Cursor and now at SpaceX, argues that fancy harnesses no longer add coding intelligence because models absorb those skills through a data flywheel. He contends the harness matters more than ever: it unlocks new frontiers like Grokbot and owns infrastructure, trust and security, and efficiency. He closes with predictions, including that 90% of agent work will run off the laptop within six months.

From coding to Knowledge work agents — Karan Vaidya, Composio

From coding to Knowledge work agents — Karan Vaidya, Composio

Karan Vaidya of Composio explains why AI agents have excelled in software engineering but struggle in other knowledge work domains. He identifies six critical primitives—centralization, history, context, verification, governance, and reversibility—that coding inherently provides but are largely absent in general knowledge work, hindering agent effectiveness and trust. The current bottleneck for AI agents is not the models, but the missing infrastructure around them.

You Didn't Ship a Bug. You Just Wrote It for a Human. - Ravi Madabhushi, Scalekit

You Didn't Ship a Bug. You Just Wrote It for a Human. - Ravi Madabhushi, Scalekit

Ravi Madabhushi details how existing infrastructure, designed for human users, fails AI agents, leading to issues like rate limits and over-permissioning. He argues for treating agents as first-class principals with fine-grained, context-aware authorization and robust visibility to prevent non-deterministic and potentially rogue behaviors.

Your Agents Need a Save Button - Hamza Tahir, ZenML

Your Agents Need a Save Button - Hamza Tahir, ZenML

Most AI agents lack a "save button" for persistent state, making debugging and optimization challenging. This talk introduces the concept of a durable runtime with checkpointing, allowing developers to replay agent executions, perform "what-if" analyses (e.g., swapping models, mocking tools), and conduct cohort-based evaluations using production data. The open-source tool Kitaru is demonstrated as a solution to build, debug, and improve agents at scale by capturing full execution state, not just traces.