Video · Source Linked
WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa SankarAtlan’s agent experiments argue for shared, versioned context instead of per-agent memory: a portable layer for business facts, skills, norms, retrieval, and feedback across changing harnesses.FEED7 SUMMARY
Video · Source Linked
Don't Ship Skills Without Evals — Philipp Schmid, Google DeepMindAgent skills need regression tests, not manual spot checks. Test triggering and output with and without each skill, across repeated trials and the harnesses your team actually uses.FEED7 SUMMARY
benchmark#skills
Video · Source Linked
Forward Deployed Engineering at Cursor — Pauline BrunetCursor’s FDE playbook treats agent deployment as co-development: choose measurable use cases, require customer ownership, avoid staff augmentation, and document the handoff.FEED7 SUMMARY
industry#enterprise
Video · Source Linked
"The engineer of the future is the person who is able to choose what is worth doing." — Addy OsmaniOsmani argues that agent throughput makes evidence-backed judgment the engineering bottleneck: builders should require explainable diffs, tests, logs, and explicit ownership before shipping.FEED7 SUMMARY
agent#harness-engineering
Video · Source Linked
"I've never seen anything scarier than an LLM with tool calls." — Erik Meijer aka @HeadinTheBoxA proposed agent harness separates planning from execution, represents tool calls as inspectable programs, and requires machine-checkable safety proofs before side effects run.FEED7 SUMMARY
agent#harness-engineering
Video · Source Linked
Stop Evaluating Models Like It's the 50s - Alejandro Vidal, MindmakersItem response theory can reveal weak eval questions, quantify uncertainty, and select smaller suites that preserve model rankings, making internal agent evals cheaper and more diagnostic.FEED7 SUMMARY
Video · Source Linked
From fork() to Fleet: Designing an Agent Sandbox Cloud — Abhishek Bhardwaj, OpenAILong-running coding agents need isolated, persistent sandboxes: microVMs limit kernel exposure, while incremental snapshots enable recovery, branching, and faster placement across a fleet.FEED7 SUMMARY
infra#sandboxing