Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The talk reframes enterprise AI deployment failures as systemic infrastructure gaps — not model selection problems — showing that observability, evaluation pipelines, and governance tooling must be built before a model is even chosen.
The `give_feedback` pattern fills a blind spot in MCP server observability — telemetry can show which tools fail, but only an agent-callable feedback tool can surface whether the agent actually accomplished its goal or had to work around a gap.
The paper resolves a contested debate by showing that guidance production method — not guidance presence alone — determines whether `AGENTS.md` files help or hurt coding agents, and provides a concrete tuning procedure that raises SWE-bench Verified resolve rate by 7.5 percentage points over an unguided baseline.
Artifacts replaces static session exports with auto-refreshing, session-aware pages that teams can view collaboratively through a private organizational link.
The RATs framework demonstrates that self-directed play — without any explicit task instructions — can build a reusable, transferable code skill library that improves both in-distribution and real-world robot task performance without retraining the underlying model.
Cursor Automations now respond to GitHub events and can operate cloud agents with computer use, expanding the scope of automated workflows the product supports.
The decomposition replaces impractical logprob- and training-based uncertainty methods with a prompt-only approach that works under real deployment constraints, enabling LLM agents to proactively seek clarification on ambiguous tasks rather than acting on underspecified instructions.
The comparison introduces a verifiable track record as a distinct evaluation axis for MCP servers, distinguishing tools that return auditable accuracy records through the MCP interface from those that only supply raw data or indicator output.
The tool reduces repeated repository rediscovery by AI coding agents, cutting 4k–13k tokens of redundant context per prompt.
The template removes the manual work of replicating a complex 64-agent, 261-skill Claude Code configuration by packaging it as a one-click, fully isolated microVM fork with the creator's persisted state included.