Agent 工程

RTK filters test, Git, search, and build noise before command output enters model context, applying context engineering at the tool-output boundary.

OpenCompany uses company.toml, agent teams, and human sign-off to put organizational structure and agent configuration into version-controlled files.

AI agent engineering readings for September 4 to 10, 2026, with key findings, engineering implications, suggested sections, and primary sources.

How jcode handles multi-agent resources, state synchronization, and verification in its harness, beyond the capabilities of the model alone.

OpenAI organization-level data suggests that more coding-agent use shifts bottlenecks to task decomposition, concurrency, harnesses, evaluation, and selection.

Strands harness-sdk, Harness MCP Server, and HydraFusion show why agent engineering needs control over context, permissions, state, validation, and recovery.

A multi-agent engineering workflow uses isolated worktrees, CI, cold-start review, evidence gates, and layered context to control delivery of AI-generated code.

A source-backed review of Vercel Eve’s filesystem-first agent model, durable execution, tools, sandboxes, approvals, deployment, and Vercel platform tradeoffs.

Break down planning, execution, evaluation, state management, and stopping rules to keep multi-step agent tasks controlled and traceable.

A 48-hour hackathon build of an event-driven multi-agent runtime with registry, workflow, execution, negotiation, settlement, and observability layers.