写作
Agent 工程
筛选文章 Agent 工程
Agent 工程
第 3 页 · 12 / 46-
Where agent credentials belong: host, vault, and broker Where keys belong when coding agents call GitHub, databases, and cloud APIs, and how vaults and credential brokers define access boundaries.
-
AI agent engineering reading list | 2026-09-11 to 09-18 AI agent engineering readings for September 11 to 18, 2026, with key findings, engineering implications, suggested sections, and primary sources.
-
Why more agent tools can mean worse tool selection How Tool Search loads definitions on demand, affects prompt caching, and differs from MCP connections and ARD resource discovery.
-
AI agent engineering reading list | 2026-09-11 to 09-17 AI agent engineering readings for September 11 to 17, 2026, with key findings, engineering implications, suggested sections, and primary sources.
-
Foreman: an independent supervisor for coding agents How Foreman separates a coding agent from supervision, using runtime evidence, Jev judgments, and deterministic policy to continue, verify, stop, or escalate.
-
AI agent engineering reading list | 2026-09-11 to 09-16 AI agent engineering readings for September 11 to 16, 2026, with key findings, engineering implications, suggested sections, and primary sources.
-
Turn production agent failures into regression tests Use Kitaru Replay, Evaluator, and Regression Suite to preserve production failures as repeatable agent tests, with tool policies and CI gates.
-
Why long tasks need more than one growing conversation How OpenAI Agents API and Anthropic Managed Agents use sessions, context windows, compaction, and persistent state for long-running agents.
-
What Tau solves by splitting an AI agent into three layers Tau separates model adapters, the agent core, and the application so tools and frontends can work together without depending on each other.
-
Connecting an agent loop to a frontend with events Follow tool execution and repeated model calls, separate streamed deltas from final messages, and explore frontend state with a model-free Python demo.
-
AWS agents propose; deterministic code validates How AWS separates agent proposals, rule checks, human approval, and execution, with code enforcing boundaries and idempotency.
-
A reliable agent might leave the code alone today GitHub Agentic Workflows jsweep checks whether a change is worthwhile and treats noop as valid, instead of forcing automation to produce a diff.