Topic
AI Agents
Agent-assisted development, execution boundaries, observability, and validation.
8 public entries.
-
微电子学习工具笔记
课程工具、操作说明、官方配图与RC练习。
-
A result object is not an evaluated result
Why automated ANSYS Mechanical work needs separate geometry, setup, solver-input, solved, evaluated, and credibility gates.
-
Why ForgeSpec keeps a typed specification between a prompt and CAD
Separating requirement interpretation, domain planning, deterministic CadQuery generation, and artifact validation.
-
Known limits of a shared persistent terminal
Failure boundaries in shell recovery, cancellation, replay, backpressure, terminal negotiation, and interactive programs.
-
One shell, two observers: the persistent terminal architecture
How a native broker owns one PTY or ConPTY while an agent and a human share observation and controlled input.
-
What I tested in the persistent terminal broker
Observed Windows and Linux checks for PTY lifecycle, authenticated IPC, state persistence, cancellation, replay, and human takeover.
-
A narrow Mechanical delivery protocol
A stepwise Discovery-to-Workbench-to-Mechanical path with explicit success signals and recovery actions.
-
Failure taxonomy for automated Mechanical handoffs
Seven ways an ANSYS workflow can look complete while its solver, evaluation, delivery, or exported evidence is still incomplete.