← All posts

Tag

Agents

3 posts

Parallel Agents on Git Worktrees: Isolation Is Not a Checkout
GitAgentsTooling

Parallel Agents on Git Worktrees: Isolation Is Not a Checkout

A worktree per task stops two coding agents from overwriting each other's files. It does not isolate the approvals, hook paths and untracked instructions that decide what an agent does next — nor the lifecycle a headless run leaves behind.

October 12, 202612 min read
Read post
Guardrails for LLM Agents: Permissions, Scopes, and the Audit Trail That Holds Up
AIAgentsSecurity

Guardrails for LLM Agents: Permissions, Scopes, and the Audit Trail That Holds Up

Permissions, output validation, multi-agent delegation, and the audit trail that reconstructs the decision chain. A production handbook for shipping agents that survive contact with reality.

August 31, 202627 min read
Read post
When to Reach for an Agent, and When to Ship the Workflow
AIArchitectureAgents

When to Reach for an Agent, and When to Ship the Workflow

An LLM agent is a commitment, not a category. Here's the decision framework, the failure modes, the three-layer reliability model, and the hybrid architecture that actually works in production.

August 28, 202617 min read
Read post