Copilot Studio: agent accounts, process memory, GitHub Copilot harness triggers
At a glance
Microsoft Copilot Studio adds org-owned managed agents with their own Microsoft 365 credentials (@mention in Teams/Outlook/Office comments), business process memory that carries preferences across cycles, and GitHub Copilot harness triggers so agents start on email or a cadence without a new prompt—rolling out via Frontier. This workflow is listed under enterprise-agent, persistent-agents, team-workflow, triggers, devtools.
Agents / tools
Microsoft Copilot Studio, GitHub Copilot harness, Microsoft 365, Teams, Outlook
AGPL self-hostable workspace runs Claude Code, Codex, OpenCode or Pi in isolated sandboxes; hand off from Slack/web/API, attach playbooks/skills/knowledge, approve sensitive actions, and get PRs or files back—positioned as an open Devin alternative.
junegunn (fzf author) documents how shell CTRL-T bindings die once you live in an agent prompt—and how tmux PREFIX bindings restore fzf: tmux-fzf-complete (files/dirs/URLs/on-screen paths/sentences) and fzf-git.sh (commits, branches, PRs) inject selections as keystrokes into Claude Code or Codex. Requires tmux 3.7+ floating panes and agent settings that keep scrollback (/tui default for Claude Code; Codex alternate_screen=never). Pattern: make agent prompts as completable as the shell.
Builder moved Claude Code + repos off a lagging MacBook onto a Grok Bot cloud PC, sends tasks from Mac/iPhone via T3 Code, and locks access with Tailscale. Pattern: keep heavy agent loops on the bot machine; approve push/deploy locally.
Official Muse Code cookbook: four built-in playbooks load only on the turn you invoke them. /plan grounds a decision-complete plan and stops for approval; /grilling and /grill-with-docs pressure-test designs (optionally writing ADRs); /taste strips AI-slop UI defaults. Explicit-invocation only—won’t auto-plan ordinary implement requests.