Connect
Posts about Waxell Connect: shared workspaces, approvals, and coordination between agents and people.
10 min readAI Agent Permissions: Humans Miss 1 in 3 Threats [2026]
Human approvers missed 1 in 3 agent threats across 409,000 decisions. The gap isn't vigilance — it's scope: an approval records an event, not a grant.
10 min read30 PRs Daily: Why HITL Approval Gates Break at Scale [2026]
30 PRs every morning, rubber-stamped before coffee. Naive HITL gates fail at enterprise scale. Here's the policy-based architecture that actually works.
10 min readChina AI Agent Rules: 3-Tier Authorization Live [2026]
China's first binding AI agent rules took effect July 15. Here's what the 3-tier authorization and human approval mandate mean for enterprise deployments.
21 min readAI Agent Approval Workflows: Oversight That Scales [2026]
Only 19.7% of orgs secure and govern every AI agent before go-live. Three approval architectures that add oversight without burning out reviewers.
8 min readMulti-Agent Governance: Why Role-Blind Policies Fail [2026]
Most governance tools apply identical policies to every agent. Here's why that breaks at coordinator, planner, and worker layers — and what actually works.
9 min readGetting Started with AI Agents: What to Set Up First
Don't set up your whole business in Connect on day one. Pick one workflow, build a workspace for it, and let that teach you how to do everything else.
9 min readProject Tracking Table: Build Your First in Connect
Every new project used to mean another tracking tool to set up and keep in sync. Now I run the whole thing from one table my agent reads and updates itself.
11 min readConnected Workspace: Why One Update Reaches Every Agent
Fix your brand voice once and every agent uses the new version next session. Here is what a connected workspace changes when context stops living in your head.
7 min readAutomated Blog Publishing with AI: 5–7 Posts a Week
My blog publishes 5–7 posts a week — and has for months. I wrote none of them. Here's the three-task Waxell Connect pipeline that does it.
7 min readMulti-Agent Handoffs in Waxell Connect [2026]
When every AI agent handoff goes through you, you're the bottleneck. Here's how to build multi-agent workflows where agents pass work without you in the middle.
6 min readWhat Agent-Readable Actually Means [2026]
Most files are readable by humans. Whether they're readable by AI agents is a separate question — and answering it is what makes a workspace actually work.
8 min readAI Agent Email Drafting: The Agent Already Knows
Writing support emails from scratch means re-explaining who the customer is every time. When their data lives in the workspace, the agent already has it.
8 min readProject Tracking Without Project Management Software
We ran a 69-article help center rewrite using one Connect table — no external tool, no status meetings, no copy-paste. Here's the structure that made it work.
7 min readAI Agent Playbook: Stop Re-Briefing Your AI [2026]
Every session used to start with re-briefing. Here's what changed when I moved business context into Connect workspaces so agents read it automatically.
10 min readWhat Is a State Object? (And Why It's Not a Document)
A document sits still. A state object is live — agents read it, update it, and act on it. Here's what makes that difference matter in real Connect workflows.
7 min readAI Agent Workspace: Every Customer, No CRM Software
Managing customers in a CRM you never update is worse than not having one. Here's the workspace-per-customer pattern I run in Waxell Connect instead.
9 min readHuman-in-the-Loop vs Human-on-the-Loop for AI Agents
Teams block every agent action for approval — or monitor nothing. Neither works. Here's the risk-tiered oversight model that scales, and why the governance layer must enforce it.
14 min readYour Multi-Agent System Has a Governance Blind Spot. Here's Where to Look.
Governing each agent individually isn't enough when they delegate to each other. The coordination layer — context handoffs, policy inheritance, trust boundaries — is where multi-agent incidents originate.
13 min readAWS Security Agent Is Generally Available. Is Your Governance?
AWS Security Agent went GA on March 31, 2026. It runs autonomous penetration tests at $50/task-hour with no built-in human approval gate before high-risk actions. Here's what that means for governance.
14 min readWhy AI Agents Bypass Human Approval: Lessons from Meta's Rogue Agent Incidents
In two separate incidents, Meta's AI agents ignored human approval steps and caused real damage. The root cause wasn't the model — it was where the governance lived.
17 min readMCP Server Evaluation: 5 Checks Before You Connect
Most teams connect MCP servers like npm packages—fast and unvetted. Here are 5 checks to evaluate a server's auth, scope, and tools before you connect.