Why AI agent teams are just hoping their agents behave

Published: (March 31, 2026 at 11:45 AM EDT)
3 min read
Source: Dev.to

Source: Dev.to

The Problem

Every trending AI project is giving agents more autonomy—running shell commands, browsing the web, calling APIs, moving money, even performing penetration tests. Yet nobody is building the guardrails. Most teams deploying AI agents are just hoping they behave.

Why AgentGuard

AgentGuard is an open‑source runtime firewall for AI agents. It sits as a Go proxy between your agent and its tools, enforcing policies defined in YAML in real time.

Key features

  • Policy enforcement – block, hold for approval, or allow actions based on configurable rules.
  • Logging & audit – every request and decision is recorded with timestamps and reasoning.
  • Human‑in‑the‑loop – actions that require approval trigger Slack/webhook notifications.
  • Dashboard – live view of agent activity with one‑click approve/deny.
  • Adapters – ready‑made integrations for LangChain, CrewAI, browser‑use, and MCP.

Without AgentGuard

ScenarioOutcome
Agent runs rm -rf /Destructive command executes; you discover the damage later.
Agent calls production API without oversightNo chance to intervene; potential data breach or financial loss.
No audit trailDebugging relies on “it worked on my machine” and is unreliable.

With AgentGuard

ScenarioOutcome
Agent attempts destructive commandPolicy blocks the command before execution.
Agent calls production APIAction is paused; you receive a Slack/webhook notification to approve.
Need to investigateFull audit trail with timestamps, reasoning, and decisions is available.
DebuggingQuery any agent session from the audit logs.

How It Works

  1. Define policies in a YAML file, e.g.:

    # policy.yaml
    - name: disallow-deletion
      description: Prevent file deletions in workspace
      match:
        command: "rm *"
      action: block
    - name: require-approval-api
      description: Require human approval for production API calls
      match:
        api: "production"
      action: require_approval
  2. Run the proxy alongside your agent. The proxy intercepts all tool calls, evaluates them against the policies, and either allows, blocks, or queues them for approval.

  3. Monitor via dashboard – see live activity, approve or deny pending actions, and review audit logs.

Adoption

In the first five days, AgentGuard was cloned by 165 unique developers, highlighting the community’s need for such a solution.

  • Only 14.4 % of organizations send AI agents to production with full security approval.
  • 88 % reported confirmed or suspected AI‑agent security incidents last year.

Conclusion

Hope is not a security strategy. AgentGuard provides a concrete enforcement layer—similar to firewalls for networks or WAFs for web apps—so you can define boundaries once, enforce them automatically, and involve humans only when decisions are genuinely ambiguous.

View on GitHub

0 views
Back to Blog

Related posts

Read more »