Outbound Firewall for AI Agents

The outbound firewall
for AI agents.

Check every AI-generated email before it sends. Protect sender reputation, prevent risky outreach, and enforce outbound policy.

Get Started →View API Docs
POST /v1/preflight/email

{
  "workspace_id": "ws_demo",
  "agent_id": "sdr-agent-01",
  "policy": "balanced",
  "to": { "email": "cfo@hospital.com", "industry": "healthcare" },
  "message": { "subject": "Quick question" },
  "decision": "requires_approval",
  "risk_score": 86,
  "approval": {
    "queue": "sales_manager",
    "reason": "Pricing claims require approval"
  }
}

Every AI email, checked before it sends.

SendGuard sits between your AI agents and your recipients — catching risky sends before they damage your reputation.

Protect Sender Reputation

AI agents can send hundreds of emails a day. One bad batch can burn your domain for months. SendGuard catches risky sends before they leave your server.

Agent-Aware Decisions

Track behavior per agent. New agents start restricted and earn trust over time. Rogue agents get flagged automatically before they cause damage.

Outbound Policy Engine

Define rules per industry, intent, or recipient type. Healthcare, finance, recruiting — each gets its own policy. Enforce compliance without manual review.

Human Approval Workflow

High-risk sends trigger approval requests before delivery. Sales managers approve or reject in one click. Full audit trail for every decision.

Cross-Platform Coverage

Route outbound through one API from Apollo, Instantly, HubSpot, Salesforce, Gmail, or your own agents. No provider lock-in, no platform-specific policy engine.

Explainable Risk Scores

Every decision includes a risk score (0–100), severity-rated reason codes, and human-readable explanations. No black boxes, no surprises.

One API call. Full protection.

Drop SendGuard into any outbound flow in minutes.

01

Call /v1/preflight/email

Pass workspace, sender, recipient, message, and policy context.

02

Get a decision

allow, block, delay, or requires_approval — with risk score and reason codes.

03

Act on it

Send, hold for approval, or drop. Full audit log written automatically.

Simple, Transparent Pricing

Pay only for what you use. Start with the Entry plan, scale as you grow.

Entry
$29
10,000 included / month
  • Email validation API
  • Preflight risk scoring
  • Provider-aware SMTP strategy
  • 300 req/min rate limit
Choose Entry
Growth
$199
150,000 included / month
  • Everything in Starter
  • Webhook callbacks
  • Agent controls
  • 3,000 req/min rate limit
Choose Growth

See full pricing details → • Included quota is consumed first, then top-ups cover overage.

Latest from the blog

Operating notes for AI outbound teams

Practical guidance on sender reputation, policy controls, and approval workflows for autonomous email systems.

ProductMay 6, 20262 min read

Why AI outbound needs a preflight firewall

Traditional deliverability checks are not enough once AI agents can autonomously send cold email at machine speed.

AI outboundsender reputationemail safety
Read article →
EngineeringMay 3, 20262 min read

Agent-aware policy is the next control plane for outbound email

The same message should not be treated equally when it comes from a new autonomous agent versus a trusted production workflow.

agent policytrust systemsoutbound controls
Read article →
OperationsApr 28, 20262 min read

From risk score to operator action

A risk score only becomes useful when it maps cleanly to operational actions like allow, delay, approval, or block.

risk scoringapprovalsoutbound operations
Read article →
Read all articles

Stop AI agents from burning your domain.

Start with 10,000 included checks per month. Add top-ups only when you need them.

Get Started →