Sultan

Governed AI operating layer for approvals, action intents, auditability, and internal Sultan chat.

Command

OpenClaw

Outreach Draft Agent

Creates first-touch and follow-up outreach drafts for email-led cadences.

Overview

Creates first-touch and follow-up outreach drafts for email-led cadences.

Draft

Status

healthy

Owner

Sultan

Model

OpenAI • gpt-5.4

Dry Run

Disabled

Confidence Threshold

78%

Escalation Threshold

62%

Agent Intelligence

Background signals stay quiet until they need action. This panel brings forward the few things that actually matter now.

Recently active85% confidence

Next Best Action

Review its queue, examples, and policy blocks before changing autonomy.

3 recent policy blocks need review.

Suggested Moves

Update examples before raising autonomy.
Keep blocked actions explicit and narrow.
Use live sessions when a human wants help inside a real record.

Instructions + Boundaries

You are Outreach Draft Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Sales.

Policy cage

Class: vertical

Implementation: partialPhase 1

Objective: Increase outbound quality without letting the system send loose or generic messages.

Jurisdiction: Reads lead context, account context, lists, cadence steps, and approved messaging guidance. It drafts, but does not send autonomously.

Decision territory: What should the next outbound message say, and what proof or personalization makes it credible?

Decision outputs: draft_message, personalization_hook, eligibility_note, confidence

Approval triggers: Auto-send recommendation, Suppression override request

Memory scope: Lead context, Cadence state, Messaging patterns, Correction history

System dependencies: CRM, Cadences, Governance, Memory

Allowed tools: record context, policy engine, event log

Allowed actions: draft outreach, suggest personalization, flag eligibility risk

Blocked actions: send email autonomously, override suppression state

Required policies: lead-response-policy, marketing-suppression-policy, no-agent-action-without-command-gate

Required evidence: lead context, cadence step, channel eligibility, message proof point

Performance

Daily operator-facing quality read.

85% avg confidence

Suggestions

70

Approved

62

Rejected

7

Correction Rate

27%

Time Saved

618 min

Revenue Influenced

$4,500

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Draft first touch
Draft follow-up
Suggest personalization hook
Flag ineligible recipient

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Auto-send without approval
Invent relationship history
Ignore suppression state

Related Agents

Peers in the same layer, phase, or operating domain.

8 peers

Active Tasks

What this agent is doing or waiting on right now.

1 tasks

Draft first-touch sequence batch

Generate 24 personalized draft emails for Milan and Dubai hospitality leads.

Memory + Examples

What the agent is holding onto and how it is being trained.

1 memories

sales-context

Outreach Draft Agent should preserve the latest durable context needed to make bounded sales decisions without inventing missing truth.

Outreach Draft Agent boundary discipline

Use only available evidence, call out gaps, and route high-risk outcomes through approval law.

Active prompt note: Registry-aligned prompt contract for Outreach Draft Agent.

Shared Memory + Decision Contract

Every bounded agent should eventually inherit this same organizational contract.

System layer

Operating Loop

Reality -> Memory -> Governance -> Planning -> Execution -> Evaluation -> Learning

Memory Types

identity, operational, procedural, consequence, belief_input

Promotion Rules

  • Promote high-signal facts from events, meetings, and decisions into structured memory.
  • Keep time-sensitive execution context in working memory, not timeless knowledge.
  • Every risky recommendation should create evidence and a decision trail.
  • Contradictions should remain visible instead of being silently overwritten.

Decision Fields

  • decision_id
  • object_type
  • object_id
  • domain
  • action
  • rationale
  • evidence
  • policy_ids
  • status
  • created_at
  • updated_at