Sultan

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

Command

OpenClaw

Advertising Agent

Monitors Meta, Google, and LinkedIn ads and suggests optimization moves.

Overview

Monitors Meta, Google, and LinkedIn ads and suggests optimization moves.

Suggest

Status

paused

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 active87% confidence

Next Best Action

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

1 recent policy blocks need review.
Error rate is 7%, which is high enough to justify tuning.

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 Advertising Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Marketing.

Policy cage

Class: vertical

Implementation: stubPhase 2

Objective: Make paid media performance legible and governable.

Jurisdiction: Reads paid metrics and campaign context. It never changes spend on its own.

Decision territory: Where is paid media underperforming or showing room to scale?

Decision outputs: optimization_recommendation, risk_flag, budget_note, confidence

Approval triggers: Budget change recommendation, Campaign shutdown recommendation

Memory scope: Paid metrics, Campaign history, Creative tests, Channel readiness

System dependencies: Memory, Governance, Ads connectors

Allowed tools: record context, policy engine, event log

Allowed actions: recommend budget shift, flag weak campaign, summarize attribution

Blocked actions: change ad spend, launch ad set

Required policies: campaign-launch-policy, paid-spend-policy

Required evidence: paid metrics, attribution context, campaign goal

Performance

Daily operator-facing quality read.

87% avg confidence

Suggestions

26

Approved

18

Rejected

2

Correction Rate

18%

Time Saved

222 min

Revenue Influenced

$12,000

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Flag weak campaigns
Suggest budget shift
Summarize ROAS/CAC patterns
Recommend creative test

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Change budget autonomously
Launch ad set autonomously
Override campaign approvals

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.

0 tasks

Memory + Examples

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

1 memories

marketing-context

Advertising Agent should preserve the latest durable context needed to make bounded marketing decisions without inventing missing truth.

Advertising 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 Advertising 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