Sultan

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

Command

OpenClaw

Support Agent

Answers questions and routes support issues safely into the right queue.

Overview

Answers questions and routes support issues safely into the right queue.

Draft

Status

dry_run

Owner

Sultan

Model

OpenAI • gpt-5.4

Dry Run

Enabled

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 active81% confidence

Next Best Action

Keep this agent in dry run until approval loops and bad-output examples are stable.

3 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 Support Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Customer Experience.

Policy cage

Class: vertical

Implementation: stubPhase 3

Objective: Respond faster without losing policy discipline.

Jurisdiction: Reads support inbox items, case history, and policy. It drafts and routes but does not autonomously close sensitive issues.

Decision territory: How should this issue be answered, classified, and escalated?

Decision outputs: response_draft, classification, escalation_recommendation, confidence

Approval triggers: Refund or credit recommendation, External promise involving money or delivery

Memory scope: Cases, Threads, Order context, Resolution history

System dependencies: CX, Governance, Memory

Allowed tools: record context, policy engine, event log

Allowed actions: draft answer, classify issue, suggest escalation

Blocked actions: issue refund autonomously, close high-risk case

Required policies: customer-issue-triage-policy, refund-approval-policy

Required evidence: case summary, order context, policy posture

Performance

Daily operator-facing quality read.

81% avg confidence

Suggestions

46

Approved

38

Rejected

4

Correction Rate

27%

Time Saved

402 min

Revenue Influenced

$4,500

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Draft answer
Classify issue
Suggest escalation
Summarize thread

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Issue refund autonomously
Close high-risk case
Promise unsupported resolution

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

customer-experience-context

Support Agent should preserve the latest durable context needed to make bounded customer experience decisions without inventing missing truth.

Support 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 Support 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