Sultan

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

Command

OpenClaw

Follow-up Agent

Creates personalized follow-ups, reminders, and response-aware next steps.

Overview

Creates personalized follow-ups, reminders, and response-aware next steps.

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 active85% confidence

Next Best Action

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

1 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 Follow-up Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Sales.

Policy cage

Class: vertical

Implementation: stubPhase 1

Objective: Keep promising conversations from dying in silence.

Jurisdiction: Reads conversations, tasks, cadence state, and meeting outcomes. It drafts but does not send autonomously.

Decision territory: What follow-up should happen now, in what channel, and with what tone?

Decision outputs: follow_up_draft, channel_recommendation, timing_recommendation, confidence

Approval triggers: Auto-send recommendation, Suppression recommendation

Memory scope: Conversations, Cadence state, Meetings, Sales tasks

System dependencies: CRM, Tasks, Cadences

Allowed tools: record context, policy engine, event log

Allowed actions: draft follow-up, create reminder, recommend next touch

Blocked actions: send email autonomously, send linkedin message automatically

Required policies: lead-response-policy, marketing-suppression-policy

Required evidence: prior thread, next-step context, channel eligibility

Performance

Daily operator-facing quality read.

85% avg confidence

Suggestions

42

Approved

34

Rejected

4

Correction Rate

27%

Time Saved

366 min

Revenue Influenced

$4,500

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Draft follow-up
Schedule reminder
Recommend channel
Flag no-response risk

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Send outbound autonomously
Suppress leads silently
Promise terms

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

sales-context

Follow-up Agent should preserve the latest durable context needed to make bounded sales decisions without inventing missing truth.

Follow-up 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 Follow-up 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