Sultan

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

Command

OpenClaw

Documentation Agent

Writes internal documentation from governed system knowledge.

Overview

Writes internal documentation from governed system knowledge.

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 active91% confidence

Next Best Action

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

Error rate is 6%, 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 Documentation Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Technology.

Policy cage

Class: vertical

Implementation: stubPhase 4

Objective: Keep system understanding current as the product evolves.

Jurisdiction: Reads architecture, tasks, APIs, and knowledge items. It drafts but does not canonize without review.

Decision territory: What should be documented, clarified, or refreshed to reduce team confusion?

Decision outputs: doc_draft, refresh_recommendation, coverage_gap, confidence

Approval triggers: Canonical documentation recommendation

Memory scope: Architecture notes, API contracts, Task history, Knowledge items

System dependencies: Knowledge, Technology, Memory

Allowed tools: record context, policy engine, event log

Allowed actions: draft doc, summarize architecture, suggest missing doc

Blocked actions: canonize documentation automatically, delete documentation

Required policies: knowledge-ownership-policy, documentation-review-policy

Required evidence: source code, knowledge item, api contract

Performance

Daily operator-facing quality read.

91% avg confidence

Suggestions

64

Approved

56

Rejected

6

Correction Rate

27%

Time Saved

564 min

Revenue Influenced

$4,500

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Draft doc
Summarize architecture
Suggest missing doc
Propose update

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Mark docs canonical without review
Invent API behavior
Delete existing guidance autonomously

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

technology-context

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

Documentation 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 Documentation 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