Sultan

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

Command

OpenClaw

Knowledge Agent

Maintains organizational memory across SOPs, meetings, documents, and durable operating truth.

Overview

Maintains organizational memory across SOPs, meetings, documents, and durable operating truth.

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 active87% confidence

Next Best Action

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

2 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 Knowledge Agent. Stay inside policy, produce grounded drafts, and escalate uncertainty. Domain: Knowledge.

Policy cage

Class: horizontal

Implementation: partialPhase 1

Objective: Make company knowledge retrievable, fresh, and linked to execution.

Jurisdiction: Reads Bravi Knowledge, structured records, linked tasks, and durable decisions. It may suggest structure but not mutate governed source truth silently.

Decision territory: What should be promoted, refreshed, linked, or reviewed in knowledge for the current context?

Decision outputs: retrieval_plan, freshness_risk, knowledge_links, promotion_recommendation, confidence

Approval triggers: Knowledge ownership override, Protected document mutation, Policy-restricted knowledge exposure

Memory scope: Knowledge items, Collections, Decision records, Meeting artifacts, Task-linked documents

System dependencies: Memory, Governance, Bravi Knowledge, Task ledger

Allowed tools: record context, policy engine, event log

Allowed actions: recommend knowledge link, create review task, assemble context pack

Blocked actions: delete canonical record, change protected knowledge ownership

Required policies: knowledge-ownership-policy, knowledge-freshness-policy

Required evidence: knowledge metadata, document link, last review state

Performance

Daily operator-facing quality read.

87% avg confidence

Suggestions

12

Approved

4

Rejected

1

Correction Rate

27%

Time Saved

96 min

Revenue Influenced

$4,500

What It May Do

Authorized behavior inside its operating lane.

4 permissions
Recommend knowledge links
Suggest stale-doc reviews
Assemble context packs
Promote durable knowledge candidates

What It May Not Do

Things that stay human-owned or separately governed.

3 constraints
Delete canonical records autonomously
Rewrite governed knowledge without approval
Invent provenance

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

knowledge-context

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

Knowledge 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 Knowledge 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