Last updated: 2026-05-19 · 4 min readBusiness〜

Agent Policy

Agent policy lets you manage, at the workspace level, how autonomously the AI agent can operate, which skills it can use, and whether it may use external web search.

Open the settings screen

  1. Open workspace settings
  2. Select "Agent Policy"
  3. Change the items you need and click "Save"

Only workspace administrators can change these settings.

Agent autonomy level

LevelNameBehavior
0Manual approval onlyEvery action requires human approval before it runs
1Auto-run low-riskOnly low-risk internal processes run automatically
2Auto-run medium-riskActions up to medium risk run automatically
3Fully autonomousAll actions run autonomously

For early rollout, we recommend level 0 or 1. Actions such as creating tasks, sending customer-facing messages, publishing materials, and updating stakeholders affect customers and Room content, so it's safer to start with an approval-based workflow.

Enabled skills

Choose which skills the AI agent can use. You can enable up to 20.

SkillRole
Deal progressionSuggests the next action based on phase, completion criteria, customer requests, and sales commitments
Signal detectionDetects changes in customer behavior and risks
Pull dialogueInterprets the user's question intent and switches between answering, analyzing, and suggesting
Stakeholder analysisOrganizes contacts, roles, influence, and unidentified people
Task plannerSuggests required tasks with priorities
Pipeline digestSummarizes key points and risks across multiple Rooms
Message plannerDrafts customer-facing messages
Content creationAssists with creating Pages, materials, meeting notes, and proposals

When the information in a Room alone isn't enough to answer or analyze, you can allow the AI agent to use external web search.

SettingDescription
Allow web searchLets the agent use external search when it determines it's needed
Monthly search limitSets the monthly search limit for the entire workspace

If the Brave Search API key is not configured, no searches run even when web search is allowed.

Agent rules

You can register up to 5 operational rules to factor into the agent's decisions.

Examples:

  • Always turn customer-facing messages into approval cards
  • For proposals involving contract terms, prioritize legal review tasks
  • Don't make definitive claims when speculating about pricing or discounts
  • When the decision-maker hasn't joined, prioritize stakeholder confirmation

Glossary

You can register up to 10 of your company's own terms and abbreviations. The agent references this glossary when generating answers, analyses, and the rationale behind its suggestions.

TermExample definition
ChampionAn internal advocate within the customer's organization who drives adoption
PoCThe validation phase before full deployment
RingiThe customer's internal approval process
ItemRecommended value
Autonomy levelLevel 0 or 1
Web searchOn only for workspaces that need it
Enabled skillsDeal progression, Pull dialogue, Task planner, Message planner
RulesCustomer-facing output requires approval; rationale visible to internal users only

The closer you get to full autonomy, the more convenient it becomes, but the impact of an erroneous action also grows. Start with an approval-based workflow for customer-facing messages, material publishing, contract terms, and CRM updates.

Agent Policy | Help center