> ## Documentation Index
> Fetch the complete documentation index at: https://livingcontext.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Workspace agent

> A conversational org-intelligence agent on Home that answers questions about your Salesforce org and docs — read-only, grounded, and always showing its work.

The workspace agent **is** Home: you land in a conversation, not a dashboard. Ask about your organization in plain language — "What changed in the org last week?", "Who can edit Opportunity Amount?", "Which fields on Case are never used?" — and it reasons over your synced Salesforce catalog and your documentation corpus, running tools in a loop until it has a grounded answer. Starter chips on the empty state (Field impact, Audit this org, Recent changes, Stale docs, Coverage gaps) give you one-click first questions.

Conversations are **persisted, private threads** — the thread list on the left groups them by day, you can leave and come back, and other members can't see your threads ("Private to you · org-scoped"). Each thread's menu offers **Rename**, **Capture as skill** (turn a good investigation into a reusable draft skill under Agents → Skills), and **Delete**.

In the composer: type **@** to mention a Salesforce object, field, or flow and pin it into context; type **/** to pick a playbook; attach screenshots or text files; dictate if your browser supports it; and pick the AI model for the chat from the models your org enabled in **Settings → Models**. **Enter** sends, **Shift+Enter** adds a line.

<Note>
  The workspace agent is **read-only**. It never modifies your Salesforce org or your docs. Its single write path is [Save as doc](#save-an-answer-as-a-doc), which goes through the normal change request review flow.
</Note>

<Warning>
  **Secrets are never echoed.** If your synced source or records contain credentials — API keys, tokens, passwords, client secrets — the agent reports *where* they live and flags them as a security risk, but never prints the full value in its answer or inside a code snippet. It treats your documentation as leads to verify, not proof: for questions about how your org is configured today, it confirms against your live org and metadata before asserting.
</Warning>

## What it can see

The agent chooses from some twenty read-only tools. As it works, tool activity streams live into the transcript — collapsed by default under a summary like "Thought & used 4 tools · 12s", expandable down to each tool's input and output — so you can see exactly what it looked at. A **Usage** chip under each answer breaks out the model, tokens, credits, and cost of that turn.

### Metadata and schema

| Tool                | What it does                                      |
| ------------------- | ------------------------------------------------- |
| `search_metadata`   | Find components in your synced Salesforce catalog |
| `get_metadata`      | Fetch full details for a specific component       |
| `get_object_schema` | Object shape — fields, types, relationships       |

### Source search

| Tool         | What it does                                                                          |
| ------------ | ------------------------------------------------------------------------------------- |
| `search_org` | Full-text search across your org's source (Apex, flows, and more), with regex support |

### Impact analysis

| Tool                | What it does                                   |
| ------------------- | ---------------------------------------------- |
| `find_usages`       | Where a component is referenced across the org |
| `list_dependencies` | What a component depends on                    |

### Change history

| Tool               | What it does                                 |
| ------------------ | -------------------------------------------- |
| `recent_changes`   | Components that changed recently             |
| `get_change_diffs` | Before/after diffs of changed components     |
| `git_history`      | Recent commits on your tracked repositories  |
| `audit_trail`      | Live Setup Audit Trail entries from your org |

### Security and access

| Tool                    | What it does                                     |
| ----------------------- | ------------------------------------------------ |
| `who_can`               | Who can see or edit a given object or field      |
| `security_health_check` | Live security health check results from your org |

### Field hygiene and org health

| Tool                       | What it does                                    |
| -------------------------- | ----------------------------------------------- |
| `find_unreferenced_fields` | Fields with no references anywhere in the org   |
| `field_utilization`        | Live population counts for fields — counts only |
| `get_org_score`            | A 0–100 org health score with trend             |

### Integrations and docs

| Tool                | What it does                                                                    |
| ------------------- | ------------------------------------------------------------------------------- |
| `list_integrations` | Inbound Apex REST endpoints and outbound Named Credentials, with vendor mapping |
| `search_docs`       | Full-text search across your documentation                                      |
| `read_doc`          | Read a specific doc                                                             |
| `get_coverage`      | Documentation coverage of your Salesforce components                            |
| `get_freshness`     | Which docs are stale relative to org changes                                    |

<Warning>
  Live tools (`audit_trail`, `security_health_check`, `field_utilization`) call Salesforce using your organization's connection. Field utilization returns **counts only** — the agent never reads record contents. See [Salesforce integration](/integrations/salesforce).
</Warning>

## Slash playbooks

Playbooks are pre-built investigations you launch with a slash command:

| Command      | What you get                                                         |
| ------------ | -------------------------------------------------------------------- |
| `/audit`     | A one-page snapshot of your org — health, changes, risks             |
| `/changes`   | A digest of recent org changes with diffs                            |
| `/stale`     | Docs that have drifted from the components they describe             |
| `/coverage`  | Where documentation coverage is thin                                 |
| `/readiness` | An Agentforce / AI readiness assessment of your org                  |
| `/classify`  | Heuristic PII/PHI classification of fields (names and metadata only) |

## Prompt commands

Shape how the agent responds within a thread:

| Command      | Effect                                      |
| ------------ | ------------------------------------------- |
| `/simplify`  | Re-explain the last answer in plainer terms |
| `/table`     | Reformat the last answer as a table         |
| `/technical` | Go deeper with technical detail             |
| `/recap`     | Summarize the thread so far                 |

## Charts and dashboards

Ask for a chart or a dashboard in plain language — "chart Opportunities won by month", "build a pipeline dashboard by stage and owner" — and the agent renders it **inline in the chat**, in your workspace theme. The charts it creates also appear in [Analytics](/guides/analytics), where you can open and filter them any time. Like everything else the agent does over your records, this is read-only — it never changes your Salesforce data.

<Note>
  Charts require an analytics source to be connected first — see [Turn analytics on](/guides/analytics#turn-analytics-on). Until then the agent will point you to Connections instead of rendering.
</Note>

## Save an answer as a doc

When the agent produces something worth keeping — an audit summary, an integration inventory, an architecture explanation — click **Save as doc**. The answer is captured as a [change request](/guides/editing-and-change-requests), filed under a topic folder inside `workspace-notes/` in your docs repo. Like everything else, it ships only after review.

<Tip>
  Run `/audit` weekly and save the result — you get a reviewed, timestamped history of your org's health in your own Git repository.
</Tip>