Employee Smart Assistant

Tenants

Create and manage workspaces. Suspend, resume, force sign-out, or sign in as a tenant's user for support.

Refresh

Create tenant

Slug

Display name

Plan Free Starter Professional Enterprise Dedicated GPU Server

Status Active Trialing

Create tenant

Lowercase letters, digits, and dashes. Becomes the schema name.

No tenants yet.

Create a workspace above to provision an isolated tenant.

Name	Slug	Status	Plan	Subscription	Users	Created	Actions

Platform billing

Cross-tenant commercial operations. Assign plans per workspace on Tenants.

Billing is not enabled on this deployment.

Reconcile Stripe subscriptions Public pricing page Manage tenant plans

Plans & trials

Configure subscription tiers, feature bundles, limits, and free-trial defaults.

Billing is not enabled on this deployment.

Platform policy

Enable commercial billing and configure the provider and marketing defaults.

Enable commercial billing Turn on paid subscriptions across the platform. When off, every workspace runs without billing.

Billing provider Manual (superadmin assigns plans) Stripe (self-serve checkout) Moyasar (KSA - Mada, cards)

Sales contact email

Market region GCC (SAR)

Auto-suspend tenants when their subscription ends When a manually-assigned plan reaches its end date, the workspace is suspended automatically.

Warn before expiry (days)

Days before the end date at which the in-app banner and email warnings begin.

Grace period after expiry (days)

Applies to manually-assigned plans. During grace the workspace is read-only; after grace it is fully suspended. 0 = suspend on the first daily check after the end date. Stripe/Moyasar plans renew automatically.

Email the billing contact before expiry Sends warning emails as a manual subscription approaches its end date, on entering the grace period, and on suspension.

Additional notice recipients

Comma-separated. The sales contact email above is always included.

Save platform policy

Free trial defaults

Applied when a workspace is set to Trialing without explicit dates.

Default trial length (days)

Default start date

Default end date

Use days only Save trial defaults

Plan catalog

Set features and limits for each plan. Changes apply to the active catalog version.

Setting	Enabled / value

Save plan

Platform Security

CORS allowed origins, CSRF protection, and HTTP security headers for the whole deployment.

Origin changes apply immediately. Toggle changes apply on the next request.

Allowed browser origins (CORS + CSRF)

Comma- or newline-separated. Include scheme and port, e.g. https://app.example.com.

Protections

Enable HTTP security headers Sends X-Content-Type-Options, X-Frame-Options, Referrer-Policy and related hardening headers on every response. Enable CSRF origin checks on mutating API requests Rejects state-changing requests whose Origin header isn't in the allowed list above.

Enable HSTS (HTTPS only) Instructs browsers to only connect over HTTPS. Enable only once TLS is fully configured.

HSTS max-age (seconds)

Content-Security-Policy override (optional)

Advanced. Leave empty to use the built-in SPA policy — a malformed value can break the app UI.

Save security settings

Super Admins

Platform superadmins can manage every workspace. Grant this only to trusted operators.

Refresh

Add a super admin

Create a brand-new platform operator account.

Username

Display name

Password

Create super admin

Promote an existing account

Grant super admin to a current workspace user.

Account

Grant super admin

Current super admins

Operations Dashboard

Central visibility for system health, user activity, and governance alerts.

Refresh

Active Users

0

Avg Latency / Err Rate

0.0 / 0.0%

KB Indexed Chunks

0

Active Connectors

0 / 0

Governance Panel Alerts

Stale connectors, quota issues, and other governance signals.

Delivery settings 0 alerts

No alerts found. System healthy.

Governance issues such as disabled MCP connectors will show up here.

Time (UTC)	Alert Type	Severity	Message

Users Management

Manage accounts, roles, company access, and token limits.

Refresh + Add User

Import from ERP Reset Password Rate Limiting Disable all Enable all

All user types Admin User All statuses Enabled Disabled

No users found.

Add a user or import from ERP to get started.

No users found.

User Usage Tracking

Per-user Personal Assistant queries and token usage.

Refresh

Users 0

Queries 0

Tokens 0

All time 30d 7d 24h

No usage data.

Usage appears after users chat with the Personal Assistant.

User	Queries	Tokens	Lifetime / Limit

Billing & plan

Workspace subscription, usage meters, and upgrade options.

Choose plan Download usage (CSV) Refresh

Payment is past due. Update your billing details to restore chat access.

Current plan

—

—

Monthly Annual

Upgrade to Pro Manage subscription Resume subscription Cancel subscription

Usage this period

Included features

Audit Log

Permission, domain, company, account, and password changes (newest first).

Refresh

No audit entries yet.

Admin changes to users, permissions, and accounts are recorded here.

Time (UTC)	Actor	Action	Target	Details

Knowledge Base

Add trusted documentation so the assistant can answer policy and process questions with reliable references.

Embedding settings

Use it for: system user guides, finance and admin policies, SOPs, and other business knowledge not stored in ERP.

Example questions: "How do I generate a sales report?" or "Am I allowed to approve this request?"

Upload & Index Document

PDF, Word, TXT, Markdown, CSV, Excel

Choose file

Upload & Index

Tip: use clear document titles and tags to improve retrieval quality.

Company

All companies

Tags

Language Any English Arabic

Indexed Documents

Review what is searchable by the assistant.

Refresh

No documents yet

Upload policies, SOPs, or user guides so the assistant can cite them when users ask process or policy questions.

PDF & Word Tag by topic Cited in answers

Upload your first document

Observability Metrics

Monitor request volume, response speed, token usage, and recent failures.

Refresh

Total Requests (7d)

0

Avg Latency (ms)

0.0

Error Rate

0.0%

Tokens Used

0

Recent Errors

Latest failed requests from the last 7 days.

0 events

No recent errors.

When requests fail, they appear here with status and latency.

Time (UTC)	Request ID	Endpoint	Status Code	Latency (ms)

Appearance

Choose the color scheme for the interface.

Theme

Language

Set the display language for the interface.

EN عربي

Theme Customization

Adjust primary and neutral tones and base font size. Changes apply immediately; they are stored in the browser like the light/dark preference.

Primary color

Choose the primary action color used for buttons, links, and active states.

Hex Reset

Neutral color

Tints secondary text and muted UI; blends with your main text color for readable contrast.

Neutral color Hex Reset

Font size

Base size for the interface and chat messages.

A A Standard Reset

Welcome to Employee Smart Assistant. One sentence is enough—just state your goal.

Font Color

Override the default text color. Resets when you switch theme.

Custom Text Color

Applied on top of the selected theme.

Reset to Default

Branding

Company identity on sign-in and the assistant avatar in chat.

Project Personalization

Customize the appearance of the application.

Company Name

Company name color

Theme default

Uses the sign-in and chat header title. Leave as theme default or pick a custom color.

Login page logo

Shown on the sign-in page inside a fixed-size badge. Use a URL or upload an image (PNG, JPEG, GIF, or WebP, max 2 MB).

No logo

Choose file No file chosen

Allowed: PNG, JPG, JPEG, GIF, WebP. Max file size: 2 MB.

Chat Agent Avatar

Customize the assistant avatar in chat messages.

ES

Avatar type

2-character text Logo URL

Use text for initials (max 2) or switch to logo mode and provide an image URL.

Code Highlight Theme

Select the syntax highlight palette used in chat markdown and artifact source previews.

Theme Lobe Theme Andromeeda Aurora X Ayu Dark Ayu Light Ayu Mirage Catppuccin Frappe Catppuccin Latte Catppuccin Macchiato Catppuccin Mocha Dark Plus Dracula Theme Dracula Theme Soft Everforest Dark Reset

const person = { name: "Alice", age: 30 };
type PersonType = typeof person; // { name: string; age: number }
type Animal = { name: string };
const dog = { name: "Buddy", breed: "Golden Retriever" } satisfies Animal;

Review your changes before saving.

You have unsaved changes.

Discard Changes Save Settings

System Settings

Global defaults for AI assistants, voice, image generation, email delivery, and rate limiting.

AI & assistants

Personal Assistant Settings

Configure the general-purpose Personal Assistant mode.

Enable Personal Assistant

Default Model

Select model…

Cloud

Local

Usage Limit per User

ERP Data Settings

Set the default model used for ERP data queries. Users with model selection permission can override this.

Default ERP Model

Select model…

Cloud

Local

Email assistant

Default model for Outlook Summarize + reply (including regenerate). Leave unset to use the Personal Assistant default model.

Default email model

Use Personal Assistant default

Use Personal Assistant default

Cloud

Local

Presentation Layer v2 (Preview)

Switch the chat UI to the new block-based message renderer. Users can override in the browser with ?v2=1 or ?legacy=1.

Use block renderer by default for all users

Assistant features

Voice (STT & Read Aloud)

Routes microphone and read-aloud through the Private LLM gateway. When off, the browser native APIs are used.

Enable provider-backed speech-to-text

STT model

Enable provider-backed text-to-speech (Read aloud)

TTS model tts-1 (faster) tts-1-hd (higher quality)

TTS voice

Image Generation

Personal Assistant image generation (OpenAI or Stability) and optional Stability edit tools.

Enable image generation

Default provider OpenAI Images Stability AI

Monthly limit per user

OpenAI model gpt-image-1 dall-e-3

Stability generate model stable-image-core stable-image-ultra

OpenAI default size 1024×1024 1792×1024 1024×1792

OpenAI default quality auto low medium high standard (dall-e-3) hd (dall-e-3)

Stability API key

Required for Stability provider and manipulation tools.

Enable Stability manipulation tools (upscale, background removal, outpaint, search/replace)

Content-safety filter on prompts (recommended)

Code Interpreter

Sandboxed Python execution (run_python) — computations beyond SQL, with saved analytics and attachments as data in, chart/CSV artifacts out. The default subprocess runner is NOT a hardened multi-tenant boundary — the docker runner is required for shared or untrusted tenants.

Enable code interpreter (the per-user permission still applies)

Execution timeout (seconds)

Max stdout/stderr (KB)

Max output files per run

Sandbox posture (superadmin only — decides the isolation boundary on this host):

Runner subprocess (trusted single-tenant only) docker (hardened, required for shared tenants)

Memory limit (MB)

Docker image

Docker CPUs

Platform

Dashboard Platform (Super Admin)

Bounds, gates and retention for code-driven dashboards. Changes apply immediately and are restricted to super admins.

Freshness window (sec)

Max sources / dashboard

Max fetch steps / source

Sample row cap

Result size cap (MB)

Cache retention (days)

Cleanup cron

Enable LLM assembly (makes real model calls on cache miss) Enable sandboxed TSX runtime (requires completed security review)

SMTP Email Settings

Configure outbound email for scheduled report delivery.

SMTP Host

SMTP Port

SMTP Username

SMTP Password

From Address

Use STARTTLS

Rate Limiting

Limits apply per signed-in user, or per client IP for login and anonymous traffic.

Enable rate limiting

Category Per minute Burst

Chat

Chat per minute

Chat burst

Upload

Upload per minute

Upload burst

Admin

Admin per minute

Admin burst

Login per IP

Login per minute

Login burst

Looking for a setting?

These settings now live next to the features they configure.

API Keys Models Outlook Integration (Microsoft 365) Channels Messaging Channels Channels Knowledge Base Embeddings Knowledge Base Governance Alert Delivery Dashboard Tool Approvals Tool Approvals

Review your changes before saving.

You have unsaved changes.

Discard Changes Save Settings

Tool Approvals

Human approval gate for side-effecting assistant tools — per-tool policies, monetary thresholds and rules. Decisions and replays live on the Policy Simulator page.

Tool Approvals

Human approval gate for side-effecting assistant tools. Destructive tools (ERP posts) require approval by default; per-tool overrides below can force approval on any tool or waive the default.

Enable the approval gate (recommended) Require a different approver (segregation of duties) — admins are notified on their bound channels; initiators can only cancel

Approval wait timeout (seconds)

Filter tools

Tool	Approval policy
Loading tools…

“Default” follows the tool’s own policy (destructive → require approval). Overrides apply on top; changes take effect on the next tool call. “Deny” blocks the tool outright and cannot be bypassed.

Advanced policies (monetary threshold & rules)

Monetary approval threshold (0 = off)

Calls at or above this amount require approval. Unverifiable amounts on configured tools also require approval (fail closed).

Amount paths (which argument carries the amount) Add

Rules (first match wins, top to bottom) Add

Tool accepts globs (bc_post_*). Leave the condition path empty for an unconditional rule. Numeric conditions fail closed when the value can’t be read.

Review your changes before saving.

You have unsaved changes.

Discard Changes Save Settings

Models

Manage which AI models are available across the platform.

0/0 enabled API Keys Refresh

Add a model

Choose a curated model from the catalog or register a custom endpoint.

From Catalog Custom Model

Search

Model

—

Add Model

Provider

OpenAI OpenAI Anthropic Gemini OpenRouter DeepSeek Kimi Private LLM Ollama

Display label

Model ID

Vision model Supports image inputs

API keys are configured per-provider in API Keys. This model will use the key registered for the selected provider.

Add Custom Model

Configured Models

Edit, enable/disable, or remove models registered in this workspace.

No models configured yet

Add one from the catalog or register a custom endpoint.

	Label	Provider	Model ID	Source	Tier	Max Tokens	Recommended	Actions	Enabled

AI Fallback

Automatic premium→free model fallback: provider health, routing policy, and switch history.

Reset circuits Refresh

Provider health

Fallback policy

Fallback history

Time	User	From	To	Reason	Switch (ms)	Error

Workflows

All durable workflow instances in this workspace: monitor, cancel stuck runs, and trigger recovery.

Run recovery sweep Refresh

Workspace health

Instance counts by status. Click a tile to filter the list below.

Instances

All statuses running waiting completed failed cancelled

Workflow	Owner	Status	Step	Updated	Detail	Actions

Integrations

Connect your ERP or business system to power AI responses with live data.

+ Add integration

Review agents

No integrations yet

Before chat can answer questions about orders, inventory, or customers, connect your ERP data source. Add an integration to enable ERP mode with live answers.

SQL database ERP OData API Schema mapping

Add your first integration

One-time setup · takes a few minutes

← Back

Add integration

Select system type

Select system

Deployment type

Description

ERP (on-prem)

SQL database, OData sign-in, and schema cache for your NST deployment.

Database

Check connectivity to the SQL Server used for ERP.

Server / Host

Port

Database Name

Username

Password

Show

BC base app GUID

Leave empty for BC14 / NAV — those databases name tables Company$Table with no GUID.

LS Central app GUID (only used when LS Central is installed)

LS Central module Auto-detect from the database Enabled Disabled

You have unsaved changes.

Discard Changes Save Settings Test the DB connection

ERP password sign-in (on‑prem NST)

Validates users against your ERP OData endpoint when local login fails.

Enable ERP password via OData

OData base URL

Verify TLS certificate

Test uses the credentials below. Click Save in this section to persist OData settings.

Test username

Test password

You have unsaved changes.

Discard Changes Save ERP sign-in settings Test ERP OData sign-in

AI Gateway (API)

Governed read/write operations via the BC gateway extension. SQL remains used for analytics.

Enable BC gateway API

Gateway base URL

Default company (chat queries use the company selected in the conversation)

Transport ODataV4 Custom API (/api/asg/ai/…)

Service account

Web service access key

Show

You have unsaved changes.

Discard Changes Save gateway settings Test gateway

Schema Cache

Clear cached schema for a specific company when table structures change.

Maintenance

Company

Refresh Schema

Cloud (SaaS) ERP

BC Cloud Standard — Microsoft REST/OData API with Azure AD OAuth2 (client credentials). Configure the app registration below.

BC Cloud Standard Included

Read-only access via Microsoft's API. The assistant uses query_erp_entity (customers, items, sales orders, GL, …). No SQL on cloud.

BC Cloud + AI Gateway Pack Coming soon

Optional pilot: publish the AI Gateway extension on your SaaS tenant (LS Central) for POS, net inventory, Count/Sum/Query, and governed writes. Requires extension install — not included in Standard.

See docs/design/bc-cloud-standard-vs-gateway-pack.md for OAuth setup, pilot checklist, and which operations need the extension vs the Standard API.

Environment

Company ID (optional)

Azure AD tenant ID

Client ID

Client secret

Show

API base URL

Save Settings Test the connection

Odoo

Connect to Odoo over its JSON-RPC API (read-only) using a database, user, and API key.

Odoo URL

Database

Company ID (optional)

Username

API key

Show

Save Settings Test the connection

Dynamics 365 Finance & Operations

Connect to F&O over its read-only OData data entities using an Azure AD app registration (client credentials).

Environment URL

Azure AD tenant ID

Default company / dataAreaId (optional)

Client ID

Client secret

Show

Save Settings Test the connection

← Back

Connection details

Edit connection Revoke

Agent Builder

Create named AI assistants with custom prompts, model overrides, and data restrictions.

Refresh + New Agent

New Agent

Define prompts, model, domains, skills, and KB scope for this assistant.

Name *

Description

System Prompt * ✨ Suggest prompt

Prepended to the standard ERP prompt. Leave mode-specific ERP SQL rules intact.

Model Override — User's choice —

Optional: force a specific model for this agent.

Data Domains

Sales Finance Inventory Purchasing Costing Operational

Unchecked = no restriction (all domains).

Skills

Pick which skills (built-in tools, MCP connectors, custom HTTP tools) this agent can use. Leave all unchecked to inherit the caller's role-level access.

KB scope (tags) ✨ Suggest scope

Comma-separated tags. KB retrieval restricts to documents whose tags match any of these. Leave empty to allow all KB docs.

Enabled (visible to users)

Save Agent Cancel

Available to install

Ready-made agents for your connected system. Installing adds them to your agents, disabled — you choose what to switch on.

Install all available

Your agents

No agents yet. Click "+ New Agent" to create one.

Specialized agents can restrict data domains, override the LLM, and scope knowledge-base retrieval.

Scheduled Reports

Automate recurring ERP queries and deliver results via email or webhook.

Refresh + New Report

New Report

Set what to run, when to run, and where to deliver.

Name *

Schedule (cron) *

Standard 5-field cron: min hour day month weekday

Weekly Monthly Weekdays

Query / Question *

Company *

Model *

Delivery

Email Webhook

Recipients (comma-separated emails)

Webhook URL

Enabled

Enabled reports run automatically on their schedule.

Save Report Preview (dry run) Cancel

Dry-run preview

Close

Query executed; nothing was delivered.

No reports yet. Click "+ New Report" to create one.

Schedule BI queries to run automatically and deliver results by email or webhook.

Run History

Close

Skill Store

Browse every skill the platform exposes — built-in tools, MCP connectors, and custom HTTP tools — and configure per-agent access.

All Built-in MCP Custom Community

No skills match the current filter.

Tools

Browse all tools available to the AI — built-in, MCP, and custom HTTP.

Refresh + New Tool

All Built-in MCP Custom

New Custom Tool

Register an HTTP endpoint the AI can call with typed parameters and optional auth.

Tool name *

HTTP method GET POST PUT DELETE

Description *

Endpoint URL *

Auth credential (optional)

Plain header Secret store

Set secret…

Output path (dot-notation, e.g. data.result)

Parameters + Add

Enabled

Save Tool Cancel

No tools match the current filter.

Use "+ New Tool" to add a custom HTTP endpoint, or open MCP Connectors to manage integrations.

MCP Connectors

Connect external MCP servers to expose their tools to the AI.

+ New Connector

New MCP Connector

Point the agent at an MCP server endpoint and control who can use its tools.

Connection

Connector name *

Transport SSE (Server-Sent Events) Streamable HTTP

Description

Server URL *

HTTP or SSE endpoint URL. Use the transport that matches your MCP server.

Authorization header (optional)

Access

Allowed roles

Admin User

Required permission (optional extra gate) — None — personal_assistant chat user_admin

Enabled When off, tools from this connector are hidden from the agent.

Save Cancel

No MCP connectors yet. Click "+ New Connector" to add one.

Add SSE or HTTP endpoints, or use built-in system connectors like Outlook and Telegram.

Channels

Link Telegram (and soon WhatsApp / Teams) so you can chat with the assistant from those platforms.

Inbound bot webhooks for Telegram, WhatsApp, and Teams. Users link their account once via /bind, then chat with the assistant from the platform.

Refresh all

Linked accounts

Refresh

No channels linked yet.

Link Telegram

1. Open Telegram and message your organization's bot.
2. Send /bind — the bot replies with a 6-character code.
3. Paste the code below and click Link.

Link

Telegram

Telegram bot

unknown

Talk to @BotFather on Telegram to create a bot, then paste the token and a strong webhook secret below. Telegram requires HTTPS for webhooks — use a tunnel (cloudflared / ngrok) in development.

Refresh

Setup checklist

1. 1
   Bot token —
3. 2
   Webhook secret —
5. 3
   Webhook URL —

Bot credentials

Bot token

Stored encrypted in the secret store. Leave blank to keep the existing value.

Webhook secret

Echoed by Telegram in X-Telegram-Bot-Api-Secret-Token. Anything random and ≥32 chars is fine.

Save secrets Generate secret

Webhook

Webhook URL (HTTPS)

Register Webhook info

Telegram POSTs every message to this URL. Must be reachable over HTTPS.

Default:

Microsoft Teams

Microsoft Teams bot

unknown

Register an Azure Bot, enable its Microsoft Teams channel, and point the messaging endpoint at /api/channels/teams/webhook. Paste the bot's app id and client secret below. Teams senders auto-link to users who connected Microsoft in their Outlook settings.

Refresh

Default messaging endpoint:

App ID

—

App secret

—

Graph (Outlook)

—

Bot credentials

Bot app id

Microsoft App (client) id of the Azure Bot registration. Leave blank to keep the existing value.

Client secret

Stored encrypted. Leave blank to keep the existing value.

Bot tenant id

Usually botframework.com for a multi-tenant bot.

Save secrets Download manifest

WhatsApp

WhatsApp

unknown

Pick a provider, then paste its credentials below. Twilio: point the "When a message comes in" webhook at /api/channels/whatsapp/webhook. Meta Cloud API: point the app's WhatsApp webhook at /api/channels/whatsapp/meta/webhook.

Refresh

Default webhook (selected provider):

Account SID

—

Token

—

Sender

—

Templates

—

Bot credentials

Provider Twilio Meta Cloud API (direct)

How this workspace sends and receives WhatsApp messages. Switching providers keeps saved credentials for both.

Account SID

From your Twilio console. Leave blank to keep the existing value.

Auth token

Stored encrypted. Also used to verify inbound webhook signatures.

WhatsApp sender

The WhatsApp-enabled Twilio number (sandbox or registered sender).

Access token

Permanent system-user access token from your Meta app. Stored encrypted.

Phone number ID

From WhatsApp → API Setup in the Meta app dashboard (not the display number).

App secret

Used to verify inbound webhook signatures (X-Hub-Signature-256). Stored encrypted.

Verify token

Must match the verify token you enter when registering the webhook in the Meta app.

Public URL (optional)

Set this if you're behind a reverse proxy so signature validation uses the public URL.

Save secrets

Proactive templates

Proactive templates

Pre-approved templates for messages sent outside WhatsApp's 24-hour window (e.g. the morning digest, which looks for one named morning_digest with a single body variable {{1}}).

No templates registered.

Name	Content SID	Lang	Description

Add template

Microsoft 365

Outlook mailboxes

unknown

Connect personal mailboxes for summarize and reply. Requires an Azure app registration with Graph scopes and the redirect URI below.

Refresh

Enabled

—

Client ID

—

Client secret

—

Azure app credentials

Enable Outlook integration

Tenant ID

Client ID

Client secret

Stored encrypted. Leave blank to keep the existing value.

Redirect URI

Default:  — add this exact URL as a "Web" redirect URI in your Azure App Registration.

Save Outlook settings Test OAuth sign-in

Opens Microsoft login after save. Requires the outlook permission on your account.

Routing & conversation behavior

Behavior of chats over Telegram, WhatsApp and Teams.

Auto mode: use the Connector model to classify ambiguous messages

Only runs on your Connector-mode model — messages are never sent to a third-party model for routing. When off, ambiguous messages stay in the previous mode (keyword routing still applies).

Conversation freshness window (hours)

After this many idle hours a channel chat starts a fresh conversation. 0 disables.

Save behavior

All linked accounts

Every channel ↔ user link across the system. Revoking forces the user to /bind again on the next inbound message.

Refresh

No channel bindings yet.

Users appear here after they complete /bind on Telegram, Teams, or WhatsApp.

Channel	ERP user	Display name	Channel id	Bound at

Auto-routing telemetry

How auto mode routed recent messages between PA and Connector. Message text is never recorded.

Reset Refresh

No routing decisions recorded yet.

Decisions appear here once users chat in auto mode (/mode auto).

When	Channel	ERP user	Route	Decided by

Tool Audit Log

Record of every tool execution — user, tool, duration, and outcome.

Refresh

No tool calls recorded yet.

Executions appear here when the assistant invokes tools during chat.

Time	User	Tool	Type	Args	ms	Result

Feedback & Issue Reports

Thumbs up/down ratings and user-submitted issue reports across assistant responses.

All time 30d 7d 24h

Refresh

Thumbs up

—

Thumbs down

—

Satisfaction

—

Rating reason tags

Issue reason tags

Recent issue reports

No feedback recorded yet.

Ratings and issue reports appear here once users respond in chat.

Time	User	Tags	Comment	Session

Company profile

How we are as a company — injected into every chat for all users. Set tenant defaults, then optional overrides per ERP legal entity.

Editing scope Tenant defaults (all companies) Override for ERP company ERP company

Suggest with AI Save profile

User Memories

Cross-user view of persistent memories the assistant carries into every chat turn. Filter by user or category, audit history, force-forget anything.

Refresh

Filter by user Category All categories Identity Preference Fact Instruction Include soft-deleted Apply filters

User	Category	Content	Source	Created	Status

No memories match your filters.

Try clearing filters or click a user card above to focus on one account.

Policy Simulator

Preview a user's effective permissions, data domains and company scope, and run "what-if" probes — nothing is persisted.

Run as: Refresh

Pick a user to start

Choose someone in Run as above — we’ll show their effective permissions and let you run safe “what‑if” checks.

Role —

Permissions granted —

Tools available —

Permissions

Green = granted (role default or override). Red = denied.

Filter Denied only

No permissions match this filter.

Data domains

Allowed companies

Tools the user would see

What‑if probes

Run safety gates without persisting changes.

Chat SQL Permission diff

What-if: chat request

Question

Company

Model type — none — claude openai gemini openrouter ollama (local) local_openai

With attachment Run

Approval decisions

Recent gated tool calls from the durable ledger. Replay re-evaluates a call under the CURRENT policy — nothing runs, nothing is persisted.

All statuses Pending Approved Denied Expired Refresh

Time	User	Tool	Status	Resolved by	Policy replay
No gated calls recorded yet.