Using Eric

This page covers the user-facing Eric workspace at /eric.

Starting a conversation

You can open Eric from:

The message icon in the app header
The Eric item in the main navigation
A direct link to /eric

If your company has exhausted its usable AI Credits, Eric shows a blocked state until an admin adds more capacity. See Assistant Settings for credit details.

Conversation list and session behavior

Eric stores work in conversations.

What the session list does

Shows saved conversations in reverse-updated order
Lets you start a New conversation
Lets you rename a conversation
Automatically generates a title after the first exchange if you do not name the session yourself
Prevents deleting a conversation while it still has an active run
Shows a running indicator when Eric is still working in another session

Back behavior

The Back button returns you to the last non-Eric page you came from. If you opened Eric directly, Back falls back to Dashboards.

Session context

When a conversation is tied to dashboard or report work, Main Eric Chat shows a Session context rail on the right with Linked dashboards and Linked reports for the active session.

Linked dashboards appear when you start In-Dashboard Eric on a dashboard, when Eric creates or updates a dashboard through a Definition File write during the conversation, or when you open an In-Dashboard Eric session in Main Eric Chat.

Linked reports appear when you start In-Report Eric on a Report Blueprint, when Eric creates or updates a report through a Definition File write during the conversation, or when you open an In-Report Eric session in Main Eric Chat.

Use Open on a linked dashboard or report to return to that workspace. Each list grows as the session touches more dashboards or reports.

Sending messages

Press Enter to send
Press Shift+Enter to insert a new line
Click the paper-plane button to send

If Eric is already responding and you send another prompt in the same conversation, the next prompt waits behind the active run instead of interrupting it.

While Eric is working

During a run, the send button changes into a Stop control.

You can:

Watch streaming status updates and tool activity
Cancel the active run with Stop
Re-attach to a still-running response if the stream was interrupted and Eric offers a Re-attach button

Desktop notifications when you step away

If a response takes a while, Eric can send a desktop notification when he finishes and you are not looking at that tab.

This applies when you open Eric in the main chat workspace, on a dashboard, or in a query editor.

Turning notifications on

The first time you open Eric (and your browser has not decided yet), you may see a dialog titled Can I ping you when I’m done?

Choose Yes to continue to your browser’s notification prompt.
Choose Allow in the browser prompt to turn notifications on.
Choose No on Eric’s dialog if you prefer not to. Eric waits about 30 days before asking again.
If you block notifications in the browser, Eric will not ask again.

If notifications are already allowed, the dialog does not appear.

When you get a notification

You get a notification only when all of these are true:

Browser notifications are allowed
Eric finished a response
You were away from that tab (the tab was hidden, or another window had focus)

The notification uses the assistant’s name as the title and says Finished responding. It stays up for about 7 seconds, or closes sooner if you click it. Clicking it brings the app window back into focus.

If you stay focused on the Eric tab while he finishes, you do not get a notification.

There is no separate in-app setting for this. Use Eric’s Yes/No dialog and your browser’s site notification controls.

Reading Eric’s responses

Eric responses can include several UI elements:

UI element	What it means
Tool call cards	Expandable cards for each tool Eric ran, showing arguments, results, and status
Final answer cards	Structured answer blocks, including text and tabular outputs
Widget draft artifact cards	Quick links to open a drafted widget in the preview canvas
Knowledge Proposal notices	References to proposed Company Knowledge changes that approvers can review
Copy button	Copies the assistant message content
Helpful / Not helpful	Sends feedback tied to that assistant run

Tool call cards

Each tool Eric runs appears as a card in the response. You can expand any card to see:

The tool name and status — pending, completed, or error
Arguments Eric passed to the tool
Results, including dataset matches, SQL queries, row counts, and runtime warnings
How long the tool took

Common tools you will see:

Finding useful datasets — searches your accessible datasets and returns top matches with confidence scores
Working with datasets — runs a SQL query against your workspace data and shows returned rows, columns, and datasets used
Reading and updating Knowledge Files — inspects the Knowledge Filesystem and updates writable Markdown files
Creating widget draft — builds a widget draft and returns layer counts, publish readiness, and a link to the canvas

If a tool fails, the card shows the error and any repair hint. You can copy the error or continue the conversation to have Eric retry.

When Eric creates or updates a widget draft, a card appears in the chat thread. Click View in canvas to open the draft preview and publishing options.

Filter Variables in chat

Eric can create and update company Filter Variables when you have Dynamic Filter Variables permission—the same permission required to manage them in Settings. When you are building dashboards or Query Widgets, ask for a dropdown, fixed option list, or search control; Eric can add the variable and bind it into Query Widgets through Query Parameters so the filter bar and widget SQL stay aligned.

Eric authors Dynamic (from a synced Dataset or saved Query Dataset), String, Number, and Search variables. Dynamic Date Range, Between Dates, boolean and date pickers, and options sourced from Modified Datasets still require the dashboard Filter Variables editor. Eric-created variables are the same company controls as ones you create in Settings.

Tier limits and dataset access match the product UI: Eric cannot exceed what you could create yourself, and Query Dataset-backed variables still require Query Source Access to that Query Dataset. For how Filter Variables work on dashboards, see Filter Variables.

Knowledge Proposals

Eric can write proposed company-wide knowledge updates into the Knowledge Filesystem. Users with Company Knowledge Update Permission review those proposals in the Company Knowledge workspace, compare the proposed Markdown against the current file, and approve or reject the change.

Eric can update writable personal, scratch, and permitted Dataset knowledge directly while working. Public company-wide writes require the proposal workflow.

Knowledge in chat and workspace

Eric starts each run with a compact Knowledge Filesystem bootstrap. He can read visible Knowledge Files with exec_command and update writable Knowledge Files with apply_patch before responding.

You can inspect and maintain knowledge in the Company Knowledge workspace:

Area	Who can edit it	How Eric changes it in chat
Personal Knowledge Directory	The signed-in user	Eric may update it directly when useful
Dataset Knowledge	Users with the required Dataset access and contribution permission	Eric may update it directly when permissions allow
Company Knowledge	Users with Company Knowledge Update Permission	Eric creates a proposal for approver review

The workspace’s Map and Files views show these areas together according to your permissions. Files also exposes visible generated Markdown and live YAML Definition Files. Definition Files are read-only in Company Knowledge; use the provided action to open the Dashboard or Query Definition Workspace that owns one.

Credit limits

Eric uses the Company’s Weekly AI Credit Allowance first. If that weekly allowance is exhausted and the Company has usable One-Off AI Credits, Main Eric Chat automatically uses those overflow credits without requiring additional user action. Admins can see this Overflow Credit Use in AI Assistant settings.

If the Company has no usable Weekly AI Credit Allowance or One-Off AI Credits, Eric shows an exhausted-state message and will not start new Main Eric Chat runs until more usable AI Credits are available. Non-admin Users are told to ask an admin for more AI Credits. Admins can buy One-Off AI Credits or manage an AI Add-On from Settings → AI Assistant → Billing & Credits or Settings → Billing. In a white-label deployment, contact your partner’s account manager to manage AI capacity.

Weekly AI Credit Allowance resets weekly. One-Off AI Credits are separate purchased credits that roll over across weekly periods and expire one year after purchase.

User Weekly Caps

When an admin sets a User Weekly Cap for you, new Main Eric Chat runs need both usable company AI Credits and remaining cap headroom. The cap limits your share of the shared pool for the current week; it is not a separate credit balance. If you hit the cap while the company still has credits, Eric blocks new messages for you until the weekly reset or an admin changes the cap. You are not prompted to buy AI Credits for cap exhaustion. If the company is out of AI Credits and your cap is also exhausted, the company exhausted message takes precedence. See Assistant Settings for how admins manage caps.

Chat settings and credit state

The Eric chat sidebar includes a settings entry point that shows the company’s current AI credit state. Anyone with Main Eric Chat access can open it.

A compact usage ring near that entry shows whichever limit is closer to empty: company AI Credits or your User Weekly Cap when you have one.

What non-admins see

A read-only Usage Summary with team activity, a leaderboard, and current weekly allowance usage
AI Credit Availability, including remaining One-Off AI Credits and the next weekly reset time
The usage ring described above, including your own User Weekly Cap when one is set
A low-credit warning when company credits or your User Weekly Cap drop to 5% or less of the relevant allowance

What admins see

Admins see all of the above, plus purchase and add-on management actions and User Weekly Cap controls on the Usage leaderboard.

Low credits and exhausted states

Low AI Credits Warning — appears when usable company credits are above zero but no more than 5% of the current Weekly AI Credit Allowance. You can still send messages; the warning is advisory.
Low User Weekly Cap Warning — same pattern when you have a cap and remaining headroom is above zero but no more than 5% of that cap.
AI Credits Exhausted — blocks new message submissions. Non-admins see a prompt to ask an admin for more credits. Admins see purchase actions.
User Weekly Cap Exhausted — blocks new message submissions for that user only. Non-admins are told to ask an admin about the cap; admins are pointed to Usage Summary to raise or clear it.
Admitted run protection — if you send a message while credits or cap headroom are still available and either limit runs out before Eric finishes, that run is allowed to complete. This does not create credit debt or reduce a future week’s allowance or User Weekly Cap.

Trust and data boundaries

Eric’s chat UI includes a trust strip with three important reminders:

Resplendent does not train on your data
Third-party AI providers are used with zero retention
Eric can only use datasets you are already allowed to access

That last point matters most operationally: if you cannot reach a dataset in Resplendent, Eric cannot use it either.

Feedback and iteration

Use the feedback buttons on assistant messages to tell Eric whether a response was helpful.

This is best when:

The answer was clearly correct or clearly wrong
A tool failed
The response was too slow
The answer was unclear

Admins can go deeper than feedback by opening the Run Inspector and Trace Viewer.