Skip to main content
Monitor your workspace from the Usage page in the left navigation. Its tabs give you different views:
  • Agent usage — What each agent delivers, how much it is used, and what it costs
  • Credit balance — The workspace’s credits: balance, burn rate, and where the credits went (workspace admins only)
  • Member adoption — How actively your workspace members are using Abundly (workspace and team admins)
  • User action log — Append-only log of workspace configuration and membership changes (audit trail; workspace admins only)
Anyone but a guest gets the Agent usage tab as soon as they have one agent, showing the agents they can use. Team admins additionally see every agent of the teams they administer, along with member adoption for those teams, and can manage limits for those agents. Workspace admins see every agent in the workspace, the credit balance, the user logs, and manage all limits.

Agent usage

The Agent usage tab is one table with a row per agent, answering the three questions an owner asks: what did the agent deliver, how much was it used, and what did it cost.
The Agent usage table grouped by team, showing each agent's criticality, key metrics with trends, triggers & chats and credits used
For each agent you see its criticality and value statement, its key metrics for the period with a trend for each, how many triggers and chat conversations it handled, and the credits it used. Trends compare with the period of equal length immediately before; the percentage is left out when the previous period is too small to compare fairly, or when the agent was created inside the period. Choose a period of the last 7, 30 or 90 days, and narrow the table by name, team, tag, criticality or whether the agent has key metrics; Owned by me keeps only the agents you own. When lifecycle phases are enabled the table shows production agents by default, so experiments do not swamp the review. Disabled agents are hidden by default and marked when shown; the Status filter switches between enabled, disabled and all agents. Personal agents are one entry in the Team filter and one group, with each row saying whose it is, and are left out by default; select them in the Team filter to include them. Active filters show as filled buttons, including the defaults; Reset to default returns to the default view. The totals above the table cover the agents shown and say how many of them were active, meaning they handled at least one trigger or chat in the period. Grouping by team adds a subtotal per team; click a team’s header to fold it down to its subtotal. Your view is kept in the page URL, so a filtered table can be bookmarked or sent to a colleague; which teams you have folded is remembered on this device instead. Export copies or downloads the visible rows as JSON, in the same shape as the Workspace API’s /workspaceapi/agent-usage endpoint, together with the period and filters that produced them. That is the format to hand to an agent or paste into a chat. Restricted and personal agents, whose default access is Nothing, are listed for the admins who oversee them, so no spending goes unaccounted for, but their row is figures only: the agent’s name is not a link and its key metrics do not open, since only the people it is shared with may enter it.
You see the agents you can use. Team administrators also see every agent of the teams they administer, restricted ones included; workspace administrators see every agent in the workspace.

Per-agent usage

To see one agent you can access, open its Activity page and use the Usage tab. It shows the same three things over the chosen period, in more depth: each key metric with its daily records, activity by channel and who took part, and credits used broken down by what consumed them, with conversations split by where they took place (in-app chat, Slack, Microsoft Teams), like the Credit breakdown for the whole workspace.

Credit balance

The Credit balance tab, for workspace administrators, is about the account rather than individual agents: how many credits are left, how fast they are going, and where they went. Per-agent figures live on the Agent usage tab.
  • Current balance — Your remaining credits, and the next top-up date and amount when the workspace has a subscription
  • Burn rate — Average credits used per day over the last 14 days
  • Credits used — Total credits used in the current billing period, or the last 30 days without a subscription
  • Credit balance history — How your balance has changed over the selected period, with the monthly allowance marked
  • Credit breakdown — Credits used over the last 7, 30 or 90 days by what consumed them: conversations, email, scheduled triggers, API calls, background work and so on. Conversations are split by where they took place (in-app chat, Slack, Microsoft Teams), with messages to agents in Slack trigger mode counted under Slack. Background work is what agents do outside conversations and the triggers listed: writing the diary, tasks, internal upkeep, and events from Trello, GitHub and Teams meeting transcripts. Not traced to a chat is conversation spend that no chat accounts for, such as naming chats, voice input and replies that were stopped or failed.
  • Credits used over time — Daily, weekly or monthly bars for a date range of your choice, coloured by agent. When the workspace uses teams the bars are stacked by team instead, and a Team dropdown narrows the chart to one team (or to agents without a team) to see its agents. The largest agents get their own colour; the rest are grouped as “Other agents”. Agents deleted in the last 30 days keep their name, marked as deleted; if their team was deleted with them, they appear under an unknown team.
Team administrators find the same chart, for one team, on the Credits used tab of each team they administer. See Teams. You can also export the credits used as a CSV file if you want to analyze spending in a spreadsheet or import it into other tools. The export uses the date range, interval and team shown in the chart and lets you choose the aggregation: per time period and agent, by agent total, by team and period, or by time period total. Per-agent aggregations can include extra agent details (team, admin emails, enabled, criticality, description, value statement, capabilities, tags, last activity, last updated).
Review your usage regularly to identify agents that may need optimization. High credit usage often indicates opportunities to simplify instructions or reduce context size.

Member adoption

The Member adoption tab shows how actively people in your workspace are using Abundly — useful for tracking rollout, identifying inactive seats, and spotting which teams have taken to the platform.
  • Active members — How many workspace members were active (logged in or interacted with an agent) in the selected period
  • Adoption rate — Active members as a share of total members
  • Average sessions per member — Mean session count across active members
  • New members — How many members joined the workspace in the period
A daily trend chart shows active members over the selected period (the last 7, 30 or 90 days). A team filter and a paginated member table let you drill into individual people, with each row showing their last login and last activity.
Team administrators see member adoption scoped to teams they administer. Workspace administrators see all members.

Agent limits

Three kinds of credit limits can stop an agent, and it stops at the first one it reaches: The limits do different jobs. The daily limit is a safety net against runaway usage, such as an agent stuck in a loop: it stops the agent quickly, and anyone who can edit the agent can lift it by resetting today’s usage. Monthly limits are for budgeting: a hard cap that only admins can change, so you can plan what an agent, or a whole team, may spend. The Agent limits tab on the Agent management page lets you set daily and monthly limits for your agents to prevent runaway credit usage.
Agent Limits tab: a workspace default of 20,000 credits per agent per month, and Platform team agents with usage bars. Releaser is near its daily limit of 500 credits

Default limits

Set a default daily limit, and optionally a default monthly limit, that apply to every agent without a limit of its own. They act as a safety net across your workspace. New workspaces start at 5,000 credits per agent per day and no default monthly limit, and workspaces that have already set their own daily default keep it. Only workspace administrators can set or change the workspace defaults.

Agent-specific limits

You can override the default daily limit for individual agents, for example to set a higher or lower limit. Setting the limit to 0 will effectively pause the agent. Only workspace administrators and team administrators of the agent’s team can set or change an agent’s daily limit. Edit or Owner access to the agent alone is not enough — it does, however, let you reset today’s usage.

Agent monthly limits

Because anyone with Edit or Owner access can reset today’s usage, the daily limit isn’t a hard ceiling. When you need one, give the agent a monthly limit: select the agent on the Agent limits tab, or open its Settings → Usage & Limits, and enter the credits it may use per month. Agents have no monthly limit unless you set one, or set a default monthly limit for the workspace, which an agent’s own monthly limit overrides. A monthly limit is a hard cap:
  • Only workspace administrators and team administrators of the agent’s team can set, change, or remove it.
  • Resetting today’s usage doesn’t affect it.
  • When it’s reached, the agent pauses, in chat and on triggers, until an admin raises the limit or the calendar month rolls over (UTC).
Everyone who can use the agent sees its monthly limit in Settings → Usage & Limits, and a chat banner when usage approaches it (80%) and when it has been reached. The agent’s owners also get a notification.

When limits are reached

When an agent hits one of its limits:
  • The agent stops immediately and shows an error message
  • No additional credits are consumed
  • All data and configurations remain intact
  • A daily limit resets automatically at UTC midnight, and a monthly limit on the 1st of the month
You’ll see visual indicators in the UI:
  • Yellow badge when an agent approaches its limit (80%+)
  • Red badge when the limit is exceeded
Workspace administrators can set the workspace default daily limit, set team monthly limits and the monthly limit for personal agents, and edit the daily and monthly limits of any agent. Team administrators can edit the daily and monthly limits of agents in teams they administer.

Team monthly limits

If your workspace uses teams, workspace administrators can cap how many credits each team consumes per month. When a team reaches its monthly limit, every agent that belongs to the team pauses until the limit is raised or the calendar month rolls over. Set monthly limits from the Settings tab on the Team management page. Each team card shows the current month’s usage, the configured limit (if any), and a progress bar. Limits can also be set and read through the Workspace API or by an agent with the Workspace Manager capability. Team monthly limits are enforced in addition to the agent’s own daily and monthly limits: an agent is blocked as soon as any of them is reached. Personal agents have a monthly limit of their own: one amount per person, shared by all of that person’s personal agents in the workspace, set under Workspace → Settings → Personal agents. When someone reaches it, all of their personal agents pause until the month rolls over or a workspace admin raises the limit. Monthly limits follow the calendar month in UTC, and usage starts again from zero on the 1st. When an agent draws on a monthly limit, everyone who can use it sees that limit:
  • In the agent’s Settings → Usage & Limits, under Team limit or Personal agents limit: this month’s usage against the limit, with a progress bar. The limit isn’t the agent’s own—it’s shared by all of the team’s agents, or all of the owner’s personal agents.
  • In chat, as a banner when usage is approaching the limit (80%) and when it has been reached. Workspace admins also get a link to edit the limit.
When you open an agent, the left sidebar can show a compact usage widget with:
  • Credits used today, with a progress bar when the agent has a daily limit
  • Credits used this month, with a progress bar, when the agent has a monthly limit
  • A quick link to that agent’s Settings → Usage & Limits
This widget auto-refreshes as new usage is recorded, including after chat responses complete and when new activity log entries arrive. To show this widget, turn on Credit details in the agent’s Settings → Usage & Limits section. Workspace admins can choose whether new agents start with credit details on under Workspace → Settings → Agent defaults; teams can override this in their own settings.

Resetting daily usage

You can manually reset an agent’s daily credit counter at any time. This is useful if an agent hit its limit due to a one-time spike and you want to resume normal operation without waiting for midnight UTC. Anyone with Edit or Owner access to the agent can reset it, as can workspace administrators and team administrators of the agent’s team. Use access is not enough. Changing the daily limit itself is stricter — see Agent-specific limits. Resetting only lifts the daily limit. While the agent’s monthly limit or its team’s monthly limit is reached, Reset today is disabled, since the agent would stay paused anyway.
Usage & Limits section in agent settings: the agent is near its daily limit at 462 of 500 credits, with Edit limit and Reset today buttons, and a monthly limit below
To reset an agent’s usage:
  1. Open the agent’s settings
  2. Under Main Settings, find Usage & Limits
  3. Click Reset Today
A reset doesn’t erase what the agent has already used. After a reset, the daily progress bar counts the credits used since the reset (for example “0 / 500 credits since reset at 09:58”), and the line below it shows the total credits used today and how many times the usage was reset. In the Usage (today) column of Agent management, an agent reset today shows that total, marked ↻. If the limit interrupted a chat conversation, a Continue button appears on the error message once the usage is reset or the limit is raised, so the agent can pick up where it left off.

What counts toward credits

Both LLM usage (tokens) and tool usage count toward credits:
  • LLM tokens — Input, output, and reasoning tokens are converted to credits based on model-specific rates
  • Tool usage — Tools like web search, document processing, and external APIs also consume credits
All agent activity counts toward the agent’s limits, regardless of how it’s triggered—chat conversations, scheduled jobs, webhooks, emails, or API calls.

User action log

The User action log tab gives workspace administrators an append-only audit trail of configuration and membership changes across the workspace — useful for reviewing who changed what, who invited whom, spotting unexpected changes, and satisfying compliance requirements. Tracked change types include:
  • Agents — created, edited, enabled/disabled, deleted, ownership and team changes
  • Teams — created, edited, membership and admin changes
  • Workspace settings — configuration, capabilities, model selection, notification settings
  • Secrets — created, updated, deleted
  • Outgoing APIs — created, updated, deleted
  • HTTP APIs and documents — created, updated, deleted
  • Members and invitations — invitations sent, revoked, and declined; members joining (with who invited them), leaving, and changing role; people added to and removed from teams; support role grants
Each row shows a timestamp, actor, resource, and a CRUD-colored badge (create / update / delete). Expand a row to see the specific fields that changed. Actors are usually workspace members, but changes an agent makes through a capability tool (for example Workspace Manager) appear here too, attributed to that agent, and changes made through the Workspace API are attributed to the API key. An agent with the Workspace Explorer capability can read this log too, and so can the Workspace API — for example to find production agents that changed after their promotion was approved. A Team Explorer agent sees the team’s own entries, who joined or left the team, and the entries for the team’s agents, except restricted ones.
Sensitive text fields — such as agent instructions and prompts — are shown as short hash tokens rather than raw content. This lets admins confirm that content changed without exposing the underlying text.
Workspace administrators see the full workspace history. Team administrators see their team’s own log on the team page: changes to the team and who joined or left it, including invitations to the team.

Filtering and export

Filter by date range, actor, resource type, and action type. Export the filtered view as CSV or JSONL (up to 50,000 rows per export).

FAQ

UTC. The daily limit resets at midnight UTC, not your local time zone.
Not directly. If you want one agent to be unlimited while others have a default limit, set that agent’s limit to a very high number (e.g., 999,999 credits/day).
Both, for different jobs. The daily limit catches a runaway day, and the people working on the agent can reset today’s usage when they need to keep going. The monthly limit is the ceiling: use it when an agent’s spend must not go past an amount, since only admins can change it and resets don’t touch it.
All of your personal agents pause, in chat and on triggers, until the month rolls over or a workspace admin raises the limit. The limit is per person, so what one of your personal agents uses counts for all of them. Team agents you use are unaffected: they draw on their team’s limit instead.

Learn more

Monitoring

Track agent activity, execution logs, and performance

Agent Optimization

Detailed examples of credit usage and optimization strategies