Monitor agent health, troubleshoot tool calls, and understand credit usage
Operate Agents After They Go Live
Building an agent is only the beginning. Once agents are running on schedules, webhooks, or requests, use Decisional’s dashboards to answer three different questions:
View
Main question
Scope
Agent Dashboard
Are my workspace agents running successfully and on schedule?
Current workspace
Tool Calls
Which integration, toolkit, or tool is failing or taking too long?
Current account
Usage
Where are credits being spent, and should I set a cap?
Current account
Start with the Agent Dashboard for overall health. Move to Tool Calls when an integration action is failing or slow. Use Usage to understand cost and control monthly agent spend.
The AI Usage and Tool Stats summaries on the Agent Dashboard are workspace-scoped. The full Usage and Tool Calls pages are account-wide. Check the account badge and use the same date range before comparing numbers across pages.
Agent Dashboard
In Agents mode, select Dashboard. This is the day-to-day operating view for the selected workspace.
The Agent Dashboard combines agent status, recent run health, published agents, and upcoming schedules.
What the Summary Cards Mean
Card
What it tells you
Total Agents
Number of agents in the workspace, with the number currently Live in parentheses
Upcoming Runs
Scheduled executions that are expected to start next
Fixer-assisted runs
Runs where Decisional’s Fixer helped recover or repair execution during the selected period
Completed Runs
Runs that finished successfully during the selected period
Failed Runs
Runs that ended in failure during the selected period
The Agent Run Activity chart shows completed, failed, and currently running executions over time. Use the 30-day, 14-day, 7-day, 24-hour, or custom date filter to separate a one-time problem from a repeated pattern.Below the chart:
Published Agents shows the Live and Paused agents in the workspace
Upcoming Runs lists scheduled executions and their expected start time
Past Runs links recent executions to their agent and run status
AI Usage summarizes workspace model and Agent Node usage
Tool Stats summarizes workspace tool volume and success
A small number of Fixer-assisted runs is not the same as a failed run—the Fixer may have recovered the execution. Repeated Fixer assistance on the same agent is still worth investigating because it can reveal a fragile instruction, changing data, or an unreliable integration.
When Something Looks Wrong
Open the affected run from Past Runs.
Select the run on the workflow graph.
Find the first failed, incomplete, or unusually slow node.
If it is an integration action, open Tool Calls to compare it with other calls to the same tool.
If it is an AI or Agent Node step, open Usage to review model, Agent Node, and per-agent activity.
Inspecting Runs
Learn how to inspect node execution, inputs, outputs, logs, and failures on the workflow run surface.
Usage and Credits
Open the full Usage page from the AI Usage section on the Agent Dashboard. The account badge shows whether the numbers belong to an organization or a personal account.
The Usage page shows the account balance, period spend, the default agent cap, and daily spend by resource type.
Balance and Spend
Metric
Meaning
Available
Current credits available after active reservations
Reserved
Credits temporarily set aside for active metered work
Total Balance
Available and reserved credits combined
Spent
Credits actually charged during the selected period
The Daily Usage chart groups credit-equivalent activity by resource type. Depending on the work performed, it can include:
AI / LLM Calls for model requests
Agent Node for sandboxed agent execution, including supported Claude Code, Codex, or Cursor runtimes
Platform Tools for metered platform-provided integration calls
Workflow Runs, Agent Builds, and Storage when those resource types apply
“Credit-equivalent” can include work paid for with a personal provider key. Personal-key usage is tracked so you can understand total activity, but it is not deducted from the Decisional credit balance. The Spent card and charged amounts exclude that personal-key portion.
Understand What Is Driving Spend
Scroll down to compare models and agents.
Spend by Model explains model usage, while Agent Spend & Caps shows which agents consume credits and how close each one is to its monthly limit.
Use Spend by Model to compare:
Credits attributed to each model
Number of model calls
Input and output tokens
Average credits per call
Use Agent Spend & Caps to compare:
LLM spend and Agent Node spend for each agent
Total calls and average credit use per model call
Monthly cap usage, active reservations, and remaining credits
Whether an agent is Live, at its cap, or blocked by its cap
You can search by agent name, UUID, or agt_ public ID. The All time option changes the spend columns, but cap usage always represents the current UTC month.
Set Monthly Agent Caps
Agent Spend Default sets the account-wide monthly cap for workflow-run credits. Individual agents can inherit this default or use their own override.
1
Choose a default
Enter a whole number of credits in Monthly cap and select Save. Leave the default clear when agents should be uncapped unless they have their own override.
2
Review current cap usage
In Agent Spend & Caps, compare each agent’s current-month usage with its effective cap and remaining credits.
3
Investigate before raising a cap
Check the agent’s model calls, Agent Node activity, and recent runs. A sudden increase may come from more work, repeated retries, unexpectedly large inputs, or a workflow loop.
4
Change the right limit
Update the account default when the policy should change for many agents. Use an individual override when one agent has a different workload.
The lower sections of the Usage page provide a full audit trail:
Usage by Resource Type summarizes where credits went
Credit Grants shows granted amounts, remaining balances, and expiration
Active Reservations shows credits currently held for work in progress
Open the full Tool Calls page from Tool Stats on the Agent Dashboard or from the Integrations area. Use it when a workflow reaches an integration step but the result is slow, missing, or incorrect.
The Tool Calls dashboard shows account-wide volume, reliability, latency, providers, and changes over time.
Read the Top-Level Metrics
Metric
Meaning
Total tool calls
Number of recorded tool operations in the selected period
Success rate
Share of calls that completed successfully, with errors and timeouts shown underneath
Avg latency
Average call duration; p95 shows the duration that 95 percent of calls completed within
Providers
Number of tool providers with activity, with the busiest providers summarized underneath
The Tool Calls Over Time chart separates successful calls from errors and timeouts. A short error spike can indicate a provider incident. A steady error rate on one toolkit is more likely to point to credentials, permissions, inputs, or an API change.Continue down the page to compare:
Calls, errors, and average latency by provider
Top toolkits and individual tools
Agents generating the most tool activity
Recent individual tool calls
Use the filters to narrow recent calls by provider, toolkit, status, caller, agent, thread, or search text. This lets you move from an account-wide spike to the exact agent and tool involved.
Tool Calls covers recorded integration tools and supported Agent Node or orchestrator actions. Some internal workflow platform tools may be only partially represented, so the total is not necessarily the same as the number of workflow nodes executed.
A Simple Weekly Review
1
Check run health
Open the Agent Dashboard for each active workspace. Look for failed runs, recurring Fixer assistance, paused agents, and missed or unexpected schedules.
2
Investigate reliability
Open Tool Calls when errors increase. Narrow the data from provider to toolkit to tool, then identify the affected agent and recent call.
3
Review spend
Open Usage and compare the current period with the previous one. Check the resource, model, and agent tables for unexpected changes.
4
Adjust guardrails
Review the default monthly cap and individual agent overrides. Raise a cap only after confirming the higher usage is expected.
These views work together: the Agent Dashboard shows what changed, Tool Calls helps explain why an integration step changed, and Usage shows what the work cost.
{"docsConfig":{"$schema":"https://mintlify.com/docs.json","theme":"mint","name":"Decisional Documentation","colors":{"primary":"#3E0D77","light":"#6B2A9E","dark":"#230D39"},"favicon":"https://mintcdn.com/decisional/RETrpsVEIJJtqrl0/favicon.svg?fit=max\u0026auto=format\u0026n=RETrpsVEIJJtqrl0\u0026q=85\u0026s=f795f45d1fbfe8d63378fcaebb4fee76","logo":{"light":"https://mintcdn.com/decisional/RETrpsVEIJJtqrl0/logo/light.svg?fit=max\u0026auto=format\u0026n=RETrpsVEIJJtqrl0\u0026q=85\u0026s=9a49e1175b3e00b4d4c78cc0f996761c","dark":"https://mintcdn.com/decisional/RETrpsVEIJJtqrl0/logo/dark.svg?fit=max\u0026auto=format\u0026n=RETrpsVEIJJtqrl0\u0026q=85\u0026s=a172e59de91ef78e1fa101d824e80228"},"navbar":{"links":[{"label":"Support","href":"mailto:founders@decisional.com"}],"primary":{"type":"button","label":"Get Started","href":"https://agents.decisional.com"}},"footer":{"socials":{"x":"https://x.com/getdecisional","linkedin":"https://www.linkedin.com/company/decisional-ai/"}},"styling":{"latex":false},"navigation":{"global":{"anchors":[{"anchor":"Community","href":"https://discord.gg/DwPDS5Prk2","icon":"discord"},{"anchor":"Blog","href":"https://www.decisional.com/blog","icon":"newspaper"},{"anchor":"Changelog","href":"https://www.decisional.com/changelog","icon":"list"}]},"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"decisional","hasAudioNarration":false,"actualSubdomain":"decisional","customDomains":["docs.decisional.com"],"gitSource":{"type":"github","owner":"groovetandon","repo":"mintlify-docs","deployBranch":"main","contentDirectory":"","isPrivate":true,"mountPath":"","label":""},"entitlements":{},"buildId":"6ae9413ed279cbf04ccd9ded:success","clientVersion":"0.0.4177","searchFilterCounts":[{"language":"default","tag":"Documentation","count":26},{"language":"default","tag":"Agents","count":11},{"language":"default","tag":"Getting Started","count":4},{"language":"default","tag":"Data \u0026 Integrations","count":4},{"language":"default","tag":"Platform","count":4},{"language":"default","tag":"Reference","count":2},{"language":"default","tag":"Dex","count":1}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[],"googleFontsInlined":false},"customCss":[],"page":{"pagePath":"dashboards-and-usage","slug":"/dashboards-and-usage","pageMetadata":{"title":"Dashboards and Usage","description":"Monitor agent health, troubleshoot tool calls, and understand credit usage","icon":"chart-line","href":"/dashboards-and-usage"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Monitor agent health, troubleshoot tool calls, and understand credit usage\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={code:`code`,li:`li`,ol:`ol`,p:`p`,strong:`strong`,tbody:`tbody`,td:`td`,th:`th`,thead:`thead`,tr:`tr`,ul:`ul`,..._provideComponents(),...props.components},{Card,Frame,Heading,Icon,Info,Note,OptimizedImage,Step,Steps,Table,Tip,Warning}=_components;if(!Card)_missingMdxReference(`Card`,true);if(!Frame)_missingMdxReference(`Frame`,true);if(!Heading)_missingMdxReference(`Heading`,true);if(!Icon)_missingMdxReference(`Icon`,true);if(!Info)_missingMdxReference(`Info`,true);if(!Note)_missingMdxReference(`Note`,true);if(!OptimizedImage)_missingMdxReference(`OptimizedImage`,true);if(!Step)_missingMdxReference(`Step`,true);if(!Steps)_missingMdxReference(`Steps`,true);if(!Table)_missingMdxReference(`Table`,true);if(!Tip)_missingMdxReference(`Tip`,true);if(!Warning)_missingMdxReference(`Warning`,true);return _jsxs(_Fragment,{children:[_jsxs(Heading,{level:`2`,id:`operate-agents-after-they-go-live`,children:[_jsx(Icon,{icon:`play`,size:20}),` Operate Agents After They Go Live`]}),`\n`,_jsx(_components.p,{children:`Building an agent is only the beginning. Once agents are running on schedules, webhooks, or requests, use Decisional’s dashboards to answer three different questions:`}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`View`}),_jsx(_components.th,{children:`Main question`}),_jsx(_components.th,{children:`Scope`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Agent Dashboard`})}),_jsx(_components.td,{children:`Are my workspace agents running successfully and on schedule?`}),_jsx(_components.td,{children:`Current workspace`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Tool Calls`})}),_jsx(_components.td,{children:`Which integration, toolkit, or tool is failing or taking too long?`}),_jsx(_components.td,{children:`Current account`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Usage`})}),_jsx(_components.td,{children:`Where are credits being spent, and should I set a cap?`}),_jsx(_components.td,{children:`Current account`})]})]})]}),`\n`,_jsxs(_components.p,{children:[`Start with the `,_jsx(_components.strong,{children:`Agent Dashboard`}),` for overall health. Move to `,_jsx(_components.strong,{children:`Tool Calls`}),` when an integration action is failing or slow. Use `,_jsx(_components.strong,{children:`Usage`}),` to understand cost and control monthly agent spend.`]}),`\n`,_jsx(Info,{children:_jsx(_components.p,{children:`The AI Usage and Tool Stats summaries on the Agent Dashboard are workspace-scoped. The full Usage and Tool Calls pages are account-wide. Check the account badge and use the same date range before comparing numbers across pages.`})}),`\n`,_jsxs(Heading,{level:`2`,id:`agent-dashboard`,children:[_jsx(Icon,{icon:`layout-dashboard`,size:20}),` Agent Dashboard`]}),`\n`,_jsxs(_components.p,{children:[`In `,_jsx(_components.strong,{children:`Agents`}),` mode, select `,_jsx(_components.strong,{children:`Dashboard`}),`. This is the day-to-day operating view for the selected workspace.`]}),`\n`,_jsx(Frame,{caption:`The Agent Dashboard combines agent status, recent run health, published agents, and upcoming schedules.`,children:_jsx(OptimizedImage,{src:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=b50056e31772392b799f959a73d9f7e2`,alt:`Agent Dashboard showing total and live agents, upcoming runs, Fixer-assisted runs, completed and failed runs, an activity chart, and published agents`,\"data-og-width\":`1697`,width:`1697`,\"data-og-height\":`927`,height:`927`,\"data-path\":`images/operations/agent-dashboard.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=280\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=fca2525a4d5dbc931e52c831139b7a36 280w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=560\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=d3ce99b1b09c03bf196c364db0cea9bc 560w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=840\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=e9d25c8a521ba264a72141cef758231c 840w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=1100\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=a8bbfd873fd6de071967842442981883 1100w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=1650\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=eac714905ae4bd52dea7ec49fc7d24f2 1650w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/agent-dashboard.png?w=2500\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=840616007101a60039d26ac8e816297f 2500w`})}),`\n`,_jsxs(Heading,{level:`3`,id:`what-the-summary-cards-mean`,children:[_jsx(Icon,{icon:`table-columns`,size:16}),` What the Summary Cards Mean`]}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Card`}),_jsx(_components.th,{children:`What it tells you`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Total Agents`})}),_jsx(_components.td,{children:`Number of agents in the workspace, with the number currently Live in parentheses`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Upcoming Runs`})}),_jsx(_components.td,{children:`Scheduled executions that are expected to start next`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Fixer-assisted runs`})}),_jsx(_components.td,{children:`Runs where Decisional’s Fixer helped recover or repair execution during the selected period`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Completed Runs`})}),_jsx(_components.td,{children:`Runs that finished successfully during the selected period`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Failed Runs`})}),_jsx(_components.td,{children:`Runs that ended in failure during the selected period`})]})]})]}),`\n`,_jsxs(_components.p,{children:[`The `,_jsx(_components.strong,{children:`Agent Run Activity`}),` chart shows completed, failed, and currently running executions over time. Use the 30-day, 14-day, 7-day, 24-hour, or custom date filter to separate a one-time problem from a repeated pattern.`]}),`\n`,_jsx(_components.p,{children:`Below the chart:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Published Agents`}),` shows the Live and Paused agents in the workspace`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Upcoming Runs`}),` lists scheduled executions and their expected start time`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Past Runs`}),` links recent executions to their agent and run status`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`AI Usage`}),` summarizes workspace model and Agent Node usage`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Tool Stats`}),` summarizes workspace tool volume and success`]}),`\n`]}),`\n`,_jsx(Tip,{children:_jsx(_components.p,{children:`A small number of Fixer-assisted runs is not the same as a failed run—the Fixer may have recovered the execution. Repeated Fixer assistance on the same agent is still worth investigating because it can reveal a fragile instruction, changing data, or an unreliable integration.`})}),`\n`,_jsxs(Heading,{level:`3`,id:`when-something-looks-wrong`,children:[_jsx(Icon,{icon:`triangle-exclamation`,size:16}),` When Something Looks Wrong`]}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[`Open the affected run from `,_jsx(_components.strong,{children:`Past Runs`}),`.`]}),`\n`,_jsx(_components.li,{children:`Select the run on the workflow graph.`}),`\n`,_jsx(_components.li,{children:`Find the first failed, incomplete, or unusually slow node.`}),`\n`,_jsxs(_components.li,{children:[`If it is an integration action, open `,_jsx(_components.strong,{children:`Tool Calls`}),` to compare it with other calls to the same tool.`]}),`\n`,_jsxs(_components.li,{children:[`If it is an AI or Agent Node step, open `,_jsx(_components.strong,{children:`Usage`}),` to review model, Agent Node, and per-agent activity.`]}),`\n`]}),`\n`,_jsx(Card,{title:`Inspecting Runs`,icon:`magnifying-glass`,href:`/guides/runs`,children:_jsx(_components.p,{children:`Learn how to inspect node execution, inputs, outputs, logs, and failures on the workflow run surface.`})}),`\n`,_jsxs(Heading,{level:`2`,id:`usage-and-credits`,children:[_jsx(Icon,{icon:`coins`,size:20}),` Usage and Credits`]}),`\n`,_jsxs(_components.p,{children:[`Open the full `,_jsx(_components.strong,{children:`Usage`}),` page from the `,_jsx(_components.strong,{children:`AI Usage`}),` section on the Agent Dashboard. The account badge shows whether the numbers belong to an organization or a personal account.`]}),`\n`,_jsx(Frame,{caption:`The Usage page shows the account balance, period spend, the default agent cap, and daily spend by resource type.`,children:_jsx(OptimizedImage,{src:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=689fb59eb6aa488b49193b50c74b8181`,alt:`Usage dashboard showing available, reserved, total, and spent credits, the Agent Spend Default, and a Daily Usage chart`,\"data-og-width\":`1694`,width:`1694`,\"data-og-height\":`928`,height:`928`,\"data-path\":`images/operations/usage-overview.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=280\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=cf10a1ed5e7fc06a22a508c8d108901b 280w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=560\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=1719802c0588dd0c189518157d7ef905 560w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=840\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=f30c196f8acc50dedf6245ffa99ddbff 840w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=1100\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=5620c8b8756e45d01043886c67ed719e 1100w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=1650\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=04201297cbeb3f8d6b33300b4ad73189 1650w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-overview.png?w=2500\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=4d68ca9dae0ed63d829e1641fff1d07c 2500w`})}),`\n`,_jsxs(Heading,{level:`3`,id:`balance-and-spend`,children:[_jsx(Icon,{icon:`wallet`,size:16}),` Balance and Spend`]}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Metric`}),_jsx(_components.th,{children:`Meaning`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Available`})}),_jsx(_components.td,{children:`Current credits available after active reservations`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Reserved`})}),_jsx(_components.td,{children:`Credits temporarily set aside for active metered work`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Total Balance`})}),_jsx(_components.td,{children:`Available and reserved credits combined`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Spent`})}),_jsx(_components.td,{children:`Credits actually charged during the selected period`})]})]})]}),`\n`,_jsxs(_components.p,{children:[`The `,_jsx(_components.strong,{children:`Daily Usage`}),` chart groups credit-equivalent activity by resource type. Depending on the work performed, it can include:`]}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`AI / LLM Calls`}),` for model requests`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Agent Node`}),` for sandboxed agent execution, including supported Claude Code, Codex, or Cursor runtimes`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Platform Tools`}),` for metered platform-provided integration calls`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Workflow Runs`}),`, `,_jsx(_components.strong,{children:`Agent Builds`}),`, and `,_jsx(_components.strong,{children:`Storage`}),` when those resource types apply`]}),`\n`]}),`\n`,_jsx(Note,{children:_jsxs(_components.p,{children:[`“Credit-equivalent” can include work paid for with a personal provider key. Personal-key usage is tracked so you can understand total activity, but it is not deducted from the Decisional credit balance. The `,_jsx(_components.strong,{children:`Spent`}),` card and charged amounts exclude that personal-key portion.`]})}),`\n`,_jsxs(Heading,{level:`3`,id:`understand-what-is-driving-spend`,children:[_jsx(Icon,{icon:`chart-pie`,size:16}),` Understand What Is Driving Spend`]}),`\n`,_jsx(_components.p,{children:`Scroll down to compare models and agents.`}),`\n`,_jsx(Frame,{caption:`Spend by Model explains model usage, while Agent Spend \u0026 Caps shows which agents consume credits and how close each one is to its monthly limit.`,children:_jsx(OptimizedImage,{src:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=d5c2bd3322581487a420032babba8fea`,alt:`Usage dashboard showing Spend by Model and Agent Spend and Caps tables with LLM spend, Agent Node spend, calls, averages, cap usage, remaining credits, and status`,\"data-og-width\":`1692`,width:`1692`,\"data-og-height\":`929`,height:`929`,\"data-path\":`images/operations/usage-agent-spend.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=280\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=a411fc74e0203499a024569d80428ee8 280w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=560\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=cecacbd716018a3c396d1b694351c7db 560w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=840\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=95cacf6bef785ce7e6af86633b2b794a 840w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=1100\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=16499980bc78b2855998ba866d0a6af6 1100w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=1650\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=4ad01f75b74dc867d5eda5fbb9332488 1650w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/usage-agent-spend.png?w=2500\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=23e730a00ce67d73e9f7877d1a40cdda 2500w`})}),`\n`,_jsxs(_components.p,{children:[`Use `,_jsx(_components.strong,{children:`Spend by Model`}),` to compare:`]}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Credits attributed to each model`}),`\n`,_jsx(_components.li,{children:`Number of model calls`}),`\n`,_jsx(_components.li,{children:`Input and output tokens`}),`\n`,_jsx(_components.li,{children:`Average credits per call`}),`\n`]}),`\n`,_jsxs(_components.p,{children:[`Use `,_jsx(_components.strong,{children:`Agent Spend \u0026 Caps`}),` to compare:`]}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`LLM spend and Agent Node spend for each agent`}),`\n`,_jsx(_components.li,{children:`Total calls and average credit use per model call`}),`\n`,_jsx(_components.li,{children:`Monthly cap usage, active reservations, and remaining credits`}),`\n`,_jsx(_components.li,{children:`Whether an agent is Live, at its cap, or blocked by its cap`}),`\n`]}),`\n`,_jsxs(_components.p,{children:[`You can search by agent name, UUID, or `,_jsx(_components.code,{children:`agt_`}),` public ID. The `,_jsx(_components.strong,{children:`All time`}),` option changes the spend columns, but cap usage always represents the current UTC month.`]}),`\n`,_jsxs(Heading,{level:`3`,id:`set-monthly-agent-caps`,children:[_jsx(Icon,{icon:`gauge-high`,size:16}),` Set Monthly Agent Caps`]}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Agent Spend Default`}),` sets the account-wide monthly cap for workflow-run credits. Individual agents can inherit this default or use their own override.`]}),`\n`,_jsxs(Steps,{children:[_jsx(Step,{title:`Choose a default`,children:_jsxs(_components.p,{children:[`Enter a whole number of credits in `,_jsx(_components.strong,{children:`Monthly cap`}),` and select `,_jsx(_components.strong,{children:`Save`}),`. Leave the default clear when agents should be uncapped unless they have their own override.`]})}),_jsx(Step,{title:`Review current cap usage`,children:_jsxs(_components.p,{children:[`In `,_jsx(_components.strong,{children:`Agent Spend \u0026 Caps`}),`, compare each agent’s current-month usage with its effective cap and remaining credits.`]})}),_jsx(Step,{title:`Investigate before raising a cap`,children:_jsx(_components.p,{children:`Check the agent’s model calls, Agent Node activity, and recent runs. A sudden increase may come from more work, repeated retries, unexpectedly large inputs, or a workflow loop.`})}),_jsx(Step,{title:`Change the right limit`,children:_jsx(_components.p,{children:`Update the account default when the policy should change for many agents. Use an individual override when one agent has a different workload.`})})]}),`\n`,_jsx(_components.p,{children:`The lower sections of the Usage page provide a full audit trail:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Usage by Resource Type`}),` summarizes where credits went`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Credit Grants`}),` shows granted amounts, remaining balances, and expiration`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Active Reservations`}),` shows credits currently held for work in progress`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Transaction Ledger`}),` lists grants, debits, reservations, settlements, refunds, adjustments, and expirations`]}),`\n`]}),`\n`,_jsxs(Heading,{level:`2`,id:`tool-calls`,children:[_jsx(Icon,{icon:`wrench`,size:20}),` Tool Calls`]}),`\n`,_jsxs(_components.p,{children:[`Open the full `,_jsx(_components.strong,{children:`Tool Calls`}),` page from `,_jsx(_components.strong,{children:`Tool Stats`}),` on the Agent Dashboard or from the Integrations area. Use it when a workflow reaches an integration step but the result is slow, missing, or incorrect.`]}),`\n`,_jsx(Frame,{caption:`The Tool Calls dashboard shows account-wide volume, reliability, latency, providers, and changes over time.`,children:_jsx(OptimizedImage,{src:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=fe35780d177f3a325290ce3f2f2dc52b`,alt:`Tool Calls dashboard showing total calls, success rate, average latency, provider count, calls over time, calls by provider, and top toolkits`,\"data-og-width\":`1693`,width:`1693`,\"data-og-height\":`929`,height:`929`,\"data-path\":`images/operations/tool-calls-dashboard.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=280\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=e634bafe8c35096997e6a506abdc093d 280w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=560\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=a3ffdfb47a445751397e495a82f5af4d 560w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=840\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=c8542fe40eee1fa63359c2c0c0b1024b 840w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=1100\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=bcc49537d266c1d1377221cd04d801be 1100w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=1650\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=22a016fba674a96763d8037ce31d028d 1650w, https://mintcdn.com/decisional/p_K8KTgUaUdelXwd/images/operations/tool-calls-dashboard.png?w=2500\u0026fit=max\u0026auto=format\u0026n=p_K8KTgUaUdelXwd\u0026q=85\u0026s=919141f45694d472606be3a97bb62dcc 2500w`})}),`\n`,_jsxs(Heading,{level:`3`,id:`read-the-top-level-metrics`,children:[_jsx(Icon,{icon:`chart-simple`,size:16}),` Read the Top-Level Metrics`]}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Metric`}),_jsx(_components.th,{children:`Meaning`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Total tool calls`})}),_jsx(_components.td,{children:`Number of recorded tool operations in the selected period`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Success rate`})}),_jsx(_components.td,{children:`Share of calls that completed successfully, with errors and timeouts shown underneath`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Avg latency`})}),_jsx(_components.td,{children:`Average call duration; p95 shows the duration that 95 percent of calls completed within`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Providers`})}),_jsx(_components.td,{children:`Number of tool providers with activity, with the busiest providers summarized underneath`})]})]})]}),`\n`,_jsxs(_components.p,{children:[`The `,_jsx(_components.strong,{children:`Tool Calls Over Time`}),` chart separates successful calls from errors and timeouts. A short error spike can indicate a provider incident. A steady error rate on one toolkit is more likely to point to credentials, permissions, inputs, or an API change.`]}),`\n`,_jsx(_components.p,{children:`Continue down the page to compare:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Calls, errors, and average latency by provider`}),`\n`,_jsx(_components.li,{children:`Top toolkits and individual tools`}),`\n`,_jsx(_components.li,{children:`Agents generating the most tool activity`}),`\n`,_jsx(_components.li,{children:`Recent individual tool calls`}),`\n`]}),`\n`,_jsx(_components.p,{children:`Use the filters to narrow recent calls by provider, toolkit, status, caller, agent, thread, or search text. This lets you move from an account-wide spike to the exact agent and tool involved.`}),`\n`,_jsx(Warning,{children:_jsx(_components.p,{children:`Tool Calls covers recorded integration tools and supported Agent Node or orchestrator actions. Some internal workflow platform tools may be only partially represented, so the total is not necessarily the same as the number of workflow nodes executed.`})}),`\n`,_jsxs(Heading,{level:`2`,id:`a-simple-weekly-review`,children:[_jsx(Icon,{icon:`clipboard-check`,size:20}),` A Simple Weekly Review`]}),`\n`,_jsxs(Steps,{children:[_jsx(Step,{title:`Check run health`,children:_jsx(_components.p,{children:`Open the Agent Dashboard for each active workspace. Look for failed runs, recurring Fixer assistance, paused agents, and missed or unexpected schedules.`})}),_jsx(Step,{title:`Investigate reliability`,children:_jsx(_components.p,{children:`Open Tool Calls when errors increase. Narrow the data from provider to toolkit to tool, then identify the affected agent and recent call.`})}),_jsx(Step,{title:`Review spend`,children:_jsx(_components.p,{children:`Open Usage and compare the current period with the previous one. Check the resource, model, and agent tables for unexpected changes.`})}),_jsx(Step,{title:`Adjust guardrails`,children:_jsx(_components.p,{children:`Review the default monthly cap and individual agent overrides. Raise a cap only after confirming the higher usage is expected.`})})]}),`\n`,_jsxs(_components.p,{children:[`These views work together: the Agent Dashboard shows `,_jsx(_components.strong,{children:`what changed`}),`, Tool Calls helps explain `,_jsx(_components.strong,{children:`why an integration step changed`}),`, and Usage shows `,_jsx(_components.strong,{children:`what the work cost`}),`.`]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Dashboards and Usage","description":"Monitor agent health, troubleshoot tool calls, and understand credit usage","icon":"chart-line","href":"/dashboards-and-usage"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":" Operate Agents After They Go Live","slug":"operate-agents-after-they-go-live","depth":2,"children":[]},{"title":" Agent Dashboard","slug":"agent-dashboard","depth":2,"children":[{"title":" What the Summary Cards Mean","slug":"what-the-summary-cards-mean","depth":3,"children":[]},{"title":" When Something Looks Wrong","slug":"when-something-looks-wrong","depth":3,"children":[]}]},{"title":" Usage and Credits","slug":"usage-and-credits","depth":2,"children":[{"title":" Balance and Spend","slug":"balance-and-spend","depth":3,"children":[]},{"title":" Understand What Is Driving Spend","slug":"understand-what-is-driving-spend","depth":3,"children":[]},{"title":" Set Monthly Agent Caps","slug":"set-monthly-agent-caps","depth":3,"children":[]}]},{"title":" Tool Calls","slug":"tool-calls","depth":2,"children":[{"title":" Read the Top-Level Metrics","slug":"read-the-top-level-metrics","depth":3,"children":[]}]},{"title":" A Simple Weekly Review","slug":"a-simple-weekly-review","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":[],"subdomain":"decisional","siteName":"Decisional Documentation","title":"Dashboards and Usage - Decisional Documentation","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-07-26T17:53:54.539Z","originalFileLocation":"dashboards-and-usage.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Monitor agent health, troubleshoot tool calls, and understand credit usage\">\u003cmeta data-mint-head name=\"application-name\" content=\"Decisional Documentation\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Dashboards and Usage - Decisional Documentation\">\u003cmeta data-mint-head property=\"og:description\" content=\"Monitor agent health, troubleshoot tool calls, and understand credit usage\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Decisional Documentation\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.decisional.com/dashboards-and-usage\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://decisional.mintlify.site/_mintlify/api/og/v2?division=Platform\u0026amp;title=Dashboards+and+Usage\u0026amp;description=Monitor+agent+health%2C+troubleshoot+tool+calls%2C+and+understand+credit+usage\u0026amp;theme=edb213072d477a6d7da28c0b\u0026amp;signature=2faa2cc8a7eeba3f3be4df6136aad780493d0a6fd5e54c3f0a19d5f6bb5cafdf\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Dashboards and Usage - Decisional Documentation\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Monitor agent health, troubleshoot tool calls, and understand credit usage\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://decisional.mintlify.site/_mintlify/api/og/v2?division=Platform\u0026amp;title=Dashboards+and+Usage\u0026amp;description=Monitor+agent+health%2C+troubleshoot+tool+calls%2C+and+understand+credit+usage\u0026amp;theme=edb213072d477a6d7da28c0b\u0026amp;signature=2faa2cc8a7eeba3f3be4df6136aad780493d0a6fd5e54c3f0a19d5f6bb5cafdf\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/decisional/Nia7cnv3ARxO7t21/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Decisional Documentation\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#3E0D77\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.decisional.com/dashboards-and-usage\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/dashboards-and-usage.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.decisional.com/#organization\",\"name\":\"Decisional Documentation\",\"url\":\"https://docs.decisional.com\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/decisional/RETrpsVEIJJtqrl0/logo/light.svg?fit=max\u0026auto=format\u0026n=RETrpsVEIJJtqrl0\u0026q=85\u0026s=9a49e1175b3e00b4d4c78cc0f996761c\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.decisional.com#website\",\"name\":\"Decisional Documentation\",\"url\":\"https://docs.decisional.com\",\"publisher\":{\"@id\":\"https://docs.decisional.com/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.decisional.com/dashboards-and-usage#webpage\",\"url\":\"https://docs.decisional.com/dashboards-and-usage\",\"name\":\"Dashboards and Usage\",\"description\":\"Monitor agent health, troubleshoot tool calls, and understand credit usage\",\"dateModified\":\"2026-07-26T17:53:54.539Z\",\"isPartOf\":{\"@id\":\"https://docs.decisional.com#website\"},\"breadcrumb\":{\"@id\":\"https://docs.decisional.com/dashboards-and-usage#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.decisional.com/dashboards-and-usage#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Decisional Documentation\",\"item\":\"https://docs.decisional.com\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Dashboards and Usage\",\"item\":\"https://docs.decisional.com/dashboards-and-usage\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://docs.decisional.com/dashboards-and-usage#article\",\"headline\":\"Dashboards and Usage\",\"name\":\"Dashboards and Usage\",\"description\":\"Monitor agent health, troubleshoot tool calls, and understand credit usage\",\"url\":\"https://docs.decisional.com/dashboards-and-usage\",\"mainEntityOfPage\":{\"@id\":\"https://docs.decisional.com/dashboards-and-usage#webpage\"},\"dateModified\":\"2026-07-26T17:53:54.539Z\",\"publisher\":{\"@id\":\"https://docs.decisional.com/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.decisional.com#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Decisional Documentation\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Decisional Documentation\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/dashboards-and-usage.md","siteName":"Decisional Documentation","nav":{"global":{"anchors":[{"anchor":"Community","href":"https://discord.gg/DwPDS5Prk2","icon":"discord"},{"anchor":"Blog","href":"https://www.decisional.com/blog","icon":"newspaper"},{"anchor":"Changelog","href":"https://www.decisional.com/changelog","icon":"list"}]},"anchors":[{"anchor":"Documentation","icon":"book-open","groups":[{"group":"Getting Started","pages":[{"title":"Welcome to Decisional","href":"/introduction"},{"title":"Quickstart","href":"/quickstart"},{"title":"Core Concepts","href":"/core-concepts"},{"title":"Setup","href":"/setup"}]},{"group":"Dex","pages":[{"title":"Using Dex","href":"/guides/ai-assistant"}]},{"group":"Agents","pages":[{"title":"Working with Agents","icon":"robot","href":"/guides/agents"},{"title":"Instructions","icon":"file-lines","href":"/agents/instructions"},{"title":"Modes","icon":"comments","href":"/agents/modes"},{"title":"Workflows","icon":"diagram-project","href":"/workflows/overview"},{"title":"Versioning","icon":"code-branch","href":"/agents/versioning"},{"title":"Sources","icon":"files","href":"/agents/sources"},{"title":"Inbox","icon":"inbox","href":"/agents/inbox"},{"title":"State Store","icon":"database","href":"/agents/state-store"},{"title":"Outputs","icon":"box","href":"/agents/outputs"},{"title":"Monitoring Runs","icon":"play","href":"/guides/runs"},{"title":"Approvals and Policy","icon":"shield-check","href":"/agents/approvals"}]},{"group":"Data \u0026 Integrations","pages":[{"title":"Integrations","href":"/integrations"},{"title":"Platform Integrations","href":"/platform-integrations"},{"title":"Custom Integrations","href":"/custom-integrations"},{"title":"Working with Sources","description":"Master document processing, RAG, and context management","href":"/guides/sources"}]},{"group":"Platform","pages":[{"title":"Dashboards and Usage","icon":"chart-line","href":"/dashboards-and-usage"},{"title":"Workspaces","description":"Collaborate with your team and manage access","href":"/guides/workspaces"},{"title":"Credentials","href":"/guides/credentials"},{"title":"Security Policy","icon":"shield-check","href":"/security"}]},{"group":"Reference","pages":[{"title":"Glossary","href":"/reference/glossary"},{"title":"Frequently Asked Questions","href":"/reference/faq"}]}]}]},"basePath":"","title":"Dashboards and Usage - Decisional Documentation","deploymentId":"dpl_HhUetB7eHHDAmK9T1Teip38TgFx9","buildId":"dpl_HhUetB7eHHDAmK9T1Teip38TgFx9","dynamics":["07c022d89b","a74be98ba7","a9bb46feb3"],"chunks":["Frame-DevImLcx.js","DynamicMarkdown-BGHukeRM.js","zoom-image-lightbox-DQG3o8Eu.js","lightbox-handle-r17bVUz3.js","Markdown-Dj-na-_-.js","dist-C5gjFYHe.js","lib-DuNMoZ05.js","lib-B8HbPgcC.js","katex-YMM-FMeD.js","html-void-elements-mCSPHezU.js","marked.esm-CZWythHk.js","AssistantPageLink-DEBW87tT.js"]}