Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.
Overview
Tracing gives you full visibility into what happened during a test call or live call. It’s one of the most powerful features for making your voice agents production-ready.With traces, you can see:
The exact conversation that occurred
What prompts were sent to the LLM
Which tools the LLM had access to (and which it called)
Speech-to-text transcriptions of user input and Transcription errors
Tool call requests and responses
Accessing Traces
Open a call from the agent’s runs and select the Trace tab. It lists the call in order: user speech, agent replies, node transitions, tool calls and pipeline errors. Agent replies show their latency, and you can expand one to see the time spent in each stage.For prompt-level detail, connect your own Langfuse project (see Setting Up Langfuse Tracing). The Trace tab then shows Open external trace, which opens the full trace for that call in Langfuse.
Understanding Trace Sections
In a Langfuse trace, entries are organized by event type. The two most important sections to focus on are:
STT (Speech-to-Text)
These entries capture the transcription of what the user said during the call. Each STT entry shows the text conversion of the user’s speech at that point in the conversation.Example:STT: “Yeah, I would want to check what your operating hours are.”
LLM (Language Model Calls)
These entries show every call made to the LLM. Each LLM trace includes:
Prompt - The full prompt sent to the LLM (combination of global prompt + node-specific prompt)
Conversation history - The entire conversation up to that point
Available tools - All tools the LLM can access for that node
Response - What the LLM generated
Tools in Traces
Each LLM call shows the tools available to the agent at that moment. These fall into three categories:
System Tools (Default)
Every node includes these by default:
Safe Calculator – Helps LLMs perform math accurately
Get Current Time – Retrieves current time
Convert Time – Converts time to a specific timezone
Pathway Tools
These correspond to the pathways (node transitions) you’ve configured. For example, if your node has pathways to “End Call” and “Move to Summary,” you’ll see those as available tools.The tool descriptions shown in traces match the descriptions you set in your pathway configuration.
Custom Tools
Any external tools you’ve attached to the node (e.g. any custom tools you created for API endpoints for booking, order submission, etc.) will appear here. See the custom tools documentation.
Tool Calls in Traces
When the LLM decides to call a tool, you’ll see:
Tool call request – The tool name and parameters sent
Tool response – The result returned (e.g., {"status": "ok"})
The tool call and response also appear in subsequent conversation history, so the LLM knows the outcome.Example flow:User: “Can you book me a table for tomorrow at 7pm?”LLM calls: book_table(date: “tomorrow”, time: “7pm”, party_size: 2)Tool response:{"status": "done", "confirmation": "Table booked"}Agent: “I’ve booked your table for tomorrow at 7pm.”
How Prompts Are Combined
The prompt sent to the LLM is a combination of:
Global Prompt – Defined in your Global Node settings
Node Prompt – Defined in the specific node being executed
If you disable the Global Node for a particular node, only the node-specific prompt will be used.
Key Concept: Conversation History
Every time an LLM call is made, the entire conversation history up to that point is passed to the LLM. This means:
The LLM always has full context
You can see exactly what context the LLM had when it made a decision
Useful for debugging unexpected responses
Setting Up Langfuse Tracing
Langfuse is an LLM observability platform. It stores and visualizes traces (prompts, responses, tool calls) so you can debug and iterate on LLM-powered applications outside of Bananaflow’s own trace viewer.You can send traces to your own Langfuse account. This enables you to use the playground feature of Langfuse.Setup steps:
In Bananaflow, go to Settings, open the Telemetry tab, and enter your Langfuse host, public key, and secret key under Tracing
Click Save
Once enabled, traces will be available for every completed call in Bananaflow.
Trace visibility
Traces sent to your own Langfuse project are private by default – opening a trace link requires access to that project. Make traces publicly viewable in the same Tracing section turns that off for your project only.
A public trace is readable by anyone holding its URL, with no Langfuse login, and it exposes the full call transcript, prompts, and tool payloads. Only enable it if you intend to share trace links outside your Langfuse project.
Quick Reference
Trace Type
What It Shows
STT
User speech transcribed to text
LLM
Prompt + conversation + tools + response
Tool Call
Tool invocation and response
Tips for Using Traces
Debug unexpected responses – Check the LLM trace to see what prompt and context the model received
Verify tool calls – Confirm tools are being triggered with correct parameters
Refine prompts – Use traces to see how your prompt instructions affect LLM behavior
Check transcription accuracy – Review STT entries if the agent misunderstands users
Was this page helpful?
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Bananaflow AI","colors":{"primary":"#005FF2","light":"#47A8FF","dark":"#006BFF"},"logo":{"light":"https://mintcdn.com/bananaflow/QToRpsLnU_h_dyEA/logo/light.svg?fit=max\u0026auto=format\u0026n=QToRpsLnU_h_dyEA\u0026q=85\u0026s=16eaca83b45b3d48fab505183cc83d18","dark":"https://mintcdn.com/bananaflow/QToRpsLnU_h_dyEA/logo/dark.svg?fit=max\u0026auto=format\u0026n=QToRpsLnU_h_dyEA\u0026q=85\u0026s=c70540e1512228f948877331660736fa","href":"https://docs.bananaflow.ai"},"favicon":"https://mintcdn.com/bananaflow/QToRpsLnU_h_dyEA/favicon.ico?fit=max\u0026auto=format\u0026n=QToRpsLnU_h_dyEA\u0026q=85\u0026s=998044cc570de2b8c619d278cbfb334b","api":{"openapi":"api-reference/openapi.json"},"background":{"color":{"light":"#FAFAFA","dark":"#000000"}},"navbar":{"links":[{"href":"mailto:hello@bananaflow.ai","label":"Support"}],"primary":{"type":"button","label":"Dashboard","href":"https://app.bananaflow.ai"}},"footer":{"socials":{"linkedin":"https://linkedin.com/company/bananaflow"}},"search":{"prompt":"Search for Tools, Webhooks, Telephony, etc..."},"fonts":{"family":"Geist"},"banner":{"content":"🎉 **New: MCP Server** – Connect Claude, Cursor, and other AI assistants to your Bananaflow workspace. [Set it up →](/integrations/mcp)","dismissible":true},"contextual":{"options":["copy","view","chatgpt","claude","perplexity","mcp","cursor","vscode"],"display":"header"},"styling":{"latex":false},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"bananaflow","hasAudioNarration":false,"actualSubdomain":"bananaflow","customDomains":["docs.bananaflow.ai"],"gitSource":{"type":"github","owner":"timetracker-developer","repo":"bananaflow-web","deployBranch":"main","contentDirectory":"docs","isPrivate":true,"mountPath":"","label":""},"feedback":{"thumbs":true},"entitlements":{"AI_CHAT":{"status":"DISABLED"},"WEB_MCP":{"status":"DISABLED"},"NARRATION":{"status":"DISABLED"}},"buildId":"6b0046b9cba301bc987935f0","clientVersion":"0.0.4270","searchFilterCounts":[{"language":"default","tag":"Guides","count":63},{"language":"default","tag":"API Reference","count":51},{"language":"default","tag":"Resources","count":48},{"language":"default","tag":"Voice Agent Builder","count":21},{"language":"default","tag":"Telephony Configurations","count":14},{"language":"default","tag":"Telephony","count":14},{"language":"default","tag":"Agents","count":12},{"language":"default","tag":"Campaigns","count":11},{"language":"default","tag":"Runs","count":9},{"language":"default","tag":"Nodes","count":8}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"site-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"starter-pricing","enabled":true,"variant":{"name":"control","enabled":true,"payload":{"type":"string","value":"control"},"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"wildcard-email-auth","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":true},"customCss":[{"filePath":"custom.css","content":":root{--bf-border: #ebebeb;--bf-border-hover: #c9c9c9}html.dark{--bf-border: #2e2e2e;--bf-border-hover: #454545}[data-search-button],.search-button,[aria-label*=\"search\"],[placeholder*=\"Search\"],button[data-testid*=\"search\"],.mintlify-search,.DocSearch-Button{border:1px solid var(--bf-border)!important;border-radius:6px!important;box-shadow:none!important;transition:border-color 0.15s ease!important}[data-search-button]:hover,.search-button:hover,[aria-label*=\"search\"]:hover,[placeholder*=\"Search\"]:hover,button[data-testid*=\"search\"]:hover,.mintlify-search:hover,.DocSearch-Button:hover{border-color:var(--bf-border-hover)!important}"}]}
{"page":{"pagePath":"configurations/tracing","slug":"/configurations/tracing","pageMetadata":{"title":"Tracing","description":"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.","href":"/configurations/tracing"},"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: \"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\"\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={a:`a`,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},{Heading,OptimizedImage,Table,Warning}=_components;if(!Heading)_missingMdxReference(`Heading`,true);if(!OptimizedImage)_missingMdxReference(`OptimizedImage`,true);if(!Table)_missingMdxReference(`Table`,true);if(!Warning)_missingMdxReference(`Warning`,true);return _jsxs(_Fragment,{children:[_jsx(Heading,{level:`2`,id:`overview`,children:`Overview`}),`\n`,_jsx(_components.p,{children:`Tracing gives you full visibility into what happened during a test call or live call. It’s one of the most powerful features for making your voice agents production-ready.`}),`\n`,_jsx(_components.p,{children:`With traces, you can see:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`The exact conversation that occurred`}),`\n`,_jsx(_components.li,{children:`What prompts were sent to the LLM`}),`\n`,_jsx(_components.li,{children:`Which tools the LLM had access to (and which it called)`}),`\n`,_jsx(_components.li,{children:`Speech-to-text transcriptions of user input and Transcription errors`}),`\n`,_jsx(_components.li,{children:`Tool call requests and responses`}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`accessing-traces`,children:`Accessing Traces`}),`\n`,_jsxs(_components.p,{children:[`Open a call from the agent’s runs and select the `,_jsx(_components.strong,{children:`Trace`}),` tab. It lists the call in order: user speech, agent replies, node transitions, tool calls and pipeline errors. Agent replies show their latency, and you can expand one to see the time spent in each stage.`]}),`\n`,_jsxs(_components.p,{children:[`For prompt-level detail, connect your own Langfuse project (see `,_jsx(_components.a,{href:`#setting-up-langfuse-tracing`,children:`Setting Up Langfuse Tracing`}),`). The `,_jsx(_components.strong,{children:`Trace`}),` tab then shows `,_jsx(_components.strong,{children:`Open external trace`}),`, which opens the full trace for that call in Langfuse.`]}),`\n`,_jsx(Heading,{level:`2`,id:`understanding-trace-sections`,children:`Understanding Trace Sections`}),`\n`,_jsx(_components.p,{children:`In a Langfuse trace, entries are organized by event type. The two most important sections to focus on are:`}),`\n`,_jsx(Heading,{level:`3`,id:`stt-speech-to-text`,children:`STT (Speech-to-Text)`}),`\n`,_jsx(_components.p,{children:`These entries capture the transcription of what the user said during the call. Each STT entry shows the text conversion of the user’s speech at that point in the conversation.`}),`\n`,_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),`\n`,_jsx(_components.p,{children:`STT: “Yeah, I would want to check what your operating hours are.”`}),`\n`,_jsx(Heading,{level:`3`,id:`llm-language-model-calls`,children:`LLM (Language Model Calls)`}),`\n`,_jsx(_components.p,{children:`These entries show every call made to the LLM. Each LLM trace includes:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Prompt`}),` - The full prompt sent to the LLM (combination of global prompt + node-specific prompt)`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Conversation history`}),` - The entire conversation up to that point`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Available tools`}),` - All tools the LLM can access for that node`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Response`}),` - What the LLM generated`]}),`\n`]}),`\n`,_jsx(OptimizedImage,{src:`https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=4d06b9534d36fe0e733650472c1b332b`,alt:`LLM Response`,\"data-og-width\":`1600`,width:`1600`,\"data-og-height\":`769`,height:`769`,\"data-path\":`images/llm-response.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=280\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=245cbcc31f1745f4a8ad37966bc5c293 280w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=560\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=eb1d8a16b393c2f6a23c4479eaa398d3 560w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=840\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=8e0c319bc82d235f8feb9db00c167a8a 840w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=1100\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=4c95dcc92e367a83cf4b1986163c04f2 1100w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=1650\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=5f490c4203af63575b9eddbb7d4656ee 1650w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/llm-response.png?w=2500\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=03cd330dff40e00f4af7954fe13c6dd0 2500w`}),`\n`,_jsx(OptimizedImage,{src:`https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=bd7803f527009a7d3d04062f4b3f8f99`,alt:`Conversation History`,\"data-og-width\":`1600`,width:`1600`,\"data-og-height\":`927`,height:`927`,\"data-path\":`images/conversation-history.png`,\"data-optimize\":`true`,\"data-opv\":`3`,srcset:`https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=280\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=f3c5cf6a2d8b33ee92b95071e2603a19 280w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=560\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=e9559360c75e7332cfd349584e173173 560w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=840\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=6e514094f2bc747796b667b939e6a7e4 840w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=1100\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=77ce7d326143e8d812c262f876608025 1100w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=1650\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=35bfaaca944b289a5f62117c65396b41 1650w, https://mintcdn.com/bananaflow/LmrVrjbPuArTFghQ/images/conversation-history.png?w=2500\u0026fit=max\u0026auto=format\u0026n=LmrVrjbPuArTFghQ\u0026q=85\u0026s=bb1d0b21285d45dcba34c905b5852414 2500w`}),`\n`,_jsx(Heading,{level:`2`,id:`tools-in-traces`,children:`Tools in Traces`}),`\n`,_jsx(_components.p,{children:`Each LLM call shows the tools available to the agent at that moment. These fall into three categories:`}),`\n`,_jsx(Heading,{level:`3`,id:`system-tools-default`,children:`System Tools (Default)`}),`\n`,_jsx(_components.p,{children:`Every node includes these by default:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Safe Calculator`}),` – Helps LLMs perform math accurately`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Get Current Time`}),` – Retrieves current time`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Convert Time`}),` – Converts time to a specific timezone`]}),`\n`]}),`\n`,_jsx(Heading,{level:`3`,id:`pathway-tools`,children:`Pathway Tools`}),`\n`,_jsx(_components.p,{children:`These correspond to the pathways (node transitions) you’ve configured. For example, if your node has pathways to “End Call” and “Move to Summary,” you’ll see those as available tools.`}),`\n`,_jsx(_components.p,{children:`The tool descriptions shown in traces match the descriptions you set in your pathway configuration.`}),`\n`,_jsx(Heading,{level:`3`,id:`custom-tools`,children:`Custom Tools`}),`\n`,_jsxs(_components.p,{children:[`Any external tools you’ve attached to the node (e.g. any custom tools you created for API endpoints for booking, order submission, etc.) will appear here. See the `,_jsx(_components.a,{href:`/voice-agent/tools/http-api`,children:`custom tools documentation`}),`.`]}),`\n`,_jsx(Heading,{level:`2`,id:`tool-calls-in-traces`,children:`Tool Calls in Traces`}),`\n`,_jsx(_components.p,{children:`When the LLM decides to call a tool, you’ll see:`}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Tool call request`}),` – The tool name and parameters sent`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Tool response`}),` – The result returned (e.g., `,_jsx(_components.code,{children:`{\"status\": \"ok\"}`}),`)`]}),`\n`]}),`\n`,_jsx(_components.p,{children:`The tool call and response also appear in subsequent conversation history, so the LLM knows the outcome.`}),`\n`,_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example flow:`})}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`User:`}),` “Can you book me a table for tomorrow at 7pm?”`]}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`LLM calls:`}),` book_table(date: “tomorrow”, time: “7pm”, party_size: 2)`]}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Tool response:`}),` `,_jsx(_components.code,{children:`{\"status\": \"done\", \"confirmation\": \"Table booked\"}`})]}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Agent:`}),` “I’ve booked your table for tomorrow at 7pm.”`]}),`\n`,_jsx(Heading,{level:`2`,id:`how-prompts-are-combined`,children:`How Prompts Are Combined`}),`\n`,_jsx(_components.p,{children:`The prompt sent to the LLM is a combination of:`}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Global Prompt`}),` – Defined in your Global Node settings`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Node Prompt`}),` – Defined in the specific node being executed`]}),`\n`]}),`\n`,_jsx(_components.p,{children:`If you disable the Global Node for a particular node, only the node-specific prompt will be used.`}),`\n`,_jsx(Heading,{level:`2`,id:`key-concept-conversation-history`,children:`Key Concept: Conversation History`}),`\n`,_jsxs(_components.p,{children:[`Every time an LLM call is made, the `,_jsx(_components.strong,{children:`entire conversation history up to that point`}),` is passed to the LLM. This means:`]}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`The LLM always has full context`}),`\n`,_jsx(_components.li,{children:`You can see exactly what context the LLM had when it made a decision`}),`\n`,_jsx(_components.li,{children:`Useful for debugging unexpected responses`}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`setting-up-langfuse-tracing`,children:`Setting Up Langfuse Tracing`}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.a,{href:`https://langfuse.com/docs`,children:`Langfuse`}),` is an LLM observability platform. It stores and visualizes traces (prompts, responses, tool calls) so you can debug and iterate on LLM-powered applications outside of Bananaflow’s own trace viewer.`]}),`\n`,_jsxs(_components.p,{children:[`You can send traces to your own Langfuse account. This enables you to use the `,_jsx(_components.a,{href:`https://langfuse.com/docs/prompt-management/features/playground`,children:`playground feature of Langfuse`}),`.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.strong,{children:`Setup steps:`})}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[`Sign up at `,_jsx(_components.a,{href:`https://langfuse.com`,children:`Langfuse`}),` and create API credentials`]}),`\n`,_jsxs(_components.li,{children:[`In Bananaflow, go to `,_jsx(_components.strong,{children:`Settings`}),`, open the `,_jsx(_components.strong,{children:`Telemetry`}),` tab, and enter your Langfuse host, public key, and secret key under `,_jsx(_components.strong,{children:`Tracing`})]}),`\n`,_jsxs(_components.li,{children:[`Click `,_jsx(_components.strong,{children:`Save`})]}),`\n`]}),`\n`,_jsx(_components.p,{children:`Once enabled, traces will be available for every completed call in Bananaflow.`}),`\n`,_jsx(Heading,{level:`3`,id:`trace-visibility`,children:`Trace visibility`}),`\n`,_jsxs(_components.p,{children:[`Traces sent to your own Langfuse project are private by default – opening a trace link requires access to that project. `,_jsx(_components.strong,{children:`Make traces publicly viewable`}),` in the same `,_jsx(_components.strong,{children:`Tracing`}),` section turns that off for your project only.`]}),`\n`,_jsx(Warning,{children:_jsx(_components.p,{children:`A public trace is readable by anyone holding its URL, with no Langfuse login, and it exposes the full call transcript, prompts, and tool payloads. Only enable it if you intend to share trace links outside your Langfuse project.`})}),`\n`,_jsx(Heading,{level:`2`,id:`quick-reference`,children:`Quick Reference`}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Trace Type`}),_jsx(_components.th,{children:`What It Shows`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`STT`}),_jsx(_components.td,{children:`User speech transcribed to text`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`LLM`}),_jsx(_components.td,{children:`Prompt + conversation + tools + response`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool Call`}),_jsx(_components.td,{children:`Tool invocation and response`})]})]})]}),`\n`,_jsx(Heading,{level:`2`,id:`tips-for-using-traces`,children:`Tips for Using Traces`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Debug unexpected responses`}),` – Check the LLM trace to see what prompt and context the model received`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Verify tool calls`}),` – Confirm tools are being triggered with correct parameters`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Refine prompts`}),` – Use traces to see how your prompt instructions affect LLM behavior`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Check transcription accuracy`}),` – Review STT entries if the agent misunderstands users`]}),`\n`]})]})}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":"Tracing","description":"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.","href":"/configurations/tracing"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"Overview","slug":"overview","depth":2,"children":[]},{"title":"Accessing Traces","slug":"accessing-traces","depth":2,"children":[]},{"title":"Understanding Trace Sections","slug":"understanding-trace-sections","depth":2,"children":[{"title":"STT (Speech-to-Text)","slug":"stt-speech-to-text","depth":3,"children":[]},{"title":"LLM (Language Model Calls)","slug":"llm-language-model-calls","depth":3,"children":[]}]},{"title":"Tools in Traces","slug":"tools-in-traces","depth":2,"children":[{"title":"System Tools (Default)","slug":"system-tools-default","depth":3,"children":[]},{"title":"Pathway Tools","slug":"pathway-tools","depth":3,"children":[]},{"title":"Custom Tools","slug":"custom-tools","depth":3,"children":[]}]},{"title":"Tool Calls in Traces","slug":"tool-calls-in-traces","depth":2,"children":[]},{"title":"How Prompts Are Combined","slug":"how-prompts-are-combined","depth":2,"children":[]},{"title":"Key Concept: Conversation History","slug":"key-concept-conversation-history","depth":2,"children":[]},{"title":"Setting Up Langfuse Tracing","slug":"setting-up-langfuse-tracing","depth":2,"children":[{"title":"Trace visibility","slug":"trace-visibility","depth":3,"children":[]}]},{"title":"Quick Reference","slug":"quick-reference","depth":2,"children":[]},{"title":"Tips for Using Traces","slug":"tips-for-using-traces","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":["/_mintlify/custom/bananaflow/52439f9c58f0d520/custom.js"],"subdomain":"bananaflow","siteName":"Bananaflow AI","title":"Tracing - Bananaflow AI","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-11-20T13:10:25.167Z","originalFileLocation":"configurations/tracing.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=\"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\">\u003cmeta data-mint-head name=\"application-name\" content=\"Bananaflow AI\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_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/bananaflow/rHG5sOcjOga6o5Go/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Tracing - Bananaflow AI\">\u003cmeta data-mint-head property=\"og:description\" content=\"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Bananaflow AI\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.bananaflow.ai/configurations/tracing\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://bananaflow.mintlify.site/_mintlify/api/og/v2?division=Configurations\u0026amp;title=Tracing\u0026amp;description=Trace+your+agent+runs+to+debug+issues%2C+understand+LLM+behavior%2C+and+refine+your+prompts.\u0026amp;theme=8b9525ec21bc986a63e24cda\u0026amp;signature=c345127a3cf4df862f46daa4f826c15a57fb99cb4bdb89a07e6555e5509f4c27\">\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=\"Tracing - Bananaflow AI\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://bananaflow.mintlify.site/_mintlify/api/og/v2?division=Configurations\u0026amp;title=Tracing\u0026amp;description=Trace+your+agent+runs+to+debug+issues%2C+understand+LLM+behavior%2C+and+refine+your+prompts.\u0026amp;theme=8b9525ec21bc986a63e24cda\u0026amp;signature=c345127a3cf4df862f46daa4f826c15a57fb99cb4bdb89a07e6555e5509f4c27\">\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/bananaflow/rHG5sOcjOga6o5Go/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Bananaflow AI\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#005FF2\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.bananaflow.ai/configurations/tracing\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/configurations/tracing.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.bananaflow.ai/#organization\",\"name\":\"Bananaflow AI\",\"url\":\"https://docs.bananaflow.ai\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/bananaflow/QToRpsLnU_h_dyEA/logo/light.svg?fit=max\u0026auto=format\u0026n=QToRpsLnU_h_dyEA\u0026q=85\u0026s=16eaca83b45b3d48fab505183cc83d18\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.bananaflow.ai#website\",\"name\":\"Bananaflow AI\",\"url\":\"https://docs.bananaflow.ai\",\"publisher\":{\"@id\":\"https://docs.bananaflow.ai/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.bananaflow.ai/configurations/tracing#webpage\",\"url\":\"https://docs.bananaflow.ai/configurations/tracing\",\"name\":\"Tracing\",\"description\":\"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\",\"dateModified\":\"2026-11-20T13:10:25.167Z\",\"isPartOf\":{\"@id\":\"https://docs.bananaflow.ai#website\"},\"breadcrumb\":{\"@id\":\"https://docs.bananaflow.ai/configurations/tracing#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.bananaflow.ai/configurations/tracing#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Configurations\",\"item\":\"https://docs.bananaflow.ai/configurations/voice\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Tracing\",\"item\":\"https://docs.bananaflow.ai/configurations/tracing\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://docs.bananaflow.ai/configurations/tracing#article\",\"headline\":\"Tracing\",\"name\":\"Tracing\",\"description\":\"Trace your agent runs to debug issues, understand LLM behavior, and refine your prompts.\",\"url\":\"https://docs.bananaflow.ai/configurations/tracing\",\"mainEntityOfPage\":{\"@id\":\"https://docs.bananaflow.ai/configurations/tracing#webpage\"},\"dateModified\":\"2026-11-20T13:10:25.167Z\",\"publisher\":{\"@id\":\"https://docs.bananaflow.ai/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.bananaflow.ai#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Bananaflow AI\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Bananaflow AI\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/configurations/tracing.md","siteName":"Bananaflow AI","nav":{"global":null,"tabs":[{"tab":"Guides","icon":"book-open","groups":[{"group":"Getting started","pages":[{"group":"Introduction","pages":[{"title":"Introduction","href":"/getting-started"}]}]},{"group":"Build your First Agent","pages":[{"title":"Your First Agent in 5 Minutes","href":"/getting-started/first-agent"},{"title":"Trigger Calls using API","href":"/getting-started/trigger-calls-from-your-backend"},{"title":"Sync Data using Webhook","href":"/getting-started/send-call-data-with-webhooks"},{"title":"Connect with Telephony","href":"/getting-started/connect-telephony"},{"title":"Use External Tools, Knowledge","href":"/getting-started/add-tools-and-knowledge-base"}]},{"group":"Core Concepts","pages":[{"title":"How Bananaflow Works","href":"/core-concepts/how-bananaflow-works"},{"title":"Workflows \u0026 Agents","href":"/core-concepts/workflows-and-agents"},{"title":"Calls \u0026 Runs","href":"/core-concepts/calls-and-runs"},{"title":"Context \u0026 Variables","href":"/core-concepts/context-and-variables"},{"title":"Campaigns","sidebarTitle":"Campaigns (Bulk Outbound Calls)","href":"/core-concepts/campaigns"}]},{"group":"Billing","pages":[{"title":"Billing Overview","href":"/billing/overview"},{"title":"Credit and Recharge","href":"/billing/credit-and-recharge"},{"title":"What You Are Charged For","href":"/billing/charges-and-low-balance"}]},{"group":"Configurations","pages":[{"title":"Voice","href":"/configurations/voice"},{"title":"API Keys","href":"/configurations/api-keys"},{"title":"Agent UUID","href":"/configurations/agent-uuid"},{"title":"Interruptions and Turn-Taking","href":"/configurations/interruption"},{"title":"Unfinished Sentences","description":"Before the agent replies, Bananaflow checks whether the caller has really finished. If they stopped mid-sentence or are still thinking, the agent waits instead of cutting in.","href":"/configurations/unfinished-sentences"},{"title":"Tracing","href":"/configurations/tracing"},{"title":"Call events","description":"Export per-call diagnostics to your organization's BigQuery table.","href":"/configurations/call-events"}]},{"group":"Voice Agent Builder","pages":[{"title":"Voice Agent Builder","href":"/voice-agent/introduction"},{"title":"Editing a Workflow","href":"/voice-agent/editing-a-workflow"},{"title":"Pre-recorded Audio","href":"/voice-agent/pre-recorded-audio"},{"title":"Template Variables","href":"/voice-agent/template-variables"},{"title":"Pre-Call Data Fetch","href":"/voice-agent/pre-call-data-fetch"},{"group":"Tools","pages":[{"title":"Tools","href":"/voice-agent/tools/introduction"},{"group":"Built-in Tools","pages":[{"title":"Call Transfer","href":"/voice-agent/tools/call-transfer"},{"title":"Transfer to Agent","href":"/voice-agent/tools/transfer-agent"},{"title":"End Call","href":"/voice-agent/tools/end-call"}]},{"group":"Custom Tools","pages":[{"title":"HTTP API","href":"/voice-agent/tools/http-api"},{"title":"MCP Tool","href":"/voice-agent/tools/mcp-tool"}]}]},{"title":"Knowledge Base","href":"/voice-agent/knowledge-base"},{"group":"Nodes","pages":[{"title":"Start Call","href":"/voice-agent/start-call"},{"title":"End Call","href":"/voice-agent/end-call"},{"title":"Agent Node","href":"/voice-agent/agent"},{"title":"Global Node","href":"/voice-agent/global"},{"title":"QA","href":"/voice-agent/qa"},{"title":"Evals","href":"/voice-agent/evals"},{"title":"API Trigger","href":"/voice-agent/api-trigger"},{"title":"Webhook","href":"/voice-agent/webhook"}]},{"title":"Add to Website","tag":"NEW","href":"/voice-agent/add-to-website"}]},{"group":"Telephony","pages":[{"title":"Telephony Integration","href":"/integrations/telephony/overview"},{"title":"Inbound Calling","href":"/integrations/telephony/inbound"},{"title":"Twilio Integration","href":"/integrations/telephony/twilio"},{"title":"Vonage Integration","href":"/integrations/telephony/vonage"},{"title":"Plivo Integration","href":"/integrations/telephony/plivo"},{"title":"Telnyx Integration","href":"/integrations/telephony/telnyx"},{"title":"Cloudonix Integration","href":"/integrations/telephony/cloudonix"},{"title":"Exotel Integration","href":"/integrations/telephony/exotel"},{"title":"Vobiz Integration","href":"/integrations/telephony/vobiz"},{"title":"WhatsApp Integration","href":"/integrations/telephony/whatsapp"},{"title":"Asterisk ARI Integration","href":"/integrations/telephony/asterisk-ari"},{"title":"VICIdial Integration","href":"/integrations/telephony/vicidial"},{"title":"Webhooks and Callbacks","href":"/integrations/telephony/webhooks"},{"title":"Agent Stream","href":"/integrations/telephony/agent-stream"}]},{"group":"Integrations","tag":"NEW","pages":[{"title":"MCP Server","href":"/integrations/mcp"},{"title":"Tuner Integration","href":"/integrations/tuner"},{"title":"Paygent Integration","href":"/integrations/paygent"},{"title":"Noveum Integration","href":"/integrations/noveum"}]}]},{"tab":"Developer","icon":"code","pages":[{"title":"Developer","href":"/developer/workflow-schema"}]},{"tab":"API Reference","icon":"square-terminal","pages":[{"title":"API Reference","href":"/api-reference/api-keys"}]}]},"basePath":"","title":"Tracing - Bananaflow AI","deploymentId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","buildId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","dynamics":["10e4515597","a74be98ba7"],"chunks":["BannerMarkdown-BOAJk9BH.js","dist-Dl6_zDnT.js","lib-DMeTj1gb.js","lib-B8HbPgcC.js","katex-Dbtb6Wk7.js","html-void-elements-mCSPHezU.js","marked.esm-CZWythHk.js","zoom-image-lightbox-BQ4tbj_9.js","lightbox-handle-r17bVUz3.js"]}