The call detail page is where you inspect everything about one call: the full transcript, the recording, who ended it, how the bot performed, what the post-call analysis and quality-control (QC) steps concluded, and how much the call cost in tokens. Open it by clicking any row on the Call list, or go directly to /dashboard/calls/[id]. The page is laid out in three columns:

Left — call summary

The key facts about the call (duration, status, direction, who ended it, caller and carrier) plus the latency and token summaries.

Middle — recording & transcript

The audio player and the full interleaved transcript of what was said and done.

Right — analysis

Integration log, tool calls, knowledge retrieval, post-call analysis, QC analysis, and the per-turn metrics table.

Top-bar buttons

These two buttons sit at the top of the page.
ButtonWhat happens when you click
BackReturns you to the page you came from (usually the Call list).
Download JSONDownloads the complete raw call record as a .json file. The button is disabled while a download is already in progress.
Download JSON is only available in the admin view. It is hidden for calls-only users and on the agent console. The file is the full underlying call document — every field, event, and metric — which is useful when you need to share an exact, unedited record with support or attach it to a ticket.

Left column — call summary

The left column lists the headline facts about the call.
FieldWhat it tells you
DurationHow long the call lasted, shown as Xm Ys (for example 2m 15s).
StatusThe call’s final status as a badge (see Status badge). A Test badge appears next to it if this was a test call.
DirectionOutbound or Inbound. Only shown when the call has a recorded direction.
Disconnected ByWho or what ended the call (see Who ended the call).
CallerThe caller’s phone number.
Carrier / DIDThe carrier name and the number the call used (the DID). Only shown when at least one of these is known.

Status badge

BadgeMeaning
completed (green)The call finished normally.
Other status (grey)Any other status the call ended in (for example failed, voicemail, no_answer) is shown in grey.
Test (grey)This was a test call, not a real customer call. Appears alongside the status.

Who ended the call

The Disconnected By field records who or what hung up. The common values you will see:
ValueMeaning
botThe bot ended the call — it reached a natural close, said its closing line, or detected dead air.
customerThe customer hung up.
voicemailThe call reached a voicemail / answering machine.
RNRThe line connected but the customer stayed silent the whole call (Ring No Response).
timeoutThe call ran past its maximum allowed duration.
errorThe call failed to start or hit an unexpected problem.
no_answerThe number rang out and was never answered.
rejectedThe call was actively rejected by the other end.
This is the raw reason the call ended. The friendlier, business-facing outcome is the disposition, which you will find in the Post-call analysis section.

Latency

The Latency card is a grid of average response times across the whole call, in milliseconds. Lower is better — these tell you whether the bot felt snappy or laggy to the customer.
MetricWhat it measures
Avg STTAverage time the Speech-to-Text engine took to turn the customer’s speech into text.
Avg LLMAverage time the language model (LLM) took to decide what to say next.
Avg RAGAverage time spent looking up knowledge-base answers (only relevant if the bot uses a knowledge base).
Avg ToolAverage time spent running the bot’s tools / integrations.
Avg TTSAverage time the voice / Text-to-Speech (TTS) engine took to start speaking.
TotalThe combined average round-trip time, highlighted. This is the closest single number to “how long the customer waited for a reply.”
These are the engine types, not vendor names, by design. A high Total points to where the delay is: a large Avg LLM or Avg TTS usually explains a sluggish-feeling call.

Tokens

The Tokens card summarizes how much language-model work the call consumed. It drives the call’s cost.
MetricWhat it tells you
PromptTokens sent into the language model during the live conversation.
CompletionTokens the language model generated in reply.
TTS CharsNumber of characters spoken by the voice engine.
Post+QCTokens used by the post-call analysis and QC steps after the call ended.
The Tokens card is hidden for calls-only users.

Post-call cache

This card only appears when post-call caching produced data for the call (and it is hidden for calls-only users). It shows how much of the post-call analysis reused a cached prompt instead of being sent fresh — which is what lowers the cost of analysis.
DetailWhat it tells you
Cache status badgeWhether the post-call cache was used for this call.
Cached Read (tok)Tokens that were read from the cache instead of being re-sent.
Cache Created (tok)Tokens written into the cache by this call.
Fresh Prompt (tok)Tokens that had to be sent fresh because they were not cached.
Completion (tok)Tokens the model generated for the analysis.
Post-call caching is configured per bot. See the Post-Call Cache controls on the Bot detail page.

Middle column — recording and transcript

Recording

The Recording card is an audio player with the standard browser controls: play, pause, a scrub bar, volume, and a download option in the player’s own menu. Use it to listen back to the exact conversation.
If a call has no recording (for example a call that failed before connecting), the player will have nothing to play.

Transcript

The Transcript is the full, time-ordered record of the call. It interleaves three kinds of entries, sorted by when they happened:
EntryIconWhat it shows
MessagesEach thing the bot and the customer said, with a timestamp.
Tool callsWrenchWhen the bot ran a tool or integration mid-call, including its result.
Knowledge searchesSearchWhen the bot looked something up in its knowledge base.
Reading the transcript top to bottom lets you follow exactly how the conversation unfolded and see where the bot paused to call a tool or fetch an answer. The same tool and knowledge entries are also broken out in their own cards in the right column.

Right column — analysis

The right column holds the diagnostic and outcome sections. Most are expanded by default; Events starts collapsed. Each section header can be clicked to collapse or expand it.

Integration log

Shows the integration activity for the call — for example any post-call data pushed to your CRM — so you can confirm the call’s result was sent on and see whether it succeeded.

Tool calls

A breakdown of every tool the bot ran during the call. For each tool you see:
DetailWhat it tells you
Function nameWhich tool / integration was called.
StatusThe outcome: ok, error, or timeout.
DurationHow long the tool took to respond.
An error or timeout here often explains an awkward moment in the transcript — the bot was waiting on a tool that did not answer in time.

Knowledge retrieval

Shows each time the bot searched its knowledge base. For each search you see:
DetailWhat it tells you
QueryWhat the bot searched for.
Hit countHow many matching passages were found.
Latency breakdownHow long the lookup took.
Cache statusWhether the answer was served from cache.

Post-call analysis

The post-call analysis is the structured outcome produced after the call by the bot’s analysis prompt. Its fields are shown as key-value pairs, and disposition fields are highlighted as badges. This is where you read the business outcome of the call — for example whether the customer agreed, declined, or asked for a callback — rather than the raw technical reason the line dropped.
The exact fields depend on each bot’s analysis prompt. A call that skipped analysis (for example a very short call or one where the customer never spoke) shows an auto-assigned disposition instead. The full catalog of analysis and disposition fields is in Post-call variables.

QC analysis

The QC (quality-control) analysis is a second structured review produced by the bot’s QC prompt — for example whether the bot followed the script, stayed compliant, or missed a required step. Like the analysis section, its fields render as key-value pairs.
QC only appears for bots that have a QC prompt configured.

Per-turn metrics

A table breaking the call down turn by turn so you can pinpoint exactly which exchange was slow.
ColumnWhat it shows
TurnThe turn number in the conversation.
STTSpeech-to-Text time for that turn (ms).
RAGKnowledge-lookup time for that turn (ms).
ToolTool-call time for that turn (ms).
LLMLanguage-model time for that turn (ms).
TTSVoice-engine time for that turn (ms).
TotalThe total response time for that turn (ms).
TokensTokens used on that turn.
The Tokens column is hidden for calls-only users.

Events

The Events section is collapsed by default. Expand it to see the low-level lifecycle events the backend recorded during the call. This is mostly useful when you are diagnosing an unusual call alongside support.

Banners and notifications

Depending on what happened, one or more banners appear at the top of the call detail.
BannerWhen it appearsWhat it tells you
Transferred → targetThe call was successfully transferred.The destination it was transferred to and the time of transfer.
Transfer attempted but failedA transfer was tried but did not connect.Shown in red, with the reason the transfer failed.
Transferred to human agentThe call was handed to a human agent.Confirms a human takeover.
Transferred from bot call — View bot callYou are viewing the leg of a call that came from a bot transfer.A link back to the original bot call.

Service errors

If the backend recorded any service errors during the call, a Service Errors section lists them. Each entry shows:
DetailWhat it tells you
Service name badgeWhich part of the pipeline reported the error (for example the Speech-to-Text engine, language model, or voice engine — shown generically).
ProcessorThe stage where the error occurred.
TimestampWhen the error happened during the call.
FATAL labelShown when the error was fatal — meaning it likely ended or broke the call rather than being a recoverable hiccup.
A FATAL service error usually means the call broke part-way through (for example the voice engine stopped responding). If you see repeated fatal errors across many calls for one bot, raise it with support — it points to a pipeline problem rather than a one-off.

Call list

Browse, filter, and search all calls, then click into any of them.

Post-call variables

The full catalog of disposition, analysis, and QC fields you see on this page.