> Markdown rendition of https://www.voiceflow.com/platform/prism ("Prism | Voiceflow"). Canonical page: https://www.voiceflow.com/platform/prism · All pages: https://www.voiceflow.com/llms.txt

Prism

# See what happened. Know what to improve.

Connect service metrics, evaluations, transcripts and logs in Voiceflow. Trace outcomes to individual conversations and see where to improve your agents.

[Get started](https://creator.voiceflow.com/start)

[Talk to sales](https://www.voiceflow.com/demo)

## Better customer experiences, at scale.

**Trusted by 3,000+** customers, with **1 billion+** agent messages processed.

> “Voiceflow takes the pain out of building powerful conversational experiences in a group setting.”

> “There’s only one real tool that gets the job done for me and that’s Voiceflow.”

[“The engineering experience was smooth — we could quickly move from a workflow designed by Voiceflow to one that we owned and could refactor ourselves.”](https://www.voiceflow.com/stories/how-turo-built-chatbot-in-two-months)

**

[45%**Offer-to-leadrate](https://www.voiceflow.com/stories/how-sanlam-studios-ai-coach-drives-leads-and-financial-literacy)

> “Voiceflow is the A-Z of learning and executing on AI Automation.”

**

[Under 12 weeks**From concept to live deployment“It allowed us to rapidly iterate on conversational flows and reduce dependency on engineers.”](https://www.voiceflow.com/stories/stubhub-internationals-90-day-journey)

> “With Voiceflow, it’s much easier to navigate our designs and test conversations.”

**

[70%**AI resolutionrate](https://www.voiceflow.com/stories/automating-60-of-customer-support-for-90-products-in-12-weeks-how-ai-automation-transformed-trilogy)

> “With Voiceflow we're building interactive prototypes as we design. This is the dream.”

> “Voiceflow takes the pain out of building powerful conversational experiences in a group setting.”

> “There’s only one real tool that gets the job done for me and that’s Voiceflow.”

[“The engineering experience was smooth — we could quickly move from a workflow designed by Voiceflow to one that we owned and could refactor ourselves.”](https://www.voiceflow.com/stories/how-turo-built-chatbot-in-two-months)

**

[45%**Offer-to-leadrate](https://www.voiceflow.com/stories/how-sanlam-studios-ai-coach-drives-leads-and-financial-literacy)

> “Voiceflow is the A-Z of learning and executing on AI Automation.”

**

[Under 12 weeks**From concept to live deployment“It allowed us to rapidly iterate on conversational flows and reduce dependency on engineers.”](https://www.voiceflow.com/stories/stubhub-internationals-90-day-journey)

> “With Voiceflow, it’s much easier to navigate our designs and test conversations.”

**

[70%**AI resolutionrate](https://www.voiceflow.com/stories/automating-60-of-customer-support-for-90-products-in-12-weeks-how-ai-automation-transformed-trilogy)

> “With Voiceflow we're building interactive prototypes as we design. This is the dream.”

> “Voiceflow takes the pain out of building powerful conversational experiences in a group setting.”

> “There’s only one real tool that gets the job done for me and that’s Voiceflow.”

[“The engineering experience was smooth — we could quickly move from a workflow designed by Voiceflow to one that we owned and could refactor ourselves.”](https://www.voiceflow.com/stories/how-turo-built-chatbot-in-two-months)

**

[45%**Offer-to-leadrate](https://www.voiceflow.com/stories/how-sanlam-studios-ai-coach-drives-leads-and-financial-literacy)

> “Voiceflow is the A-Z of learning and executing on AI Automation.”

**

[Under 12 weeks**From concept to live deployment“It allowed us to rapidly iterate on conversational flows and reduce dependency on engineers.”](https://www.voiceflow.com/stories/stubhub-internationals-90-day-journey)

> “With Voiceflow, it’s much easier to navigate our designs and test conversations.”

**

[70%**AI resolutionrate](https://www.voiceflow.com/stories/automating-60-of-customer-support-for-90-products-in-12-weeks-how-ai-automation-transformed-trilogy)

> “With Voiceflow we're building interactive prototypes as we design. This is the dream.”

## Go from the big picture to the details.

Track performance, assess quality and inspect the conversations that need attention.

AnalyticsEvaluationsTranscriptsLogs

## Understand how your agent performs.

Bring usage, quality and operational metrics into one view.

Monitor conversation volume

Track conversation volume over time to see how demand for your agent is changing.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/analytics)

Inspect playbook usage

See which playbooks customers use most, so you can prioritize improvements to the busiest journeys.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/analytics)

Filter by environment

Focus the dashboard on the environment you want to assess, keeping development and live usage in context.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/analytics#filtering-your-view)

Choose the reporting period

Set a date range to investigate a launch, a busy week or the period after a change.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/analytics#filtering-your-view)

## Make quality measurable.

Score conversations against explicit criteria and inspect the results.

Review outcomes over time

Follow evaluation results and compare the individual conversations behind them.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/evaluations#viewing-evaluation-results)

Inspect the criteria

Define what the evaluation should judge, with explicit criteria and descriptions for the lowest and highest scores.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/evaluations#understanding-evaluations)

Test the criteria first

Run an evaluation on an existing transcript to check how it scores a real conversation before relying on the metric.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/evaluations#creating-an-evaluation)

Open the underlying results

Use the individual results to investigate where your agent needs attention.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/evaluations#viewing-evaluation-results)

## Follow the conversation, turn by turn.

Inspect what the customer asked, how the agent responded and how the exchange was evaluated.

Find the right conversations

Filter by date, environment, user or evaluation to find the exchanges that need a closer look.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#filtering-transcripts)

Read the exchange

Review the complete conversation, including the agent’s messages and interactive responses.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Understand the score

Read an evaluation result alongside its reasoning to understand the score.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Keep the context

Use date, user and cost metadata to place a conversation in context.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

## See what happened behind the answer.

Trace tool calls, inspect their data and diagnose the exact step that needs attention.

Follow the execution sequence

Read timestamped inputs, outputs and tool events to understand the steps behind a customer conversation.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Inspect the tool inputs

Open a tool call to verify the values the agent sent, such as the order ID and refund amount.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Check the returned result

Inspect the tool response to confirm the action completed and see the result the agent received.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Narrow the investigation

Search logs or filter their levels to isolate the events relevant to the issue you are debugging.

[Learn more](https://www.voiceflow.com/docs/documentation/measure/transcripts#reviewing-individual-transcripts)

Feature highlights

## See the outcome. Trace what happened.

Measure how conversations resolve, then inspect the steps and tool calls behind them. Keep customer outcomes and execution details in one place.

### **Resolution analytics** show conversation outcomes

![Creator resolution analytics with an illustrative 84% resolution rate, up 12.0% versus the previous period, and a donut with 840 resolved conversations, 120 handed to the team, and 40 unresolved. A demonstration cursor moves between the donut segments, showing their counts and percentages.](https://www.voiceflow.com/images/platform-overview-v2/analytics-detail.png)

### **Agent logs** reveal the actions behind each conversation

Build together

## Give every team a clearer view of service quality.

Use shared evidence to align investigation, prioritization and business decisions.

SupportCX DesignProductEngineeringQALeadership

### **Support** turns missed resolutions into better guidance.

Find recurring questions and failed handoffs in Prism’s transcripts. Bring those findings into Studio’s playbooks to improve the next conversation.

Playbooks

### **CX Design** sees where conversations lose their way.

Read transcripts alongside evaluation reasoning in Prism. Use that evidence to refine instructions, tone and conversation paths in Studio.

Agent Studio

![Pine customer guide prompt with rich headings, voice principles, guardrails, and example dialogue in Voiceflow](https://www.voiceflow.com/images/team-workflow/cx-design-main.png)

### **Product** turns evidence into a plan.

Use Prism’s findings to choose the next improvement. Atlas can help investigate the conversations behind it.

Atlas

### **Engineering** traces failures to their source.

Inspect tool inputs, outputs and warnings in Prism’s logs. Fix the underlying function or integration in Studio with the conversation as evidence.

Functions

### **QA** investigates quality gaps.

Filter transcripts and review evaluation reasoning to identify the behavior that needs to change.

Transcripts

![Voiceflow transcripts table with resolution, quality, policy compliance, and sentiment evaluations for illustrative customer support conversations](https://www.voiceflow.com/images/team-workflow/qa-main.png)

### **Leadership** follows service outcomes.

Review resolution, usage and cost trends to guide the team’s priorities.

Analytics

![Creator Leadership workspace with fictional Pine support data](https://www.voiceflow.com/images/team-workflow/leadership-main.png)

Developer capabilities

## Put conversation evidence to work in your stack.

Use documented APIs and CLI commands to query analytics and work with transcripts and evaluations.

Onboard agent Set up Voiceflow by following https://www.voiceflow.com/agents/setup

[Docs](https://www.voiceflow.com/docs/api-reference/analytics-api/overview)

### **Analytics queries** fit your reporting workflow

![Claude](https://www.voiceflow.com/docs/images/icons/claude.svg)![Codex](https://www.voiceflow.com/docs/images/icons/open-ai.svg)![Cursor](https://www.voiceflow.com/docs/images/icons/cursor.svg)![Visual Studio Code](https://www.voiceflow.com/images/vscode.svg)

Voiceflow CLI

$`vf project list`

Customer support

$`vf environment list -p "$PROJECT_ID"`

Main · Staging

$`vf playbook list -p "$PROJECT_ID" -e Main`

Order support · Returns & refunds

$

### **Evaluation APIs** connect quality checks to your tools

Returned result`{ "order_status": "shipped", "tracking_url": "…/track/1042" }`

Customer stories

## Better customer experiences, at scale.

See the customer outcomes teams achieve with Voiceflow, from faster resolution to better service.

←→

[70% AI resolution rate.Read story →](https://www.voiceflow.com/stories/automating-60-of-customer-support-for-90-products-in-12-weeks-how-ai-automation-transformed-trilogy)

[![eSnipe](https://www.voiceflow.com/images/esnipe-cover-logo.png)70% help center tickets automated.Read story →](https://www.voiceflow.com/stories/how-esnipe-automated-70-of-their-help-center-tickets-with-an-ai-powered-search-agent)

[82% bot satisfaction.Read story →](https://www.voiceflow.com/stories/how-turo-built-chatbot-in-two-months)

[45% offer-to-lead conversion.Read story →](https://www.voiceflow.com/stories/how-sanlam-studios-ai-coach-drives-leads-and-financial-literacy)

[30 support hours saved per week.Read story →](https://www.voiceflow.com/stories/how-roam-saved-30-hours-a-week-in-customer-support-hours)

[30% project time saved.Read story →](https://www.voiceflow.com/stories/flowcharts-to-voiceflow-how-wooliesx-reinvented-their-conversation-design-workflow)

[![BMW](https://www.voiceflow.com/images/bmw-cover-logo-v2.svg)50% reduction in prototyping time.Read story →](https://www.voiceflow.com/stories/how-bmw-reduced-prototyping-time-of-their-in-car-voice-apps-by-50)

[90 days from idea to launch.Read story →](https://www.voiceflow.com/stories/stubhub-internationals-90-day-journey)

[How Rocket Mortgage Accelerated their Team’s Conversation Design WorkflowRead story →](https://www.voiceflow.com/stories/how-rocket-mortgage-accelerated-their-teams-conversation-design-workflow)

[How Chase Uses Voiceflow to Run More Efficient, Inclusive Conversational AI Design ReviewsRead story →](https://www.voiceflow.com/stories/using-voiceflow-to-run-more-efficient-inclusive-ai-design-reviews)

FAQ

## Frequently asked questions

**How is Prism different from Rehearsal?**

Prism helps you understand production conversations through analytics, evaluations, transcripts and logs. Rehearsal tests expected behavior through simulated conversations before you release a change.

**Can I define my own quality metrics?**

Yes. Evaluations support rating, binary, options and text results. Choose a model and write criteria that describe what to assess.

**Can I evaluate older conversations?**

Enabled evaluations run on new transcripts. Select historical transcripts and use Batch run evaluation to apply them retrospectively.

**Are estimated savings actual measured savings?**

The Time saved and Dollars saved widgets use estimates you supply for each automated conversation. Review those assumptions when interpreting the totals.

## Explore the platform

###

[![Studio](https://www.voiceflow.com/og/products/studio.png)StudioBuild and edit AI agents together, with deep control over how they work.Explore Studio](https://www.voiceflow.com/platform/studio)

###

[![Atlas](https://www.voiceflow.com/og/products/atlas.png)AtlasMeet Atlas, your copilot for building and improving AI agents.Explore Atlas](https://www.voiceflow.com/platform/atlas)

###

[![Rehearsal](https://www.voiceflow.com/og/products/rehearsal.png)RehearsalTest agent behavior with AI simulations and automated checks.Explore Rehearsal](https://www.voiceflow.com/platform/rehearsal)
