> ## Documentation Index > Fetch the complete documentation index at: https://docs.vortexiq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Crisp on Vortex IQ > Monitor Crisp pipeline, responsiveness and customer-satisfaction signals, and catch stalls before they become churn. Monitor Crisp pipeline, responsiveness and customer-satisfaction signals, and catch stalls before they become churn. [Connect or manage this source](https://app.vortexiq.ai/workbench/settings/sources) · [How connecting works](/integrations/connector-catalogue) · [Create a workflow](https://app.vortexiq.ai/workbench/flows/create?connector=crisp) performance signals automated checks automated fixes workflows API operations ### What you can achieve Capabilities are grouped around merchant outcomes, not API terminology. Find failures, leaks and risks before they cost sales. Monitor orders, fulfilment, delivery and settlement. Find storefront, speed, accessibility and journey problems. Improve discovery, conversion, campaigns and repeat purchase. ### From connection to verified outcome The controlled sequence every capability follows. Nothing changes a connected system without the approval step. Authorise the source. Scopes are shown before access is granted. Watch the signals against your own baselines, not universal defaults. Run checks and gather evidence specific to your store. Explain what happened, why it matters and the proposed action. You review scope, risk and reversibility before anything changes. Apply through governed connector operations. Confirm the intended result and keep the receipt. No changes are made without the configured approval policy. Read-only operations do not modify the connected system; schedules, access scopes, API usage and data handling remain governed by Vortex IQ controls. ### Monitor performance 24 performance signals. Open an outcome to see its signals and how each one alerts. Read-only operations do not modify the connected system. | Signal | Alert behaviour | What it tracks | | ----------------------------------- | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Avg Cycle Time (days)** | Alert band 3 / 7 | Mean days from first-response (work started) to resolved - how long active work takes. | | **Avg Lead Time (days)** | Alert band 5 / 14 | Mean days from created\_at to resolved\_at - total time in the system including queue wait. | | **Avg Time-to-Fix (days)** | Alert band 3 / 14 | Mean days from finding created\_at to resolved\_at over the window. | | **Backlog by Priority** | Alert band 25 / 50 | Open conversations split by priority segment - is the queue top-heavy with urgent work? | | **Backlog by Status** | Merchant rule | Open conversations split by state (pending / unresolved) - the shape of the working inbox. | | **Blocked Tickets** | Alert band 0 / 8 | Open conversations tagged blocked/waiting - cannot progress until an external dependency clears. Warn 3 / critical 8. | | **Cycle Time by Priority** | Alert band 2 / 5 | Mean cycle time bucketed by priority - are urgent items actually moving faster? | | **Finding Resolution Rate (90d)** | Alert band 75 / 50 | resolved\_in\_90d / created\_in\_90d x 100. Is the team fixing what Vortex IQ surfaces, or is the audit just noise? | | **First Response Time (min)** | Alert band 30 / 240 | Crisp's own 'First Response Time' Analytics metric (POST /website/{website_id}/analytics/generate, confirmed real route per the official Go SDK's rout | | **In Progress** | Merchant rule | Conversations in unresolved state with an operator assigned - being handled right now. | | **Oldest Open (days)** | Alert band 14 / 90 | Age in days of the oldest still-open conversation - the maximum-age outlier. | | **Open Tickets** | Alert band 50 / 200 | Every unresolved Crisp conversation (customer chat + findings) - the whole open inbox. | | **Overloaded Assignees (>10 open)** | Alert band 0 / 1 | Count of operators carrying more than 10 open conversations - redistribution signal. | | **Scope Added Mid-Sprint** | Alert band 5 / 15 | % of findings added after the sprint started - work preempting committed audit follow-up. | | **Sprint Progress** | Alert band 90 / 70 | % of the current sprint committed findings resolved against time elapsed - burn-down health. | | **Sprint Velocity (avg)** | Alert band 0 / 20 | Findings resolved per sprint, averaged over the last 5 sprints - capacity trend. | | **Tickets Resolved (7d)** | Alert band 0 / 25 | Conversations moved to resolved in the last 7 days vs the prior 7 - weekly outflow. | | **Tickets by Assignee** | Alert band 5 / 10 | Open conversations per operator - where the work is concentrated. | | **Unassigned Tickets** | Alert band 0 / 20 | Open conversations with no operator assigned - nobody owns these. Warn 5 / critical 20. | | **VortexIQ Findings In Progress** | Merchant rule | Findings in unresolved state with an assigned operator - actively being worked. | | **VortexIQ Findings Open** | Alert band 5 / 20 | Crisp conversations tagged vortexiq:finding in pending/unresolved state - open audit work the team has not closed. | | **VortexIQ Findings Resolved** | Merchant rule | Findings moved to resolved state in the trailing 90 days - the raw outflow count behind resolution rate. | | Signal | Alert behaviour | What it tracks | | ----------------------------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- | | **Abandoned Findings (>14d no movement)** | Alert band 0 / 5 | Findings with no agent activity in 14 days - quietly losing money while everyone assumes they are in the queue. | | Signal | Alert behaviour | What it tracks | | -------------------- | --------------- | -------------------------------------------------------------------------------------- | | **Throughput Trend** | Merchant rule | Daily resolved-count sparkline over 30 days - is the team speeding up or slowing down? | ### Audit risks and opportunities A fix status appears only where the action, inputs, approval, verification and recovery controls are mapped. Candidate remediations are never executable. Open a check for the detail. **Severity** high · **Outcome** Grow revenue · **Fix status** Report only CSAT below 70 percent predicts churn before it shows in revenue; the transcripts behind the score say exactly what to fix. Vortex IQ detects and explains this; resolution is manual, with evidence and recommended steps. Reference: `SUPPORT-CSAT-001` **Severity** medium · **Outcome** Protect revenue · **Fix status** Report only Customers are waiting a median of over 4 hours just to hear back for the first time, before their actual issue is even addressed. Slow first response is one of the most common drivers of a bad support experience and of customers escalating, cancelling an order, or leaving a negative review while the Vortex IQ detects and explains this; resolution is manual, with evidence and recommended steps. Reference: `SUPPORT-FRT-001` **Severity** medium · **Outcome** Run operations · **Fix status** Report only The open-conversation backlog grew more than 20% in a week. A growing backlog means response and resolution times for everyone in the queue are about to get worse, not just the customers who are waiting today; the problem compounds until incoming volume and resolution capacity come back into balance Vortex IQ detects and explains this; resolution is manual, with evidence and recommended steps. Reference: `SUPPORT-BACKLOG-001` #### Build your own automated fixes Turn any finding into an automated fix with a Vortex IQ workflow: **over 13,000 read and write operations across more than 200 connectors** are available as building blocks, with approval, verification and rollback on every change. ### Automate approved work Vortex IQ is integrated with **5 read** and **4 write** operations across websites, websiteanalyticsgenerates, websiteconversations, websiteconversationmessages, websiteconversationmetas, websiteconversationroutings on Crisp. Combine them with anything from the **over 13,000 operations across more than 200 connectors** to automate the work in your own words. Changes follow your configured approval policy: the target, proposed change, affected records, risk, reversibility and verification plan are shown before execution. [Create a workflow](https://app.vortexiq.ai/workbench/flows/create?connector=crisp) #### Ready to build your first Crisp workflow Pick a trigger, add the operations above as steps, and every step that changes data pauses for your approval. Monitoring and audits are live now and can start any workflow you build. | Resource | Read operations | Write operations | | --------------------------- | --------------- | ---------------- | | websites | 1 | 0 | | websiteanalyticsgenerates | 0 | 1 | | websiteconversations | 1 | 0 | | websiteconversationmessages | 1 | 0 | | websiteconversationmetas | 1 | 0 | | websiteconversationroutings | 0 | 1 | | websiteconversationsegments | 0 | 1 | | websiteconversationstates | 0 | 1 | Signed-in users see the full catalogue in the workflow builder, filtered to the sources they have connected.