Customer Experience
·
What is a ticketing system, and how do AI agents change how it works? A practical breakdown for operations and CX leaders managing real call and ticket volume.
Aahan Sawhney
CMS article
What Is a Ticketing System and Why It Still Defines Customer Operations
Every support and operations team, regardless of size or industry, eventually runs into the same problem: too many requests arriving through too many channels, with no reliable way to track which ones got resolved, which ones got dropped, and which ones are about to escalate. A ticketing system is the infrastructure that prevents that chaos from compounding.
At its core, a ticketing system is a software platform that converts incoming customer or internal requests into structured records called tickets. Each ticket captures the nature of the issue, the channel it arrived on, the person who submitted it, any actions taken, and the current status. That record persists until the issue is closed, and it creates an audit trail that individual email threads or phone logs simply cannot replicate.
The term gets used interchangeably with help desk software, issue tracking, and support desk platforms, but the underlying mechanics are the same. A ticket is created, assigned, worked, and resolved. Every step is logged.
Why the Ticketing System Became the Backbone of Support Operations
Before digital ticketing, most support teams operated on a combination of shared email inboxes, sticky notes, spreadsheet trackers, and institutional memory. That model worked when support volume was low and teams were small. It stopped working as soon as volume scaled or team turnover introduced knowledge gaps.
The shift toward electronic ticketing systems happened gradually through the late 1990s and early 2000s, as companies like Remedy (later BMC), Zendesk, and Freshdesk brought structured ticket management to broader markets. What made these platforms compelling was not just organization. It was visibility. A manager could now see, at a glance, how many open tickets existed, which agents were carrying the heaviest load, and where SLA deadlines were at risk.
That visibility created accountability. And accountability, over time, created measurable improvements in resolution time and customer satisfaction.
Today, according to the global help desk software market is valued in the billions, with growth driven primarily by the demand for multichannel support, automation, and AI-assisted resolution. The meaning of ticketing has expanded well beyond phone and email. Modern digital ticketing systems handle requests arriving from chat, SMS, social media, self-service portals, and automated systems triggering programmatic alerts.
The Anatomy of a Ticket
Understanding what a ticketing system does requires understanding what a ticket actually contains. A well-structured ticket includes:
Ticket ID: A unique identifier for tracking and referencing
Requester information: Name, contact details, account or customer record
Channel of origin: Phone, email, chat, web form, API, etc.
Issue category: Billing, technical, account access, product question, escalation
Priority level: Often derived from SLA rules tied to customer tier or issue severity
Assigned agent or queue: Where the ticket sits in the workflow
Status: Open, in progress, pending customer response, resolved, closed
Activity log: Every update, note, reply, or status change with timestamps
Resolution notes: What was done to close the issue
This structure is what separates a ticketing system from a simple task manager. The context is customer-facing, the stakes are tied to service commitments, and the record has downstream value for reporting, compliance, and continuous improvement.
The Electronic Ticketing System vs. the Digital Ticketing System
These two terms are often treated as synonyms, and in most modern contexts they effectively are. But there is a subtle distinction worth noting for organizations evaluating platforms.
Electronic ticketing system is the broader, older term. It refers to any software-based system that creates and tracks tickets electronically, as opposed to paper-based logging. It encompasses everything from early ITSM platforms running on-premise servers to modern cloud-based SaaS tools.
Digital ticketing system typically implies a more connected, multichannel, often cloud-native architecture. A digital ticketing system is expected to accept inputs from web forms, mobile apps, APIs, and conversational interfaces, not just email or phone. It is more likely to include native integrations with CRM platforms, knowledge bases, and automation engines.
For practical purposes, any platform a company is evaluating today will be a digital ticketing system. The distinction matters more historically than operationally.
What Ticketing Systems Actually Measure
The value of a ticketing system is not just in creating records. It is in producing data that operations teams can act on. The most commonly tracked metrics include:
First response time (FRT): How long from ticket creation to the first agent reply
Mean time to resolution (MTTR): Average time from ticket open to ticket closed
First contact resolution (FCR): Percentage of tickets resolved without reopening or escalation
SLA compliance rate: How often tickets are resolved within contractually agreed timeframes
Ticket volume by channel: Where requests are coming from, and in what volume
Agent utilization: How many tickets each agent handles, and at what quality level
CSAT score: Post-resolution customer satisfaction ratings, often collected via automated surveys
These metrics matter enormously to operations leaders for a straightforward reason: they are the empirical foundation of staffing decisions, SLA renegotiations, and technology investments. If MTTR is trending upward, something in the workflow is breaking. If FRT is consistently high on one channel, that channel needs attention.
How Ticketing Systems Evolved With Customer Expectations
Customer expectations around support have shifted significantly over the past decade. Customers now expect fast responses regardless of channel. They expect agents to have context about their history without being asked to repeat themselves. They expect issues to be resolved in a single interaction wherever possible.
Those expectations have pushed ticketing systems to evolve in two important directions. First, multichannel unification: the ability to pull tickets from every channel into a single queue, so an agent working a chat conversation can see that the same customer called last week and had their issue partially resolved. Second, automation and intelligent routing: the ability to use rules, AI, or machine learning to assign tickets to the right agent, surface relevant knowledge base articles, and flag high-priority issues before they breach SLA.
This evolution is where AI agents begin to intersect with ticketing systems in meaningful ways, and that intersection is expanding rapidly. The question is no longer whether AI will touch the ticketing workflow. It is how deeply, and through which channels.
A ticketing system creates the record. An AI voice agent can create the ticket itself, qualify the issue, and route it to the right queue, before a human agent ever picks it up.
Why the Meaning of Ticketing Has Expanded Beyond Support
Originally, ticketing systems were almost exclusively a customer support tool. IT helpdesks used them for break-fix requests. Customer service teams used them for billing and product questions. That is still the dominant use case, but the meaning of ticketing has expanded into other operational domains.
HR teams use ticketing systems to manage employee requests, onboarding tasks, and policy inquiries. Legal and compliance teams use them to track contract reviews and regulatory requests. Facilities and operations teams use them to manage maintenance work orders. In financial services, ticketing infrastructure is used to manage client service requests, KYC document submissions, and dispute resolution workflows.
This horizontal expansion of ticketing across business functions has created a new class of requirement: the ability to ingest requests from conversational interfaces, including phone calls, and automatically generate structured tickets without requiring a human to type in the details.
That is the gap where AI voice agents are now sitting. And understanding how they fit requires first understanding how traditional ticketing workflows actually break down under pressure.
How Ticketing Systems Work in Practice, and Where AI Agents Change the Equation
A ticketing system's mechanics are straightforward in theory. In practice, the workflow has a number of pressure points that become visible only at scale. Understanding those pressure points is essential for any operations leader thinking about how AI agents fit alongside, not instead of, their existing ticketing infrastructure.
The Standard Ticketing Workflow
Most ticketing systems follow a version of this lifecycle:
Ticket creation: A customer submits a request via email, web form, phone (transcribed to a ticket by an integration or agent note), chat, or self-service portal. The system assigns a ticket ID and logs the channel, requester, and timestamp.
Categorization and prioritization: Either manually by the receiving agent, or automatically via rules or AI tagging, the ticket is given a category and a priority level.
Routing and assignment: The ticket is routed to the appropriate queue or agent. This can be based on issue type, agent skill set, customer tier, or round-robin logic.
Work and updates: The assigned agent investigates, communicates with the requester, and logs all activity. If collaboration is needed, the ticket can be escalated internally or split into child tickets.
Resolution and closure: Once the issue is resolved, the ticket is marked closed. An automated CSAT survey is typically triggered.
Reporting and analysis: Aggregate ticket data flows into dashboards and reports for operations review.
This lifecycle works well when ticket volume is manageable, agents are available, and the incoming information is structured. It starts to break down when volume spikes, when tickets arrive via voice (inherently unstructured), or when the requester provides incomplete information that requires back-and-forth to clarify.
The Phone Channel Problem
Phone calls are the most challenging input channel for ticketing systems, and they remain one of the highest-volume channels for customer support in regulated industries. Voice remains a primary support channel in financial services, healthcare, and insurance, where customers prefer to call for sensitive or complex issues.
The problem is structural. When a customer calls, the information exchanged is verbal, sequential, and unstructured. To create a useful ticket from that call, an agent must simultaneously listen, resolve, and document. The documentation often happens after the call, from memory, which introduces errors, omissions, and inconsistencies.
Those documentation gaps downstream affect SLA tracking, quality monitoring, and any handoff that happens when a ticket is transferred between agents or teams. If the ticket created from a phone call is incomplete, the next agent inherits incomplete context, and the customer has to repeat themselves.
This is the exact problem that AI voice agents are designed to address.
How AI Voice Agents Interact With Ticketing Systems
An AI voice agent operating on an inbound call can do something a human agent cannot do during a live conversation: maintain perfect, structured documentation in real time. Every piece of information exchanged during the call, the customer's name, account number, issue description, any answers provided, and any actions taken, can be captured in a structured format and written directly into the ticketing system via a CRM or API integration.
This transforms the phone channel from the most documentation-intensive channel into one of the most accurately documented ones.
Beyond documentation, AI voice agents can perform the categorization and prioritization steps that normally require a skilled agent to interpret. By processing what the customer says and matching it to a taxonomy of issue types and priority rules, the agent can route the ticket to the right queue or, where appropriate, resolve it entirely without creating a ticket at all.
For high-volume operations, this matters at scale. If a team receives 500 inbound calls per day and each call currently requires 3 to 5 minutes of post-call documentation, automating that step saves significant agent time every single day.
Fair Comparison: AI-Integrated Ticketing vs. Traditional Workflows
Not every approach to bringing AI into a ticketing workflow is equivalent. There are broadly three models in use today:
Model 1: AI chatbots in front of the ticketing system. A chatbot handles initial contact on web or mobile, attempts self-service resolution, and creates a ticket if it cannot resolve. This model works well for digital channels but does not address the phone channel.
Model 2: Transcription and tagging tools layered on top of calls. Post-call transcription software converts call recordings into text, which is then analyzed and used to update tickets. This is better than manual documentation but still introduces a lag. The ticket is not updated in real time, and if the call is not resolved, the lag delays routing.
Model 3: AI voice agents handling the call itself. Rather than transcribing after the fact, an AI voice agent conducts the intake conversation, performs qualification, creates the ticket with complete structured data in real time, and either resolves the issue, routes to the right queue, or warm-transfers to a human agent with the full ticket context already populated.
Model 3 is the most complete integration. It addresses the phone channel's structural documentation problem at the source, rather than trying to patch it downstream.
Named Competitors and Their Approaches
Several AI voice platforms are positioning themselves in this space, and it is worth being direct about how their approaches differ.
Vapi is the most developer-flexible option in the market. Teams with strong engineering capacity can build custom voice agent integrations with essentially any ticketing system. The trade-off is implementation time and ongoing engineering maintenance. Vapi is the right choice if you want maximum control and have the team to build and maintain the integration layer.
Retell AI sits between developer tool and business platform. It offers more pre-built functionality than Vapi but still requires meaningful technical work to configure integrations with specific ticketing systems at an enterprise level.
Bland AI is built for high-volume outbound calling. For teams that need to push outbound campaigns at volume, it performs well. However, features like warm transfer and scheduling that are critical for inbound support workflows are gated behind an Enterprise tier, which adds cost and negotiation complexity for teams that need those capabilities from day one.
Feather AI is positioned as a business-ready AI agent platform for teams that need a working calling operation live quickly, without assembling a custom stack. Native CRM integrations with Salesforce and HubSpot mean that ticket creation and context passing happen through existing infrastructure, not a custom API layer that requires ongoing maintenance.
The Multichannel Reality
One reality that any serious evaluation of AI and ticketing must acknowledge is that voice is one channel among several. A complete ticketing strategy has to account for the full channel mix: email, chat, SMS, web form, and phone. AI voice agents address the phone channel. They do not replace the ticketing system or the agents working other channels.
The most effective implementations treat AI voice agents as a front-end layer that feeds qualified, structured tickets into the existing ticketing system, where the rest of the support workflow continues normally. This is an additive model, not a replacement model. The ticketing system remains the system of record. The AI voice agent becomes the most consistent, highest-throughput intake mechanism for the phone channel.
For operations teams managing hundreds or thousands of calls per month, this additive model produces compounding returns: better ticket data quality, faster routing, reduced post-call documentation burden, and improved SLA compliance across the board.
The ticketing system is the system of record. The AI voice agent is the most consistent intake mechanism the phone channel has ever had.
What This Means for the Ticketing System Itself
The arrival of AI voice agents in the workflow does not make ticketing systems obsolete. If anything, it makes them more valuable, because the quality and completeness of ticket data improves. Better input data means better reporting, better SLA tracking, and better decision-making about staffing and tooling.
What it does change is the expectation of how tickets from the voice channel get created. In an AI-augmented operation, a ticket should never arrive from a phone call with a vague description like "customer called, had a question." It should arrive with a structured summary, a priority classification, relevant account data attached, and a clear indication of what the next step is.
That shift, from incomplete voice-channel tickets to structured, actionable ones, is one of the most underappreciated operational improvements AI voice agents enable.
Where Ticketing Systems and AI Voice Agents Fall Short: An Honest Assessment
Any technology evaluation that only covers the upside is incomplete. Before committing resources to a ticketing system upgrade or an AI voice agent deployment, operations leaders need a clear-eyed view of where these systems genuinely struggle, where manual processes or simpler tools still outperform them, and where specific platforms fall short for specific use cases.
Where Traditional Ticketing Systems Break Down
High-volume, voice-heavy channels. Most ticketing systems were designed around text-based inputs. Phone calls remain an afterthought in most platforms, handled through manual agent entry or third-party integrations that are fragile and inconsistently maintained. If the majority of your support volume arrives by phone, a ticketing system alone will not solve your documentation or routing problems. It creates a place to log tickets, but does not address the quality or speed of how those tickets are created.
Rigid categorization taxonomy. Ticketing systems rely on predefined categories and fields to structure tickets. When customer issues do not fit neatly into those categories, agents either force-fit the ticket into the wrong category or leave fields blank. Over time, miscategorized tickets corrupt reporting data, making it harder to see where recurring issues are concentrated. Fixing a broken taxonomy is a significant project, and most teams defer it too long.
SLA management without intelligent prioritization. Most ticketing systems apply SLA rules based on static criteria: customer tier, channel, or issue type selected at intake. They do not dynamically adjust priority based on sentiment, urgency signals in the customer's language, or real-time queue depth. This means that a genuinely urgent issue submitted by a customer who selected the wrong category can sit in the wrong queue until it breaches SLA, even though the information to prioritize it correctly was present in the ticket.
Integration maintenance burden. The promise of a digital ticketing system is that it connects to your other tools. In practice, integrations between ticketing systems, CRMs, knowledge bases, and communication platforms require ongoing maintenance. API versions change, authentication tokens expire, and custom integrations built by contractors or internal engineers become liabilities when the people who built them leave.
Reporting that describes the past without informing the present. Standard ticketing dashboards show historical performance. They do not flag that a particular issue type is trending upward in real time, or that a specific agent is showing signs of burnout based on ticket handling patterns. Turning ticketing data into proactive operational intelligence typically requires a separate analytics layer that most teams have not built.
Where AI Voice Agents Genuinely Fall Short
Complex, emotionally charged interactions. AI voice agents perform well on structured intake, qualification, and information retrieval. They do not perform well when a customer is genuinely distressed, when the conversation is highly nonlinear, or when the resolution requires empathy and judgment that goes beyond scripted responses. Attempting to keep an AI voice agent on an escalating call longer than necessary risks making the customer experience worse, not better. Smart deployment means defining clear escalation triggers and having warm transfer to a human agent happen quickly when those triggers are hit.
Low-volume, high-complexity support environments. If your support operation handles relatively few tickets but each one is highly complex (think enterprise software implementation issues or multi-party legal disputes), an AI voice agent adds little value at the intake stage. The operational leverage AI agents provide comes from volume. Low-volume environments see minimal return on the implementation investment.
Environments without clean CRM or knowledge base data. An AI voice agent's ability to give accurate, grounded answers depends on the quality of the knowledge base it is connected to. If your internal documentation is outdated, inconsistent, or sparse, the agent will either give wrong answers or default to unhelpful non-answers. This is not a deficiency of the AI layer in isolation. It is a data quality problem that no AI tool can solve on its own. Teams that deploy AI agents without auditing their knowledge base first typically have a poor initial experience and blame the technology rather than the underlying data.
Teams expecting zero human involvement. AI voice agents are not a complete replacement for human support staff. In regulated industries, many interactions require a licensed professional to complete (a licensed insurance agent for policy changes, a financial advisor for investment recommendations, a nurse or physician for clinical guidance). Deploying an AI agent without clear human handoff protocols in those contexts is not just an operational risk. In some jurisdictions, it is a compliance risk.
Where Specific Platforms Have Real Limitations
Being specific matters here. Platform marketing tends to smooth over the real trade-offs.
Vapi offers the most flexibility in the market, but that flexibility has a cost. Building a production-grade integration between Vapi and a ticketing system like Zendesk or ServiceNow requires significant engineering effort and produces a custom codebase that your team owns and maintains. If you have a strong engineering team and want control over every layer of the stack, Vapi is excellent. If you are an operations leader without dedicated engineering support, Vapi is not designed for you.
Bland AI is optimized for outbound calling at volume. For inbound support workflows, especially ones that require warm transfer to a human agent or appointment scheduling as part of the resolution flow, those capabilities are gated to an Enterprise tier. For teams that need a full inbound support workflow from the start, this creates cost and timeline uncertainty.
Retell AI is a reasonable middle ground but still requires meaningful technical work to configure production-level integrations. It is not a no-code deployment for operations teams without technical support.
Feather AI Has Limits Too
In the interest of a fair assessment, Feather AI is not the right choice for every organization evaluating AI voice agents.
If you want full control over every layer of the voice stack and have the engineering team to build and maintain it, a developer-first platform like Vapi will serve you better. Feather AI is designed for teams that want a working operation quickly, with compliance built in, not for teams that want to build their own infrastructure from scratch.
If your call volume is very low (fewer than a few hundred calls per month), the return on deploying an AI voice agent platform is minimal. The operational leverage that makes AI agents compelling at scale simply does not materialize at low volume.
If you are looking for an instant self-serve signup with no implementation conversation, Feather AI is also not structured that way. Getting a Feather AI deployment right involves a scoping conversation about your workflows, your CRM setup, and your compliance requirements. That process takes time. Teams that need something running entirely on their own without any vendor interaction should look at lighter-weight, self-serve tools.
No AI voice platform eliminates the need for thoughtful workflow design, clean underlying data, and clear escalation protocols. The technology amplifies what is already there. It does not compensate for what is missing.
The Honest Bottom Line
Ticketing systems and AI voice agents are both mature enough to deliver real operational value when deployed correctly. Both are also capable of delivering frustration when deployed against the wrong use case, on top of bad data, or without the operational design work that any serious implementation requires.
The teams that get the most out of this combination are the ones who go in with realistic expectations: AI handles volume, creates structure, and reduces documentation burden. Humans handle complexity, judgment, and relationship-sensitive moments. The ticketing system holds the record for all of it. None of these roles is interchangeable, and none of these tools is optional if you are operating at real scale.
How Feather AI Fits Into Your Ticketing and Voice Operations
Understanding what a ticketing system does and how AI voice agents can improve its inputs is a useful framework. But at some point, the operational question becomes concrete: which platform actually fits the way your organization runs, and what does implementation realistically look like?
This section covers where Feather AI fits into the picture, who it is built for, who it is not, and what the path from evaluation to live deployment looks like.
The Specific Problem Feather AI Solves in a Ticketing Context
Feather AI is an AI voice agent platform designed for businesses that need a working calling operation, inbound and outbound, running quickly, without requiring an internal engineering team to build the underlying stack.
In the context of ticketing and support operations, the specific problems Feather AI addresses are:
1. Voice channel intake that creates structured, complete tickets in real time. Feather AI voice agents can conduct intake conversations on inbound calls, capture all relevant information from the caller, and pass that structured data into your CRM or ticketing system via native integrations with Salesforce and HubSpot. This eliminates the post-call documentation lag and the quality inconsistencies that come with manual agent note-taking.
Rather than a ticket arriving with a vague note, a Feather AI-handled intake produces a ticket with the caller's account ID, issue category, priority signals, and a structured summary of what was discussed and any actions taken. That data quality improvement compounds across every report, every SLA calculation, and every agent handoff downstream.
2. Warm transfer to a human agent with full context attached. When an inbound caller's issue requires human judgment, licensed expertise, or a sensitive escalation, Feather AI's warm transfer capability routes the caller to the right agent and passes the full call context simultaneously. The human agent does not start from scratch. They pick up a conversation that is already qualified, documented, and routed correctly. In support operations, this is the difference between a seamless escalation and a frustrated customer who just repeated themselves to a machine and now has to repeat themselves again to a person.
3. Real-time observability and call quality monitoring. Feather AI includes real-time observability tools that let operations leaders see what is happening on live calls, flag quality issues as they occur, and review structured call data without waiting for a manual audit. For support teams managing SLAs and compliance requirements, this visibility is operationally significant. It makes the voice channel as measurable and manageable as any other channel in the ticketing system.
Who Feather AI Is Built For
Feather AI is the right fit for operations and revenue leaders at regulated or compliance-sensitive businesses who are running real call volume (hundreds or more calls per month) and need a working calling operation without hiring engineers to build it.
Core verticals where Feather AI is purpose-built include financial services, healthcare, and insurance. These are environments where phone remains a primary support channel, where compliance (HIPAA, GDPR, SOC 2) is non-negotiable, and where the quality of call documentation has direct regulatory implications. Feather AI bundles HIPAA, GDPR, and SOC 2 compliance into the standard offering rather than gating it to enterprise pricing tiers.
Beyond core verticals, Feather AI is also relevant for operations teams in telecommunications, retail, travel and hospitality, and technology businesses that have meaningful inbound call volume and want to reduce the documentation burden on human agents without sacrificing ticket quality.
Who Feather AI Is Not the Right Fit For
Being direct about this matters. Feather AI is not designed for:
Solo developers or technical teams who want to assemble a fully custom voice stack with complete control over every component. That is closer to Vapi's audience, and Vapi is genuinely excellent for that use case.
Very low-volume or non-regulated small businesses where the operational leverage of AI agents at scale does not apply and simpler, cheaper tools will do the job.
Buyers expecting instant self-serve signup with no implementation conversation. Getting a Feather AI deployment right involves scoping your workflows, your CRM configuration, and your compliance requirements. That process is an investment, not a barrier, but it is not instant.
What the Implementation Path Looks Like
One of the consistent friction points operations teams face with AI voice agent deployments is the gap between demo and production. Platforms look compelling in a demo environment with clean data and scripted scenarios. They look different when they encounter your actual caller base, your actual CRM schema, and your actual escalation workflows.
Feather AI's approach is to get to production quickly. The platform is designed to go from deployment scoping to a live calling operation in days, not months. Pre-production testing against simulated caller personas means the agent is stress-tested against realistic call scenarios before it takes a live call. This reduces the risk of a go-live that immediately surfaces edge cases your team did not anticipate.
Persistent memory across calls means that a caller who has interacted with a Feather AI agent before is recognized. Their history is available. The agent does not treat every call as the first. In a support context, this is directly relevant to ticket continuity: a caller following up on an open ticket does not have to re-explain their situation.
For teams with more complex or custom workflow requirements, the Agent SDK allows engineering teams to build beyond the no-code dashboard without starting from scratch. This is not a trade-off between flexibility and speed. It is a spectrum that accommodates both the operations leader who wants a working deployment quickly and the technical team that wants to extend it over time.
Closing: The Ticketing System and the Voice Channel, Finally Integrated
The meaning of ticketing has always been about creating a reliable record of every customer interaction, one that persists, can be acted on, and feeds into better operational decisions over time. The phone channel has historically been the weakest link in that record-keeping infrastructure, not because the interactions were less important, but because voice is inherently hard to structure.
AI voice agents change that. They bring the phone channel into the same structured, measurable, auditable framework that email and chat have operated in for years. The ticketing system becomes a more complete picture of customer interactions. SLA tracking becomes more accurate. Agents inherit better context. Reports reflect reality more closely.
For organizations running serious call volume in regulated industries, this is not a marginal improvement. It is a structural one. And it is available now, not as a future roadmap item.
If you are evaluating whether an AI voice agent layer makes sense for your support and ticketing operations, the most direct next step is a conversation about your specific workflows, volumes, and compliance requirements.
![](data:image/svg+xml,<svg display="block" role="presentation" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M 16 7.999 L 16 0 L 0 0 L 0 7.999 Z M 16 16 C 13.878 15.999 11.843 16.842 10.343 18.342 C 8.842 19.842 7.999 21.877 7.999 23.999 L 0.001 23.999 L 0.001 23.794 C 0.11 15.086 7.176 8.054 15.896 8 L 24 8 L 24 24 L 16 24 Z" fill="rgba(255, 255, 255, 0.03)" height="24px" id="lngUwvl9j" width="24.0000007312145px"/></svg>)