Requests arrive everywhere
Email, WhatsApp, calls and forms each have their own owner, and customers ask twice because nobody can see the first request.
Every channel files into one governed ticket queue with the whole conversation attached.
QuipCRM · Service CRM & Agentic Support
Every request, every reply, every SLA — in one workspace.
An end-to-end support desk built for Indian businesses. The ticket workspace, the governance that makes a promise measurable — categories, SLAs, escalation, routing — and QuipAI, which deflects the routine questions, drafts the replies for the rest, and hands over to a human the moment it is not sure.
- 32Modules
- 15AI modules (7 in-ticket + 8 agentic)
- 4SLA tiers
- 4Escalation levels
- 9Notification events
Service DeskHarbour LineToday
LiveIllustrative
Illustrative service desk board: open tickets with SLA countdowns, deflection rate and a ticket volume trend.
18+3
Open
2
Breaching
64%+4%
Deflected by AI
4.7+0.2
CSAT
Queue · by SLA6 shown
ARhighRefund not received for #HL-87508m
DMmediumWrong add-on charged at checkout34m
PNhighBoarding pass QR not scanning3m
RSlowReschedule request — 08:00 sailing112m
MIhighPayment failed, amount deducted15m
SAlowInvoice needs GST number added140m
Tickets · 8 days↓ 12% vs last week
Agent Assist3 replies drafted
4 capability areas · 32 modules
Everything Service CRM covers, at a glance
01
Service Desk
One screen per ticket: the queue, the whole conversation, and the AI that reads both.
- Ticket Workspace
- Queues, Folders & Tags
- Ticket Record
- Conversation Thread
- Ticket Actions
- Reply, Email & WhatsApp
- Attachments
- Self-Service Intake
- Sandbox Demo Mode
Governance & Service Levels
The promises you make to the business, written down once and enforced by the system.
- Categories & Sub-categories
- System Tags
- SLA Policies
- Escalation Matrix
- Assignment Rules
- Notification Matrix
- Business Hours
- General Settings
QuipAI in the Ticket
The intelligence layer, one column wide, on every ticket an agent opens.
- Agent Assistant
- Knowledge Base
- Requester Chat Assistant
- Activity Log
- AI Insights
- Conversation Trend
- Collapsible AI Rail
Agentic AI & Analytics
The control plane for autonomous resolution, and the numbers that justify widening it.
- Command Centre
- Live Monitor
- AI Setup & Guardrails
- AI Performance
- Agent Hub
- Ticket Deflection
- Ticketing Dashboard
- SLA & Agent Analytics
Why it matters
Where the work usually falls through
SLAs exist only on paper
Response targets are agreed with the business, but nothing measures them until a customer escalates to someone senior.
Category and severity set the SLA tier at creation, and escalation fires off the clock.
Agents answer the same question all day
Routine questions fill the queue, and every agent searches the help centre separately for the same answer.
QuipAI answers from the knowledge base first and drafts the reply for the rest.
01 · Service Desk
9 modulesEverything an agent needs, on one screen
One screen per ticket: the queue, the whole conversation, and the AI that reads both.
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
01
Ticket Workspace
Queue, conversation and AI in one screen — no tab switching
- Three panes: the queue on the left, the ticket and its whole conversation in the middle, QuipAI on the right
- Status, priority, folder and tags sit on the ticket header, with the details that decide what happens next underneath
- Assign, re-prioritise, escalate or process a refund without leaving the ticket
02
Queues, Folders & Tags
The inbox organised the way the team already works
- Tickets filtered by queue, folder and status alongside a live search
- System tags carry the cross-cutting labels reporting actually uses
- Filters persist per agent so the working queue stays consistent shift to shift
03
Ticket Record
Every field that decides what happens next, on the ticket
- Customer, order/reference id, category, severity, region and assignment on one record
- Additional details (order value, environment, delivery slot and similar) captured per category
- The record is what routing, SLA and escalation all read from — nothing lives off to the side
04
Conversation Thread
The whole exchange, inbound and outbound, in order
- Every inbound and outbound message shown chronologically with sender and channel
- Outbound replies clearly marked so the agent always knows what the customer has seen
- The thread is what QuipAI and the knowledge base read to ground their suggestions
05
Ticket Actions
Assign, re-prioritise, escalate or refund without leaving the ticket
- Quick actions for assignment, priority change and escalation on the ticket toolbar
- Refunds and other case-specific actions available inline, with a confirmation step
- Every action writes to the activity log automatically
06
Reply, Email & WhatsApp
Answer in the thread or on the customer's own channel
- Reply inline in the ticket thread, or send by email or WhatsApp from the same screen
- Assignment and channel choice shown together before sending
- Every outbound reply, whichever channel, lands back on the same ticket record
07
Attachments
Evidence attached to the record and previewed in place
- Files attached to a ticket are previewed without leaving the record
- Attachments stay linked to the specific message or action that produced them
- Used for proof of delivery, damage photos, signed confirmations and similar evidence
08
Self-Service Intake
The requester finds the answer before it becomes a ticket
- Requester picks a department and sees the matching knowledge base first
- A ticket is only filed if the existing answer does not resolve it
- Department selection also seeds the category the ticket is created with
09
Sandbox Demo Mode
Evaluate on a switchable dataset before any data moves
- A demo toggle switches the desk onto a sandbox dataset for evaluation
- Lets a prospect or new team try the full workspace before any real data is connected
- The same toggle is what the pitch-kit screenshots were captured against
02 · Governance & Service Levels
8 modulesService levels the system enforces, not just records
The promises you make to the business, written down once and enforced by the system.
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
app.quipcom.ai
01
Categories & Sub-categories
One taxonomy the whole company files against
- A shared category and sub-category tree used across every desk
- Category chosen at intake is what drives SLA tier and routing
- Keeps reporting comparable across teams instead of each desk inventing its own labels
02
System Tags
The cross-cutting labels your reporting actually uses
- Tags apply across categories rather than being tied to one taxonomy branch
- Used to mark things like urgency or theme that cut across the category tree
- Filterable in the queue and usable as a routing or reporting dimension
03
SLA Policies
Four tiers, response and resolution, with the clock rules
- Four SLA tiers, each with its own response and resolution targets
- Tiers are assigned by category and severity at ticket creation
- The SLA clock is what the escalation matrix and business hours setting both key off
04
Escalation Matrix
Four levels, triggered by the SLA rather than by memory
- Four escalation levels, each with its own notified role
- Escalation fires automatically off the SLA clock, not off someone remembering
- Team Lead is the first escalation level in the role model
05
Assignment Rules
Round-robin, load-balanced, skill-based or manual — with capacity
- Four assignment strategies: round-robin, load-balanced, skill-based or manual
- Agent capacity is visible while a strategy is being chosen or a ticket assigned
- Strategy can be set per queue rather than one rule for the whole desk
06
Notification Matrix
Nine events across email, push and Slack, per recipient role
- Nine distinct events (assignment, escalation, SLA breach and similar) each configurable
- Each event can notify by email, push or Slack, per recipient role
- Keeps requesters, agents and managers informed without a fixed one-size template
07
Business Hours
The SLA clock stops when the office does
- Business hours defined per desk, so the SLA clock only runs while the team is working
- Prevents an overnight or weekend gap from silently breaching a response target
- Feeds directly into SLA policy and escalation timing
08
General Settings
ID format, auto-close, CSAT, attachments, reopen window
- Ticket ID format, auto-close timing and the reopen window are all configurable
- CSAT survey and attachment rules set here apply desk-wide
- One settings surface rather than scattered configuration per feature
03 · QuipAI in the Ticket
7 modulesAI that has already read the ticket
The intelligence layer, one column wide, on every ticket an agent opens.
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — A ticket with the QuipAI rail drafting a reply
Agent Assistant SearchAR
HL-2041 · Refund not receivedHigh · SLA 8m
MI
I cancelled booking HL-8750 on Monday and the refund still hasn't arrived. It's been 5 days.
MI
Can you tell me when I'll get it?
RefundsWhatsAppBooking HL-8750 · ₹2,180 · cancelled 5d ago
QuipAI 91% confident
Drafted reply
Hi Meera — sorry for the wait. Your refund of ₹2,180 for HL-8750 was initiated on Monday and takes 5–7 working days to reach your bank, so it should land by Thursday. I've added a note to alert you the moment it clears.
Refund policy §3 Payment gateway log
SendEditAgent reviews before send
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Knowledge base sources being loaded, extracted, tested and published
Knowledge Studio SearchAR
Load Extract Test Publish
Sources (6) Add
Refund & cancellation policy.txt14 Q&A
Vehicle policy.docx9 Q&A
harbourline.example/faq31 Q&A
Timetable notes.txt12 Q&A
Boarding rules.docxextracting…
Agent SOP v4.docxqueued
Test the knowledge base Cited
Can I get a refund 2 hours before departure?
Cancellations up to 2 hours before departure are refunded at 80%. Inside 2 hours, no refund — but you can reschedule once for free.
Refund policy §2.1Confidence 93%
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — A bot conversation handed to an agent below the confidence threshold
Bot-to-Human Hand-over SearchAR
WhatsApp · +91 •••• 4021
We're a group of 40 — can we book the 11:00 with a private deck?
Group bookings above 25 need a quick check with our team. I'm connecting you to a person now — they have this conversation.
Confidence 54% — below your 70% threshold
Hi, this is Sana from Harbour Line. Yes — the upper deck seats 48. Which date?
Hand-over packetAgent has context
Reason Group size exceeds self-service limit
Summary 40 pax, 11:00 sailing, wants private deck
Customer Returning · 3 previous bookings
Suggested Upper-deck group rate, ask for date
Assigned Sana Ali · 12s to pick up
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Who did what on a ticket, in order
Activity Log SearchAR
HL-2041 · Refund not receivedHigh · SLA 8m
MI
I cancelled booking HL-8750 on Monday and the refund still hasn't arrived. It's been 5 days.
RefundsWhatsAppBooking HL-8750 · ₹2,180 · cancelled 5d ago
Activity
09:12Meera Iyeropened ticket via WhatsApp
09:12QuipAIcategorised Refunds · priority High · SLA 30m
09:13QuipAIdrafted reply (91%) with 2 citations
09:15Asha Raoedited and sent the reply
09:15SystemSLA paused · waiting on customer
10:40Meera Iyerreplied "Thanks, got it"
10:41Asha Raoresolved · CSAT survey sent
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — A feed of AI-detected events with recommended actions
AI Insights SearchAR
AI insights · this week 6 new
Reply quality on refund tickets up 14% since the new policy doc was publishedOpen
Reschedule requests spiking on the 11:00 sailing — 3× normal; check capacityOpen
Priya resolved 9 tickets under SLA today; strongest on boarding issuesOpen
Suggested macro: "Refund timing" — would have covered 22 tickets this weekOpen
Two agents over capacity after 4pm; hand-overs queueing 6 minOpen
Knowledge base answered 71% of web questions without a ticketOpen
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Conversation activity across the week
Conversation Trend SearchAR
Conversations · 7 daysAI · human
126+8%
Avg per day
11:00
Peak hour
3.4 msgs+0.3
Engagement
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Ticket workspace with the AI rail collapsed to icons
Ticket Workspace SearchAR
HL-2041 · Refund not receivedHigh · SLA 8m
MI
I cancelled booking HL-8750 on Monday and the refund still hasn't arrived. It's been 5 days.
MI
Can you tell me when I'll get it?
RefundsWhatsAppBooking HL-8750 · ₹2,180 · cancelled 5d ago
01
Agent Assistant
A drafting assistant that has already read the ticket
- Drafts a reply grounded in the ticket, the knowledge base and the activity log
- Sits in the AI rail beside the thread, one column wide
- The agent reviews and sends — the draft does not go out on its own
02
Knowledge Base
The answer the agent would have gone looking for
- Surfaces the knowledge article relevant to the ticket directly in the rail
- Saves the agent a separate search across a help centre or wiki
- The same knowledge base grounds the requester chat assistant and the drafted reply
03
Requester Chat Assistant
Deflection at the point of asking, not after
- Answers the requester from the knowledge base before a ticket is even created
- Part of the self-service intake flow, ahead of the "file a ticket" step
- Reduces volume at the point of asking rather than after a ticket is already open
04
Activity Log
Who did what to this ticket, in order
- Every assignment, status change, escalation and reply recorded in order
- Gives a new agent or a manager the full history without asking around
- The same log AI Insights scores against
05
AI Insights
Scored skills and gaps behind the reply that went out
- Scores the skills and gaps visible in how a ticket was actually handled
- Greets the signed-in agent by name inside the rail
- Turns individual tickets into material for a coaching conversation
06
Conversation Trend
Activity, performance and engagement across the week
- A week-level view of conversation activity, performance and engagement
- Sits alongside the per-ticket AI insights rather than replacing them
- Gives an agent context on their own week, not just the one ticket in front of them
07
Collapsible AI Rail
One column when you want it, an icon rail when you do not
- The AI rail expands to a full column or collapses to an icon strip
- Lets an agent reclaim screen width for the thread when the AI panel is not needed
- State persists so the choice does not reset on every ticket
04 · Agentic AI & Analytics
8 modulesLet AI resolve more, with the numbers to prove it
The control plane for autonomous resolution, and the numbers that justify widening it.
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Volume, resolution rate and handling time on one board
Command Centre SearchAR
412+6%
Volume today
61%+3%
Resolved by AI
4m 10s-40s
Avg handling
9
Open escalations
Volume · today by hour
By channel
WhatsApp46%
Web chat31%
Email17%
Forms6%
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Every AI conversation in progress with its confidence
Live Monitor SearchAR
14
Live now
82%
Avg confidence
2
Below threshold
70%
Threshold
Conversations the AI is holding
Refund status for HL-8750WhatsApp
96%Answering
Can I bring a bicycle?Web
91%Answering
Change name on ticketWeb
88%Self-service
Group booking for 40 peopleWhatsApp
54%Handing over
Invoice with GST numberEmail
72%Answering
Complaint about crewWhatsApp
31%Handed over
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Confidence thresholds, approvals and escalation rules
AI Setup & Guardrails SearchAR
Confidence & hand-over
Answer automatically above70%
Escalate to a person below55%
Always hand over on "refund" + "complaint"
Customer can ask for a human at any point
Approvals & audit
Agent reviews drafts before sending
AI may issue refunds under ₹500
Log every AI action with its reasoning
Knowledge sources: approved only
Changes take effect immediately and are versioned.
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — AI accuracy over time and CSAT against human agents
AI Performance SearchAR
89%+3%
AI accuracy
4.6
CSAT · AI
4.7
CSAT · human
7%-2%
Corrections by agents
Accuracy · 12 weeks
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Escalation queue and agent capacity
Agent Hub SearchAR
Escalation queue (9)2 waiting > 5m
Group booking for 40 peopleWhatsApp6mAssign
Complaint about crewWhatsApp5mAssign
Corporate invoice changeEmail3mAssign
Vehicle bay not shownWeb2mAssign
Refund for double chargeWeb1mAssign
Capacity
ARAsha Rao
3/5
DMDev Menon
5/5
PNPriya Nair
2/4
RSRahul Shah
4/5
SASana Ali
1/4
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Deflection funnel and CSAT for AI versus human
Ticket Deflection SearchAR
1,284
Conversations
64%+4%
Deflected
29%
Handed over
4.6 / 4.7
CSAT · AI vs human
Where it went
Answered by knowledge base58%
Self-service action (reschedule, resend QR)6%
Handed to agent · low confidence21%
Handed to agent · customer asked8%
Abandoned7%
Deflection · 8 weeks
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — Analytics dashboard with KPIs, a trend line and a breakdown
Analytics SearchAR
128-9%
Open tickets
94%+2%
SLA met
11m-3m
First response
4.7+0.2
CSAT
Tickets · 30 days
By category
Refunds
31%
Reschedule
24%
Boarding / QR
18%
Payments
15%
Other
12%
app.quipcom.ai
Illustrative UI
Illustrative QuipAI screen — SLA compliance by department and agent leaderboard
SLA & Agent Analytics SearchAR
SLA compliance · by department
Refunds91%
Reschedule97%
Boarding94%
Payments88%
General98%
Leaderboard · this week
1PNPriya Nair41 resolvedCSAT 4.8
2ARAsha Rao38 resolvedCSAT 4.7
3DMDev Menon35 resolvedCSAT 4.6
4RSRahul Shah29 resolvedCSAT 4.7
5SASana Ali27 resolvedCSAT 4.9
01
Command Centre
Volume, resolution rate and handling time on one board
- Volume, resolution rate and average handling time shown on one operational board
- The top-level view of what the AI is handling across the whole desk
- Where a manager starts before drilling into a single conversation
02
Live Monitor
Every conversation the AI is holding, with its confidence
- Every live AI-held conversation listed with its current confidence score
- Lets a supervisor see, in real time, what the AI is about to do
- The confidence score is what the guardrail threshold acts on
03
AI Setup & Guardrails
Confidence and escalation thresholds you set, not inherit
- Confidence and escalation thresholds are configured per desk, not fixed by the vendor
- Setting the threshold higher hands over more to a human; lower lets the AI take more
- Changes here are what AI Performance and Ticket Deflection then measure against
04
AI Performance
Accuracy over time, and CSAT for AI against human
- Tracks AI accuracy over time rather than a single point-in-time number
- Compares CSAT on AI-handled conversations against human-handled ones
- The evidence for deciding whether to widen or narrow what the AI handles
05
Agent Hub
The escalation queue and who has capacity for it
- Shows the queue of conversations escalated out of the AI
- Agent capacity visible alongside the queue so hand-over goes to someone free
- Connects the agentic layer back to the human assignment rules
06
Ticket Deflection
What never reached an agent, and by which route
- Counts what was resolved without ever reaching a human agent
- Broken down by the route it was deflected through (chat, knowledge base and similar)
- The number that justifies — or does not yet justify — widening AI scope
07
Ticketing Dashboard
Agent and manager views over the same dataset
- One dashboard with both an agent view and a manager view
- Both views read the same underlying ticket dataset — no separate reporting pipeline
- The general operational home page for the desk
08
SLA & Agent Analytics
Compliance by department, leaderboard, workload
- SLA compliance broken down by department
- An agent leaderboard alongside workload distribution across the team
- Turns the same activity data used for escalation into a management report
How it works
From first touch to done, step by step
- 01
Raise
The requester picks a department, sees the matching knowledge base, and only files a ticket if the answer is not already there.
- 02
Route
Category and tags set the SLA tier; the assignment strategy picks the agent; the notification matrix tells everyone who needs to know.
- 03
Resolve
The agent works one screen — thread, record, actions and QuipAI — while the SLA clock runs against business hours.
- 04
Learn
Deflection, accuracy, CSAT and SLA compliance are measured per category, which is what tells you where to let the AI take more.
What changes
Before and after, in plain terms
Operational changes, not promised percentages. We size the impact with you against your own baseline.
Area
Today
With Service CRM
Intake
Tickets are logged by hand from inboxes and calls.
Email, forms, chat and WhatsApp become categorised tickets on their own.
Routing
A lead assigns tickets by looking at who seems free.
Round-robin, load-balanced or skill-based assignment, with capacity visible.
Service levels
Breaches are noticed after the customer complains.
An SLA clock that respects business hours, with four escalation levels.
Replying
Agents search the wiki and write each reply from scratch.
A drafted reply grounded in the ticket and the knowledge base, reviewed before it goes.
Deflection
Every question becomes a ticket.
Requesters see the matching answer before filing, and the bot answers what it can.
Reporting
Monthly reports are rebuilt from exports.
Agent and manager dashboards on one dataset, with SLA compliance by department.
Built for you
One workspace, 5 roles
Each role sees its own queue, its own actions and the same underlying record.
For the requester
Raise, track and reopen their own tickets; answer the CSAT survey.
- Answers from the knowledge base before filing
- A ticket they can track and reopen
- A short CSAT survey once it is resolved
Modules they use most
Part of the platform
Service CRM is one product. The platform keeps it connected.
Configured to your process, brand, roles and integrations. The layer underneath is shared, so adding another product extends what you already run.
Shared across every QuipCom product
Roles & permissionsTheme & brandingWorkflow rulesAPIs & integrationsAgentic AI
Deployment: Cloud · SaaS · On-premise
Works with Sales CRM
Pair it with Sales CRM
Together they make QuipCRM: the customer the sales team won and every request they raise afterwards, on one platform.
Explore Sales CRM Works with Conversational AIAdd Conversational AI
A website chatbot and a WhatsApp bot answer from the same knowledge base and hand over into this ticket desk with the transcript attached.
Explore Conversational AIRollout
How it goes live
Each phase is usable on its own. Configuration follows your process, not a fixed template.
- 1Phase 1
Foundation
Categories and sub-categories, tags, the ticket record, queues and roles.
- 2Phase 2
Service levels
SLA tiers, the escalation matrix, business hours and the notification matrix.
- 3Phase 3
Routing at scale
Assignment strategies, agent capacity, folders and self-service intake.
- 4Phase 4
Assisted resolution
Agent assistant, knowledge base, activity log and conversation insights.
- 5Phase 5
Agentic operations
Autonomous resolution inside your thresholds, deflection, guardrails, AI performance.
Where things stand
What you can see working in a demo today, and what is configured during production activation.
Demonstrable today
- Full ticket workspace, queue, record, thread and actions
- All governance surfaces: categories, SLAs, escalation, routing, notifications, business hours
- All seven QuipAI-in-the-ticket capabilities
- The agentic control plane: command centre, live monitor, guardrails, performance, deflection
- Five role profiles with different controls
Production activation
- Tenant-aware APIs, backend authorisation and audit logs
- Email and WhatsApp provider credentials
- The knowledge sources behind the AI (website URLs, .docx and text files; additional formats scoped at onboarding)
- The live requester queue and routing queues, once pointed at your data
- Model governance and evaluation before widening AI scope
Service CRM: questions teams ask
Yes. Separate queues, permissions, workflows, and SLAs keep each experience appropriate while leadership sees the complete operational picture.
Yes. Require notes, photos, signatures, approvals, or checklists before closure, all visible in the activity log.
Only within thresholds you set in AI Setup & Guardrails. Below your confidence threshold, it drafts for a human rather than sending.
The conversation hands over to a human agent through the Agent Hub, which shows who has capacity to take it.
Yes, on a separate queue with its own categories and routing — the same governance model applies.
Yes, both are native reply and intake channels alongside the in-app thread.
The SLA clock only runs during the business hours configured for the desk, so nights and weekends do not count as a silent breach.
Still need help? Book a demo.
Bring one real support queue.
We’ll set up your categories, SLA tiers and escalation live, and show QuipAI drafting replies on sample tickets.