AiMY
Connect
Talent
QA
Sales
V1
NW
Since your last visitlast seen Tue, 9:14am

I ran 34 new evaluations across your 12 agents, 1 feedback needs your review, 1 justify is waiting on you, and 1 follow-up is due today.

82% avg quality 2 agents at risk 12 agents · Product Support
Evaluated this cycle9/ 12
3 pending → Nadia Fathy, Karim Adel, Yara Nabil
Acknowledged6/ 8 sent
2 ignored past the nudge window, Show the 2 waiting on acknowledgement →
Most-failed goal62%
Follow-up Confirmation · 5 of 12 below target, Roll out the plan to 5 agents →

Agents

agents that need you now

Feedback I've sent · loop status

Giving & tracking feedback for your 12 directs

OA
Omar AbdallahNegative
Follow-up Confirmation, Survey Promotion
AiMY-drafted · sent 21 days ago · acknowledged
Did Omar improve?
TM
Tariq MansourNegative
Issue Resolution
AiMY-drafted · sent 2 days ago
Awaiting ack · follow-up in 19d
AK
Aisha KhalilPositive
Script Adherence · how to exceed
AiMY-drafted · sent 1 week ago
No action needed
MC
Michael ChenNegative
Script Adherence
AiMY-drafted · sent 26 days ago · justifyd → overturned
Resolved · overturned
Reviews
Viewing
12 agents on Product Support · click an agent to drill in
AiMY operations summary
Quality is 96.0% across 3,363 reviews, 89.7% pass rate, 345 failures. Repeated status/ETA misses in Objectif Lune and Qvidian, plus time-between-updates failures, are the main drivers.
High · AiMY confidence
Operational snapshot
Product performance
60% 70% 80% 90% 100%
#1 SS Second Street 96.8% 8 fails
#2 AD Adestra 94.4% 23 fails
#3 AR AccuRoute 91.8% 21 fails
#4 FB Filebound 91.7% 17 fails
#5 PV Panviva 90.7% 21 fails
#6 PS PSA 89.2% 25 fails
#7 RA RightAnswers 87.8% 41 fails
#8 IF InterFax 85.9% 52 fails
#9 OL Objectif Lune 82.7% 72 fails
#10 BA BA Insights 82.6% 19 fails
Coaching priorities
H
Incorrect status High priority
High impact · suggested 45 min session · expected ↓ 60 failures
150
failures
M
Grammar mistake Medium priority
Medium impact · suggested 30 min session · expected ↓ 17 failures
55
failures
M
Time between updates Medium priority
Medium impact · suggested 30 min session · expected ↓ 14 failures
47
failures
AIMY TEAM ANALYSIS · Updated 4 minutes ago

Product Support's quality score dropped 2 points to 84% over the last 30 days, but the decline isn't team-wide, it's concentrated in 2 agents (Omar Abdallah and Tariq Mansour). The other 10 agents are at or above team baseline. CSAT, Adherence, and Utilization remain healthy team-wide.

!
Failure pattern is process adherence, not skill
75 of the 200 goal misses this period are missed follow-up SOPs. This is the same root cause for both at-risk agents, suggesting a process or training gap, not individual skill regression.
!
AHT spike correlates with billing-category routing change
Multiple agents show AHT increase coinciding with the Apr 18 routing update. Likely systemic, not coaching-related.
✓
Top performers are stable training resources
Sarah Reyes and Lina Haddad have consistent 90%+ scores across 12 weeks. Their recordings are available for shadow-training.
AiMY recommends · 3 actions
Targeted coaching for Omar & Tariq on follow-up SOPs · routing retro with team lead · benchmark against Onboarding's playbook (91% quality, similar volume).

Recent evaluations

AiMY-run · this agent
OA
Omar Abdallah
Product Support·5 months tenure·Team Lead: Lina H.
At risk
Coaching priority · process gap AiMY DETECTED P1 · Urgent
Omar is missing follow-up SOP steps in 47 of 89 interactions this period. He resolves the issue but doesn't set clear next steps. Pattern is consistent across ticket closures, not channel-specific.
AiMY classifies this as a process adherence gap, not a knowledge gap. Recommendation: targeted SOP refresh, not broad retraining.
53% miss rate Quality 64% ↓ 9pts CSAT 71% ↓ 5% FCR 68% → flat 2 open actions · oldest 14d
MC
Michael Chen
Watch · 11 months tenure
Watch
AHT spiked +28% this week, but the spike correlates exactly with billing-category routing changes. Other agents show the same pattern. Likely systemic, not skill regression.
SR
Sarah Reyes
Top performer · 2.5 yrs tenure
Excelling
Empathy scores 3× team average. FCR hit personal best this week. Consider using her recordings as training material for empathy-handling on at-risk agents.
OA
Omar Abdallah At risk
Product Support·Egypt·5 months tenure·Reports to Lina Haddad·Reviewed by Salma Ehab
89 of 142 interactions evaluated 63% coverage
By channel: Email/Ticket66% Call71% Voice58% Accum. score64%
AiMY on Omar Abdallah Updated 4 min ago
Across the 89 evaluations I've scored, Omar's one failing goal is Follow-up Confirmation (64% vs the 80% target). I drafted the negative feedback he has now acknowledged, and his coaching plan is 60% complete. If it closes on pace I'll ask Lina to re-evaluate, otherwise it escalates to the Feedback Manager.
Quality 64% ↓9pts Follow-up SOP 47% ↓3pts 1 plan stalled 18d

goal standing

6 goals · vs 80% target
AiMY has been tracking Omar for 5 months Updated 4 min ago
142 Interactions observed
89 Evaluations scored
47 Follow-up SOP misses
1 Coaching session with confirmed improvement
AiMY first detected the follow-up SOP gap in W5 (Feb 18), 8 weeks before the quality score crossed below 70%. The pattern has been consistent across email and chat, not concentrated in one channel. Empathy scores recovered after the Mar 14 coaching session, confirming AiMY's model that soft-skill goals respond to coaching for this agent.
Trajectory confidence
84%
Based on 8-week stable pattern across 2 channels · comparable to 3 similar historical cases where SOP coaching resolved the gap within 4 weeks.
Detection timeline
First interaction observed
Onboarding period · quality at 73% · no flags raised
Dec 12
Follow-up SOP gap first detected
W5 · pass rate dropped from 88% → 72% · 3 consecutive instances · below threshold signal triggered
Feb 18
Pattern confirmed cross-channel
Email and chat both showing the same gap · not channel-specific · AiMY confidence upgraded to High
Mar 02
Empathy coaching session · Lina H.
45 min · de-escalation patterns · AiMY tracked empathy scores weekly for 4 weeks post-session
Mar 14
Empathy recovery confirmed
+6pts over 4 weeks · AiMY marked empathy coaching as effective for this agent · model updated
Apr 11
Quality score crossed 70% threshold
Primary cause: follow-up SOP miss rate now at 53% · CSAT impact confirmed at −14pts per missed instance
Apr 28
Quality score
64%
↓ 9pts tgt 85%
CSAT
71%
↓ 5% tgt 80%
FCR
68%
→ Flat tgt 75%
Avg handle time
6m 02s
→ Normal tgt <7m
Adherence
89%
↑ Good tgt 85%
Utilization
84%
→ Stable tgt 80%
AIMY ANALYSIS · Updated 4 minutes ago

Omar's quality score has dropped 9 points over 6 weeks, but the underlying pattern is narrow: he's missing follow-up SOP steps in 47 of 89 closures. Resolution itself is sound, FCR at 68% is near team baseline and his AHT and adherence are healthy. This indicates a process gap, not a knowledge or empathy gap.

!
Follow-up SOP missed in 47 of 89 interactions (53%)
Pattern is consistent across email and chat channels, not channel-specific.
!
CSAT dip concentrated in tickets without next-step confirmation
Customers without clear follow-up scored 14pts lower on average.
✓
Empathy and tone scores remain at team baseline
No evidence of skill regression. Soft skills are intact.

The pattern is concentrated and resolvable. Two top performers on the team can serve as shadow-training material.

AiMY recommends
30-min SOP refresh on follow-up confirmation, paired with shadowing one of Sarah Reyes's recorded interactions. Avoid broad retraining. Pattern doesn't support it.
2
2 open coaching actions · oldest opened 12 days ago 1 in progress
Pending: SOP refresh on follow-up confirmation (Lina H., scheduled tomorrow) · Stalled: Empathy shadow review (no date set, opened Apr 16)
Behavioral goal breakdown
40% 55% 70% 85% 100%
1Next steps · 47% · ↓3pts, click for detail 2Resolution confirm · 62% · ↓8pts, click for detail 3Categorization · 74% · stable, click for detail 4Empathy · 86% · ↑+2pts, click for detail 6Survey promotion · 91% · ↑+4pts, click for detail 5Identity verification · 94% · stable, click for detail
Failing <70% Watch 70–85% Meeting target ≥85%
Click a marker or row for detail
1
Did the agent set clear next steps and follow-up timeline?
47%
↓3 12pts
2
Did the agent confirm the issue was fully resolved?
62%
↓3 8pts
3
Did the agent log the ticket with correct category and tags?
74%
→ Stable
4
Did the agent demonstrate empathy during the interaction?
86%
↑ +2pts
5
Did the agent verify customer identity before sharing details?
94%
→ Stable
6
Did the agent promote the post-interaction survey?
91%
↑ +4pts
Quality score trend · 12 weeks
TARGET 85% W1 W4 W7 W10 W12 (now) Omar Team avg
Now: 64% · 21pts below target
Trajectory suggests recovery to 75% in 4 weeks with active coaching · set a goal to track progress and trigger alerts if off-track.
goal compliance heatmap · 12 weeks
Weekly pass rate per category, blue dot marks a coaching session that week
Low → High
goal category W1W2W3W4W5W6 W7W8W9W10W11W12
Follow-up SOP
88
85
78
72
61
55
52
49
51
48
47
47
Resolution confirm.
91
89
87
76
74
70
73
71
69
64
62
60
Ticket categorisation
82
80
77
75
74
74
74
76
75
74
74
74
Empathy & tone
78
75
73
68
65
63
63
72
78
84
86
86
Identity verification
95
94
96
95
94
93
94
95
94
94
94
94
Survey promotion
88
90
89
91
90
91
91
91
91
91
91
91
Coaching history
!
Pending, SOP refresh on follow-up confirmation Scheduled
Tomorrow, 2:00 PM
AiMY-suggested · 30 min · with Lina Haddad (team lead). Includes shadow review of Sarah Reyes's closure recordings.
✓
Empathy & tone · 1:1 review
Mar 14, 2026
45 min with Lina H. Discussed customer de-escalation patterns. Empathy scores rose +6pts in the 4 weeks following.
✓ Improvement confirmed
i
Onboarding QA review · 90-day milestone
Feb 02, 2026
Standard milestone review. Quality score at 73%, on track. No coaching flags raised at this point.
!
Ticket categorization training
Jan 18, 2026
Group session · 4 agents. Addressed inconsistent ticket tagging. Tagging accuracy rose to 74%, still slightly below team avg.
~ Partial improvement
00:00
Agent handled Voice call · May 7, 2026 · 10:05 · 8m 34s
Voice
Sentiment Opened frustrated at the refund delay, closed neutral after the escalation — partial recovery. ↑ +8 by close 32 / 100 team 64
C
Hi, I've been waiting 3 days for a refund and still nothing. This is really frustrating. Can you please just fix this today?
10:05
OA
Hi, I'm sorry to hear that. Let me pull up your account and check the refund status right now.
10:06
C
It says processing but it's been 3 days. You said 2 business days last time.
10:07
OA
I can see the refund was submitted on May 5th. It's still in the processing queue, I'm escalating this now so it clears today. You'll receive an email confirmation within the hour.
10:09
C
Okay, thank you. But what if it doesn't? Who do I contact?
10:11
OA
You're all set. Is there anything else I can help you with today?
10:12
C
No, I guess not. Bye.
10:13
52% Provisional score0 reviewed · 6 remaining
Passed 3 Failed 2 Pending 1 Unscored 1
AiMY confidence91%
×

Follow-up confirmation

CR-041

Did the agent set clear next steps and a follow-up timeline?

AiMY Fail18 pts

Why AiMY scored this: The customer asked who to contact if the refund did not clear. The call ended without a named contact, fallback route or follow-up time.

96% confident
Customer10:11
Okay, thank you. But what if it doesn't? Who do I contact?
Agent10:12
You're all set. Is there anything else I can help you with today?
Manual review Not reviewed
×

Resolution confirmation

CR-018

Did the agent confirm the issue was fully resolved?

AiMY Fail16 pts

Why AiMY scored this: The agent escalated the refund and said "you're all set" but did not verify with the customer that the resolution was satisfactory.

92% confident
Agent10:09
I'm escalating this now so it clears today. You'll receive an email confirmation within the hour.
Manual review Not reviewed
!

Ticket categorization

CR-023

Did the agent log the ticket with correct category and tags?

AiMY Pending10 pts

Why AiMY scored this: Tagged as "billing". A more precise categorization as "refund delay escalation" would improve routing accuracy.

61% confident
Manual review Not reviewed
✓

Empathy & tone

CR-007

Did the agent demonstrate empathy during the interaction?

AiMY Pass14 pts

Why AiMY scored this: Opened with an apology, acknowledged the delay and took immediate action. Tone remained steady throughout.

94% confident
Manual review Not reviewed
✓

Identity verification

CR-002

Did the agent verify customer identity before sharing details?

AiMY Pass15 pts

Why AiMY scored this: Full identity verification completed before the account lookup.

98% confident
Manual review Not reviewed
✓

Survey promotion

CR-043

Did the agent promote the post-interaction survey?

AiMY Pass12 pts

Why AiMY scored this: Survey mentioned at the close of the call.

88% confident
Manual review Not reviewed
–

Disposition code

CR-030

Was the interaction tagged with the correct disposition code?

Unscored

I can't score this one. The disposition code is a CRM field, not something said on the call, and this voice transcript carries no record of it.

Agree with remaining KPIs?

Apply your agreement to every KPI that already has an AiMY verdict. Existing scores will not change.

KPIs will be marked as agreed
AiMY's existing verdict is kept for each included KPI.
0
52%
Overall quality score
Fail Voice
High · AiMY confidence
AiMY confidence
91%
Full transcript available✓ Yes
All goals answerable✓ 6 / 6
Conflicting signalsNone
Interaction length8m 34s, sufficient

Omar resolved the refund issue correctly but closed without confirming next steps with the customer. The customer explicitly asked "who do I contact if it doesn't work?". This went unanswered before the call ended. The follow-up SOP and resolution confirmation goals both failed as a result.

Did agent set clear next steps?0%Fail
Did agent confirm issue resolved?0%Fail
Empathy & tone88%Pass
Identity verification100%Pass
Ticket categorization74%Borderline
Survey promotion91%Pass
goal breakdown
Did the agent set clear next steps and follow-up timeline? 0% Fail
Customer asked "who do I contact if it doesn't work?", agent ended the call without answering. No follow-up timeline provided.
Did the agent confirm the issue was fully resolved? 0% Fail
Agent escalated the refund and said "you're all set" but did not verify with the customer that the resolution was satisfactory.
Did the agent demonstrate empathy during the interaction? 88% Pass
Opened with an apology, acknowledged the delay, took immediate action. Tone remained steady throughout.
Did the agent verify customer identity before sharing details? 100% Pass
Full identity verification completed before account lookup.
Did the agent log the ticket with correct category and tags? 74% Borderline
Tagged as "billing", more precise categorization as "refund delay escalation" would improve routing accuracy.
Did the agent promote the post-interaction survey? 91% Pass
Survey mentioned at close of call.
Was the interaction tagged with the correct disposition code?
I can't score this one. The disposition code is a CRM field, not something said on the call, and this voice transcript carries no record of it.
AiMY handled Chat · May 8, 2026 · 14:22 · 4m 11s
Chat
Sentiment Escalated mid-session and never recovered. ↓ −6 by close 28 / 100 team 64
C
I need to cancel my order, order #44821. It's been 5 days and hasn't shipped.
14:22
AiMY
I can help with that. Let me check order #44821 for you.
14:22
C
Also I want to know why it hasn't shipped. This is unacceptable.
14:24
AiMY
I've located your order. It's showing a warehouse hold due to a stock discrepancy, I'm initiating a cancellation and refund now. You'll receive confirmation within 2 business days.
14:25
C
Fine. But can you make it faster?
14:26
AiMY
Your cancellation is confirmed. Is there anything else I can assist with?
14:26
AiMY handled Model confidence is the primary quality signal for AI interactions
58%
Overall quality score
Fail Chat
High · Model confidence
Model confidence
88%
Full chat log available✓ Yes
goals answerable (excl. empathy)✓ 5 / 5
Customer intent unambiguousClear
Model action loggedCancellation confirmed
Model flags
!
Follow-up confirmation skipped
Customer asked to expedite. AI acknowledged cancellation but did not address the timeline question or set expectations.
✓
Resolution action taken correctly
Cancellation initiated with correct reason code. Refund timeline communicated.

AiMY completed the cancellation correctly but skipped two process steps: it did not address the customer's request to expedite, and it did not confirm resolution before closing. Resolution confirmation and follow-up SOP both failed. Identity verification and categorization scored well.

goal breakdown · AI interaction
Did the AI set clear next steps and follow-up timeline? 0% Fail
Customer asked "can you make it faster?". AI confirmed cancellation but did not address the timeline question.
Did the AI confirm the issue was fully resolved? 0% Fail
Closed with "is there anything else?" without verifying customer satisfaction with the resolution.
Did the AI verify customer identity before sharing account details? 100% Pass
Identity confirmed before order lookup via session authentication token.
Did the AI log the ticket with correct category and tags? 91% Pass
Tagged as "cancellation, warehouse hold". Correct category and reason code.
Did the AI promote the post-interaction survey? 0% Fail
Survey not triggered at session close. Model gap, closing sequence did not include survey prompt.
Empathy & tone goal not scored for AiMY-handled interactions.
3
Enter to send
Suggestion dismissed AiMY will surface fewer of these.

Dispute

Justify this feedback

Quarterly evaluation

Challenge this goal

Raises a change request in Goal Hub · reviewed by an admin

New Feedback

Proactive, no time constraint · covers one or more goals

Feedback report

Aggregate the feedback loop, for everyone or one person
All agents (12)
Omar Abdallah
Tariq Mansour
Michael Chen
Aisha Khalil
Daniel Rodriguez
Priya Venkat
Jamal Williams
Sarah Reyes
Last 7 days
Last 30 days
Last 90 days
This quarter

Insights & Actions

AiMY-surfaced patterns across your directs
2 agents constantly below target
Omar Abdallah & Tariq Mansour, repeated negative feedback. AiMY can auto-schedule an HR meeting.
Follow-up Confirmation is the top team gap
Lowest-scoring goal across 5 agents. A shared micro-lesson would lift the whole team.
4 agents actively acting on their goals
Aisha, Daniel, Jamal & Sarah completed coaching plans and are on track, no action needed.
3 unsubmitted feedbacks for new hires
Michael, Priya (& 1 more) have no feedback yet, nudge their supervisor before probation ends.