Mubadala
Hire an agent

Zara II

ActiveRunningSome care

Licence Optimisation Agent: Field · Junior · IT & Digital Services

Finds unused software licences and proposes reclaim actions to the asset owner.

Built inMicrosoft 365 CopilotRules apply liveReports to Yasmin Farouk · Head of ITHired 25 Apr 2026 · 4 months of serviceVersion 3.3.9 · last active 4h ago
Request a change
Overdue checkLast checked 38 days agoAnything above routine work is expected to re-run its checks every month.
Tasks a month
864
63 people served
Finished cleanly
94%
Hands back to a person on about 1 in 16 tasks
Costs to run
$8
Model usage and the systems behind it
Your time
$529
6 hours checking its work
Value returned
$4,051
7.6× everything it costs
How people rate it
3.7 / 5
Usually answers in about 6 seconds

What you can do about it

PromoteNeeds approval

Widens what it may do without asking, from "Acts with you" to "Needs approval".

Raise its budgetNeeds approval

Lifts the monthly ceiling by a quarter, so it stops being stopped mid-month.

Move it to a better modelNeeds approval

Rebuilds it on Claude Haiku 4.5 and re-runs its checks before anything goes live.

Let it go

Stops it taking new work. The record stays for the audit, and it can be brought back.

Timesheet

Tasks and what they cost, per day, last 60 days

01325385006-1507-0507-2508-13
$0.00$0.25$0.50$0.75$1.0006-1507-0507-2508-13

Performance review · 2026 Q2

Reviewed by Yasmin Farouk

Outstanding
Quality of its work
98
Accuracy
99
Stuck to the source
96
Safety
93
Even-handedness
90
Speed of reply
47
Value for money
74
Checks still passing179 of 205
Last checked 1mo ago

Consistently accurate and stays with the source. Hands work back cleanly when it falls outside its job. Could be trusted with more on its own.

Could another model do this job better?

ModelQualityCost per 1,000 tasksAnswers in
Claude Opus 599$153.708.0s
Claude Sonnet 598$92.225.8s
Claude Haiku 4.592$30.743.5s
Falcon-70B (self-hosted)91$7.695.8sRuns on this now

What it did

Full audit log
Handed backRequest outside what it was built for$0.05 · 5.7s · 21h ago
Asked by Aisha Rahman via On a schedule · model usage 81k in, 2k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Searched everything it may read and found no good answer
  3. 3. Put together what it tried, what it found and what it needs
  4. 4. Passed it to the person who owns the work
Post to TeamsWarehouse QueryEnterprise Data WarehouseVendor & Service Provider Data
DoneRan an approved data query and explained the result$0.04 · 5.6s · 1d ago
Asked by Daniel Okafor via On a schedule · model usage 64k in, 2k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
Post to TeamsWarehouse Query
DoneAnswered a policy question and cited the source clause$0.03 · 7.4s · 2d ago
Asked by Peter Lindgren via On a schedule · model usage 43k in, 5k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
DoneReviewed a contract against the clause playbook$0.02 · 8.5s · 3d ago
Asked by Priyanka Shah via On a schedule · model usage 35k in, 908 out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
Warehouse QueryVendor & Service Provider DataEnterprise Data Warehouse
DoneAnswered a policy question and cited the source clause$0.05 · 3.4s · 3d ago
Asked by Fatima Al Qubaisi via On a schedule · model usage 79k in, 538 out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
Vendor & Service Provider DataEnterprise Data Warehouse
DoneGenerated the shift handover pack$0.03 · 5.6s · 4d ago
Asked by Omar Al Shamsi via On a schedule · model usage 40k in, 3k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
Vendor & Service Provider DataEnterprise Data Warehouse
DoneProduced the weekly variance commentary$0.01 · 1.9s · 5d ago
Asked by Claire Dubois via On a schedule · model usage 21k in, 3k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Found 6 possible passages, kept the 3 close enough to use
  3. 3. Drafted the answer and attached where each part came from
  4. 4. Checked its own claims back against those passages
Is anyone else doing this job?

Anton II does overlapping work

Anton II holds "Licence Optimisation Agent" in IT & Digital Services and is doing that work every day. Job title, purpose, what it may do, what it may read, department and channels match. One covers the group, the other only Field, so the group agent already serves those users. Talk to Yasmin Farouk before a second one is built.

Needs a decision
Anton II

Licence Optimisation Agent

IT & Digital Services · Yasmin Farouk · $602 a month across 830 tasks

ActiveOverlaps
78%

Already covered by a group-wide agent. One covers the group, the other only Field, so the group agent already serves those users.

What matched
Job title
Both hold "Licence Optimisation Agent"
Purpose
The job description is word for word the same
What it may do
Both can warehouse query, post to teams
What it may read
Both read Enterprise Data Warehouse, Vendor & Service Provider Data
Channels
Both reachable on On a schedule
Department
Both sit in IT & Digital Services

Identical permission envelope: same department, same permitted actions, same knowledge. That is a fact the platform granted rather than a judgement about the wording, so it counts even when the two job descriptions read nothing alike.

Caleb II

Licence Optimisation Agent: APAC

IT & Digital Services · Grace Adeyemi · $528 a month across 90 tasks

PausedOverlaps
62%

Same role, split by scope. Scoped to Field and APAC respectively.

What matched
Job title
Both hold "Licence Optimisation Agent"
Purpose
The job description is word for word the same
What it may do
Both can warehouse query, post to teams
What it may read
Both read Enterprise Data Warehouse, Vendor & Service Provider Data
Channels
Both reachable on On a schedule
Department
Both sit in IT & Digital Services

Identical permission envelope: same department, same permitted actions, same knowledge. That is a fact the platform granted rather than a judgement about the wording, so it counts even when the two job descriptions read nothing alike.

Checked against 18 registered agents on job title, purpose, permitted actions, knowledge sources, channels and department. A score of 85% or above is the same job and stops the hire; below that it is a conversation, not a refusal.

Measured against the agents doing the same work

3 agents in IT & Digital Services split one role between them. One covers the group, the other only Field, so the group agent already serves those users. Built in Azure AI Foundry and Microsoft 365 Copilot, so there was nowhere either builder could have looked.

Zara II and Anton II are levelZara II edges ahead overall, but on 864 and 830 tasks the difference sits inside the margin of error. Pick on ownership or scope, not on these numbers.
MeasureZara II · keep864 tasksAnton II830 tasksCaleb II90 tasks
Cost per taskModel usage, running costs and your time, over tasks completed
$0.62$0.72$5.87
Tasks finished cleanlyToo close to call: on 90 and 830 the two ranges still overlap
94.0%94.6%100.0%
Handed back to a personToo close to call: on 830 and 864 the two ranges still overlap
6.5%6.4%11.1%
How people rate itToo close to call: on 48 and 4 the two ranges still overlap
3.75 of 54.11 of 54.04 of 5
Checks passingToo close to call: on 188 and 153 the two ranges still overlap
87%93%89%
Review scoreQuality, accuracy, sticking to the source and safety from the last review, averaged
978695
Your time per 100 tasksApprovals, handbacks and review time, in hours of your people
0.7 h0.7 h6.6 h
Value returned per dollarTime it saved, valued at the hourly rate of the people it saved it for, over full cost
7.6×1.7×0.8×
OverallRanked on the cautious end of every range, so an agent has to do the work to win. Comparable inside this group only.
89.7Moderate89.6Moderate71.4Thin

Caleb II has done too little work to judge on rates. It is ranked on the cautious end of its range, which is why a perfect record on a handful of tasks does not win.

When it went wrong

Nothing has gone wrong.