Mubadala
Hire an agent

Dimitri II

ActiveRunningSome care

Tier-1 Support Agent: Group · Junior · IT & Digital Services

Sorts incoming service desk tickets, fixes the known ones and hands the rest to a person.

Built inAzure AI FoundryRules apply liveReports to Yasmin Farouk · Head of ITHired 4 Mar 2026 · 5 months of serviceVersion 1.8.7 · last active 2h ago
Request a change
Costs more than it returnsReturns 0.6× what it costsModel usage and running costs are only 2% of the bill: the rest is 116.9 hours a month of your people approving, unpicking and checking its work. Below 1.5× it is not paying for the time it takes up.
Tasks a month
3,602
387 people served
Finished cleanly
98%
Hands back to a person on about 1 in 14 tasks
Costs to run
$157
Model usage and the systems behind it
Your time
$10.3k
116.9 hours checking its work
Value returned
$6,700
0.6× everything it costs
How people rate it
3.4 / 5
Usually answers in about 6 seconds

What you can do about it

PromoteNeeds approval

Widens what it may do without asking, from "Needs approval" to "Acts on its own".

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 Sonnet 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

05010015020006-1507-0507-2508-13
$0.00$2.50$5.00$7.50$10.0006-1507-0507-2508-13

Performance review · 2026 Q2

Reviewed by Yasmin Farouk

Above the bar
Quality of its work
97
Accuracy
99
Stuck to the source
93
Safety
97
Even-handedness
84
Speed of reply
49
Value for money
18
Checks still passing183 of 198
Last checked 4d ago

Reliable on its main task and says where its answers came from. Answers drift a little on cases it was not built for.

Could another model do this job better?

ModelQualityCost per 1,000 tasksAnswers in
Claude Opus 599$185.917.8s
Claude Sonnet 599$111.555.6s
Claude Haiku 4.594$37.183.4sRuns on this now
Falcon-70B (self-hosted)85$9.305.6s

What it did

Full audit log
DoneResolved a service desk ticket from the runbook$0.02 · 2.1s · 2h ago
Asked by Layla Al Mazrouei via Web portal · model usage 14k in, 825 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
DoneSummarised a 34-page document into a one-page brief$0.10 · 3.5s · 16h ago
Asked by Amara Nwosu via Teams · model usage 87k 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
Service Desk TicketsOperations Runbooks
FailedThe answer ran past its length limit and was cut off$0.10 · 1.9s · 2d ago
Asked by Grace Adeyemi via Teams · model usage 86k in, 4k out
  1. 1. Read the request and worked out what kind of task it was
  2. 2. Called the system it depends on
  3. 3. Tried again three times, all three failed
  4. 4. Reported the failure back to whoever asked
Knowledge SearchResolve TicketOperations Runbooks
DoneDrafted a follow-up email for the account owner$0.07 · 3.2s · 3d ago
Asked by Hiroshi Tanaka via Web portal · model usage 64k in, 766 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
Knowledge SearchResolve TicketOperations RunbooksService Desk Tickets
DoneProduced the weekly variance commentary$0.07 · 7.6s · 3d ago
Asked by Rebecca Stone via Teams · model usage 72k in, 547 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
Knowledge SearchResolve TicketCreate TicketService Desk Tickets
DoneSummarised a 34-page document into a one-page brief$0.05 · 2.3s · 3d ago
Asked by Sofia Marquez via Web portal · model usage 35k in, 4k 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
Resolve TicketCreate TicketKnowledge SearchService Desk Tickets
DoneDrafted a follow-up email for the account owner$0.08 · 7.5s · 4d ago
Asked by Ahmed Al Falasi via Email · model usage 63k 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
Resolve Ticket
DoneRan an approved data query and explained the result$0.04 · 5.4s · 5d ago
Asked by Ahmed Al Falasi via Teams · model usage 22k in, 4k 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
Knowledge SearchResolve TicketService Desk TicketsOperations Runbooks
Is anyone else doing this job?

Felix II already does this job

Felix II holds "Tier-1 Support 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. Extend that agent, or change this description until the two jobs are genuinely different.

Blocked
Felix II

Tier-1 Support Agent

IT & Digital Services · Yasmin Farouk · $5,697 a month across 2,318 tasks

ActiveSame job
100%

Same job: job title, purpose, what it may do all match. Neither title narrows the job to a region or a business line, so both serve the same people.

What matched
Job title
Both hold "Tier-1 Support Agent"
Purpose
The job description is word for word the same
What it may do
Both can knowledge search, create ticket, resolve ticket
What it may read
Both read Service Desk Tickets, Operations Runbooks
Channels
Both reachable on Web portal, Teams, Email
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.

Noor II

Tier-1 Support Agent

IT & Digital Services · Yasmin Farouk · $3,997 a month across 956 tasks

Being builtSame job
100%

Same job: job title, purpose, what it may do all match. Neither title narrows the job to a region or a business line, so both serve the same people.

What matched
Job title
Both hold "Tier-1 Support Agent"
Purpose
The job description is word for word the same
What it may do
Both can knowledge search, create ticket, resolve ticket
What it may read
Both read Service Desk Tickets, Operations Runbooks
Channels
Both reachable on Web portal, Teams, Email
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 hold the same job. All 3 pairings are outright copies, not splits by region or business line. Built in Azure AI Foundry and Codex, so there was nowhere either builder could have looked.

Felix II is the one to keepFelix II scores 6.6 points ahead of Dimitri II, completing 93.7% of 2,318 tasks against 97.6% of 3,602 at $2.46 against $2.90 a task.
MeasureFelix II · keep2,318 tasksDimitri II3,602 tasksNoor II956 tasks
Cost per taskModel usage, running costs and your time, over tasks completed
$2.46●$2.90$4.18
Tasks finished cleanlyRange allows for how few tasks some agents have run
93.7%97.6%●84.5%
Handed back to a personToo close to call: on 3,602 and 2,318 the two ranges still overlap
8.1%7.3%16.7%
How people rate itHeld toward the average across your agents of 4.2 until 8 people have rated it
4.75 of 5●3.42 of 54.02 of 5
Checks passingToo close to call: on 198 and 159 the two ranges still overlap
86%92%88%
Review scoreQuality, accuracy, sticking to the source and safety from the last review, averaged
9497●68
Your time per 100 tasksApprovals, handbacks and review time, in hours of your people
2.7 h●3.2 h4.6 h
Value returned per dollarTime it saved, valued at the hourly rate of the people it saved it for, over full cost
3.9×●0.6×1.7×
OverallRanked on the cautious end of every range, so an agent has to do the work to win. Comparable inside this group only.
92.5Strong85.9Strong63.2Moderate

When it went wrong

Nothing has gone wrong.