Mubadala
Hire an agent

Ravi II

ActiveRunningSome care

Access Request Reviewer: APAC · Lead · IT & Digital Services

Reviews access requests against role definitions and provisions the ones that match cleanly.

Built inMicrosoft 365 CopilotRules apply liveReports to Yasmin Farouk · Head of ITHired 21 Feb 2025 · 18 months of serviceVersion 2.9.12 · last active 3h ago
Request a change
Tasks a month
292
19 people served
Finished cleanly
100%
Hands back to a person on about 1 in 10 tasks
Costs to run
$83
Model usage and the systems behind it
Your time
$528
6 hours checking its work
Value returned
$5,900
9.7× everything it costs
How people rate it
4.1 / 5
Usually answers in about 10 seconds

What you can do about it

PromoteNeeds approval

Already at the top of the ladder

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 Opus 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

0510152006-1507-0507-2508-13
$0.00$1.25$2.50$3.75$5.0006-1507-0507-2508-13

Performance review · 2026 Q2

Reviewed by Yasmin Farouk

Above the bar
Quality of its work
98
Accuracy
96
Stuck to the source
97
Safety
92
Even-handedness
85
Speed of reply
20
Value for money
18
Checks still passing111 of 119
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$423.6912.1s
Claude Sonnet 599$254.218.7sRuns on this now
Claude Haiku 4.596$84.745.3s
Falcon-70B (self-hosted)91$21.188.7s

What it did

Full audit log
DoneProduced the weekly variance commentary$0.21 · 4.5s · 6h ago
Asked by Salem Al Dhaheri via Web portal · model usage 67k in, 430 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
Provision AccessKnowledge SearchCreate TicketCorporate Policy Library
DoneAnswered a policy question and cited the source clause$0.09 · 6.3s · 15h ago
Asked by Ibrahim Al-Sayed via Other systems · model usage 14k 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
Provision AccessCreate TicketKnowledge Search
Handed backRequest outside what it was built for$0.02 · 5.5s · 19h ago
Asked by Layla Al Mazrouei via Other systems · model usage 5k in, 319 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
Corporate Policy LibraryService Desk Tickets
DoneRan an approved data query and explained the result$0.10 · 3.7s · 22h ago
Asked by Layla Al Mazrouei via Web portal · model usage 30k in, 546 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 SearchProvision AccessCreate TicketService Desk TicketsCorporate Policy Library
DoneReviewed a contract against the clause playbook$0.27 · 2.6s · 1d ago
Asked by Yasmin Farouk via Other systems · model usage 71k 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
Create TicketKnowledge SearchProvision Access
DoneDrafted a follow-up email for the account owner$0.23 · 2.1s · 2d ago
Asked by Salem Al Dhaheri via Web portal · model usage 55k 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
Provision AccessKnowledge SearchCreate TicketService Desk TicketsCorporate Policy Library
DoneProduced the weekly variance commentary$0.08 · 3.0s · 6d ago
Asked by David Novak via Web portal · model usage 23k in, 833 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
Provision AccessCreate TicketKnowledge SearchCorporate Policy Library
DoneReviewed a contract against the clause playbook$0.18 · 2.7s · 6d ago
Asked by Peter Lindgren via Other systems · model usage 50k 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
Corporate Policy LibraryService Desk Tickets
Is anyone else doing this job?

Wren II does overlapping work

Wren II holds "Access Request Reviewer" 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 APAC, so the group agent already serves those users. Talk to Grace Adeyemi before a second one is built.

Needs a decision
Wren II

Access Request Reviewer

IT & Digital Services · Grace Adeyemi · $913 a month across 170 tasks

ActiveOverlaps
78%

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

What matched
Job title
Both hold "Access Request Reviewer"
Purpose
The job description is word for word the same
What it may do
Both can provision access, knowledge search, create ticket
What it may read
Both read Corporate Policy Library, Service Desk Tickets
Channels
Both reachable on Web portal, Other systems
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.

Kofi II

Access Request Reviewer

IT & Digital Services · Grace Adeyemi · $1,171 a month across 340 tasks

ActiveOverlaps
78%

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

What matched
Job title
Both hold "Access Request Reviewer"
Purpose
The job description is word for word the same
What it may do
Both can provision access, knowledge search, create ticket
What it may read
Both read Corporate Policy Library, Service Desk Tickets
Channels
Both reachable on Web portal, Other systems
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.

Saoirse II

Access Request Reviewer: Retail

IT & Digital Services · Yasmin Farouk · $334 a month across 0 tasks

ActiveOverlaps
62%

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

What matched
Job title
Both hold "Access Request Reviewer"
Purpose
The job description is word for word the same
What it may do
Both can provision access, knowledge search, create ticket
What it may read
Both read Corporate Policy Library, Service Desk Tickets
Channels
Both reachable on Web portal, Other systems
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

4 agents in IT & Digital Services hold the same job. 1 of the 6 pairings is an outright copy rather than a split by region or business line. Built in Codex and Microsoft 365 Copilot, so there was nowhere either builder could have looked.

Ravi II is the one to keepRavi II scores 17.2 points ahead of Wren II, completing 100.0% of 292 tasks against 100.0% of 170 at $2.09 against $5.37 a task.
MeasureRavi II · keep292 tasksWren II170 tasksKofi II340 tasksSaoirse II0 tasks
Cost per taskModel usage, running costs and your time, over tasks completed
$2.09$5.37$3.44too few tasks
Tasks finished cleanlyToo close to call: on 292 and 170 the two ranges still overlap
100.0%100.0%75.9%no tasks
Handed back to a personToo close to call: on 170 and 292 the two ranges still overlap
10.3%7.6%19.1%no tasks
How people rate itHeld toward the average across your agents of 4.2 until 8 people have rated it
4.12 of 54.25 of 54.56 of 54.16 of 5
Checks passingToo close to call: on 210 and 119 the two ranges still overlap
93%96%61%62%
Review scoreQuality, accuracy, sticking to the source and safety from the last review, averaged
96956850
Your time per 100 tasksApprovals, handbacks and review time, in hours of your people
2.1 h6.1 h3.4 hno tasks
Value returned per dollarTime it saved, valued at the hourly rate of the people it saved it for, over full cost
9.7×1.0×4.2×0.0×
OverallRanked on the cautious end of every range, so an agent has to do the work to win. Comparable inside this group only.
91.9Moderate74.7Thin69.2Moderate32.4Too few tasks

Wren II, Saoirse II have done too little work to judge on rates. They are ranked on the cautious end of their range, which is why a perfect record on a handful of tasks does not win.

When it went wrong

Nothing has gone wrong.