Rosa II
ActiveRunningRoutineKnowledge Base Curator: Retail · Junior · IT & Digital Services
Turns repeatedly-resolved tickets into knowledge articles and retires stale ones.
What you can do about it
Timesheet
Tasks and what they cost, per day, last 60 days
Performance review · 2026 Q2
Reviewed by Yasmin Farouk
Does the job it was given. Sticks to the source less well on long documents, worth narrowing what it reads.
Could another model do this job better?
| Model | Quality | Cost per 1,000 tasks | Answers in | |
|---|---|---|---|---|
| Claude Opus 5 | 97 | $189.30 | 6.1s | |
| Claude Sonnet 5 | 96 | $113.58 | 4.4s | Runs on this now |
| Claude Haiku 4.5 | 84 | $37.86 | 2.7s | |
| Falcon-70B (self-hosted) | 83 | $9.47 | 4.4s |
What it did
DoneSummarised a 34-page document into a one-page brief$0.26 · 1.9s · 1d ago
- 1. Read the request and worked out what kind of task it was
- 2. Found 6 possible passages, kept the 3 close enough to use
- 3. Drafted the answer and attached where each part came from
- 4. Checked its own claims back against those passages
FailedFound no documents it is allowed to read$0.14 · 4.6s · 2d ago
- 1. Read the request and worked out what kind of task it was
- 2. Called the system it depends on
- 3. Tried again three times, all three failed
- 4. Reported the failure back to whoever asked
DoneSummarised a 34-page document into a one-page brief$0.20 · 2.1s · 3d ago
- 1. Read the request and worked out what kind of task it was
- 2. Found 6 possible passages, kept the 3 close enough to use
- 3. Drafted the answer and attached where each part came from
- 4. Checked its own claims back against those passages
DoneRan an approved data query and explained the result$0.11 · 738ms · 4d ago
- 1. Read the request and worked out what kind of task it was
- 2. Found 6 possible passages, kept the 3 close enough to use
- 3. Drafted the answer and attached where each part came from
- 4. Checked its own claims back against those passages
DoneGenerated the shift handover pack$0.09 · 4.4s · 6d ago
- 1. Read the request and worked out what kind of task it was
- 2. Found 6 possible passages, kept the 3 close enough to use
- 3. Drafted the answer and attached where each part came from
- 4. Checked its own claims back against those passages
Petra II does overlapping work
Petra II holds "Knowledge Base Curator" in IT & Digital Services and is doing the work on a trial. Job title, purpose, what it may do, what it may read, department and channels match. One covers the group, the other only Retail, so the group agent already serves those users. Talk to Andreas Wolff before a second one is built.
Knowledge Base Curator
IT & Digital Services · Andreas Wolff · $3,383 a month across 1,303 tasks
Already covered by a group-wide agent. One covers the group, the other only Retail, so the group agent already serves those users.
What matched
- Job title
- Both hold "Knowledge Base Curator"
- Purpose
- The job description is word for word the same
- What it may do
- Both can knowledge search, generate document
- What it may read
- Both read Service Desk Tickets, Operations Runbooks
- 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.
Knowledge Base Curator: Wholesale
IT & Digital Services · Grace Adeyemi · $224 a month across 31 tasks
Same role, split by scope. Scoped to Retail and Wholesale respectively.
What matched
- Job title
- Both hold "Knowledge Base Curator"
- Purpose
- The job description is word for word the same
- What it may do
- Both can knowledge search, generate document
- What it may read
- Both read Service Desk Tickets, Operations Runbooks
- 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.
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 Wholesale, so the group agent already serves those users. Built in Copilot Studio and Codex, so there was nowhere either builder could have looked.
| Measure | Rosa II · keep1,282 tasks | Samir II31 tasks | Petra II1,303 tasks |
|---|---|---|---|
Cost per taskModel usage, running costs and your time, over tasks completed | $2.19● | too few tasks | $2.60 |
Tasks finished cleanlyToo close to call: on 1,282 and 31 the two ranges still overlap | 95.2% | 100.0% | 79.7% |
Handed back to a personToo close to call: on 1,282 and 31 the two ranges still overlap | 7.3% | 9.7% | 25.6% |
How people rate itHeld toward the average across your agents of 4.2 until 8 people have rated it | 4.20 of 5 | 4.14 of 5 | 4.58 of 5● |
Checks passingToo close to call: on 90 and 118 the two ranges still overlap | 95% | 89% | 99% |
Review scoreQuality, accuracy, sticking to the source and safety from the last review, averaged | 91 | 92● | 67 |
Your time per 100 tasksApprovals, handbacks and review time, in hours of your people | 2.3 h● | 8.1 h | 2.8 h |
Value returned per dollarTime it saved, valued at the hourly rate of the people it saved it for, over full cost | 1.5× | 0.6× | 1.8×● |
OverallRanked on the cautious end of every range, so an agent has to do the work to win. Comparable inside this group only. | 91.4Strong | 77.4Too few tasks | 64.1Strong |
Samir 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.