PAY-1502Refund emails sent once1 of 3 criteria metSam Carter
Reporting and metrics
Where the work is, where it waits, and what your review bots are worth.
Bots and people are counted apart.
No leaderboards, no developer scorecards.
One stated window
Reports' headline figures cover one window: this sprint so far if you work in sprints, otherwise the last 7 or 14 days. Anything else, such as right now or the last 12 weeks, says so in its heading.
Each tile opens the pull requests behind its figure.
This sprint so far
Right now
Open pull requests33
Red checks now1
Last 12 weeks · pull requests opened and merged
OpenedMerged
Every sprint or month on one chart
Fifteen measures for each sprint of the last 12 weeks, or each month of the last 6. Compare any of them on one chart, as the change from their first period.
Merged PRsBot review comments
Oct 15 – Oct 29 · people against automation
PRs merged53
Review comments635
Approvals34
PeopleAutomation
Stays the same
Every figure counts only what happened inside its window, so a period reads the same next month.
Same repositories
Every period is measured over the repositories tracked since the first one shown, so adding a repo isn't growth.
No guessing
No projection for calendar months: they aren't the same length. Where the data can't support a number, it says so.
Where every hour goes
Every hour a pull request is open belongs to someone: a reviewer, the author, or the merge, once it's approved.
Counted in your team's working hours, against time budgets you can change. Bots never move the ball. Pull requests opened by automation, or that no person touched, are left out, and the page says how many.
Where the working hours went
Balanced
23
approved on the first review
of 41 merged pull requests
Approved on the first review, last 12 weeks
36%Waiting for a reviewer31%Waiting for the author33%Approved, waiting to merge
Each wait against its time budget
Within budgetAcceptablePast limitThree in four finished
42 min to merge half of pull requests in October, from about 7 h in September
Faster reviews, fewer bottlenecks
On a nine-repository delivery team, Limn took over the reviews in October. Half of their pull requests now merge within an hour of working time, and twice as many land each week. It cost them nothing extra.
Measured by Limn's Chronology report: merged pull requests by people, working hours, September vs October 2026 after Limn auto-review introduced.
Hours saved, in dollars
Add an optional hourly cost and the working hours saved also read as an estimate in US$. Until you set one, it stays blank.
Where the working hours went
Waiting for a reviewerWaiting for the authorApproved, waiting to merge
Each wait against its budget
First look
Reply to review
Approved to merged
Opened to merged
Within budgetAcceptablePast limitToo few to judge
Over 26 weeks
Where the hours went each week, each wait against its budget, and the working hours saved. Markers show when a repo joined, a setting changed or a bot arrived.
Open a marker to compare before and after.
Where the work is happening
Which repositories carry the work, and how far each merged change could reach. Unknown is never shown as zero.
| Repository | Opened | Lines changed |
|---|---|---|
| acme/payments | 14 | 3.3k |
| acme/web | 11 | 2.1k |
| acme/api | 9 | 1.5k |
| acme/ledger | 5 | size unknown |
PeopleAutomationLines changed
| Repository | Merged | Low | Medium | High |
|---|---|---|---|---|
| acme/payments | 0 | 4 | 2 | |
| acme/web | 2 | 0 | 3 | |
| acme/api | 3 | 1 | 1 | |
| acme/ledger | 0 | 1 | 0 |
LowMediumHigh
What your bots are worth
Bot comments graded nit, minor, major or critical by Limn's own model, on your own machine.
On 300 bot comments, the model agreed with an independent grader 70% of the time. CodeRabbit’s own label agreed 47% of the time, on the ones it labelled.
What each bot costs per comment your team acted on.
Findings502
High severity49%244 major or critical
Nits30%152 trivial or optional
Top topicCorrectness117 findings
A row per bot
| Bot | Threads | Used | Not addressed | Severity mix | High |
|---|---|---|---|---|---|
| 132 | 58% | 55 | 44% | ||
| 125 | 61% | 49 | 54% | ||
| 41 | 80% | 8 | 51% | ||
| 41 | 59% | 17 | 44% |
CriticalMajorMinorNit
How each bot compares with the same bot in similar-sized public repositories, or a plain sentence saying why it can't. Cost is per workspace and never added up across workspaces.
For a bot whose comments your team rarely acts on, it says what turning it off would save in a year.
CostUS$30.00 a monthPrice you entered
Per merged PRUS$0.51From your own data
Per comment your team usedUS$0.45From your own data
Your team used 52% of what it said. Teams with similar repos used 74%.
Where these numbers come from
| Repository | Size group | Acted on |
|---|---|---|
| acme/api | Band 3 of 10 | 25% |
| acme/payments | Band 7 of 10 | 59% |
| acme/web | Band 6 of 10 | 52% |
This Sprint
The sprint by theme, critical path or person, on your tracker's own status columns. Jira, Linear or GitHub Issues. Limn writes nothing back.
Themes and critical paths are written by your own AI agent.
Refunds
PAY-1421Partial refunds3 of 4 criteria metDana Wu
PAY-139Refund reasons in the export2 criteriaPriya Nair
Ledger
PAY-1583Retire the nightly ledger job2 criteriaTom Becker
PAY-1463Rename ledger tables1 of 3 criteria metPriya Nair
PAY-148Index ledger by day3 of 3 criteria metWei Zhang
On a critical pathOn a path and waiting
See your own numbers
One command. No account.
npx limn-review