Code Review

Code review that protects against slop

Every coding agent writes code differently, and not all of it is good. Ellipsis reviews every pull request, from any agent or engineer, and catches real bugs before they merge.

Install on GitHubDocumentation
Comments posted by severity
Last 30 days · beaconhq · 1,068 comments
Median review 2m
4003002001000
58
196
372
318
124
Blocking
High
Medium
Low
Trivial
68%code suggestions applied after merge
54%comment regions later edited
12%@ellipsis asked to fix

Accuracy

Feedback that lands

Ellipsis measures whether review comments changed the merged code, not just how many comments were posted.
May 20Jun 3Jun 18
BlockingHighMediumLowTrivial

Severity

Volume by severity

See review volume over time, stacked by blocking, high, medium, low, and trivial findings.
Blocking88% addressed
High74% addressed
Medium59% addressed
Low41% addressed
Trivial22% addressed

Calibration

Know which severities actually get fixed

For each severity, the share of posted comments that were acted on: the flagged issue resolved on the default branch after merge. Blocking and high findings should land far more often than nits, and they do.
Logical bug24%
Style19%
Security14%
Performance12%
Maintainability11%
Testing9%
Docs7%
API design4%

What it catches

A full breakdown of comment types

Every comment is classified (logical bugs, security, performance, maintainability, testing, style, and more) so you can see whether Ellipsis is catching substance or just nits. For Beacon, bugs and security lead the mix.
BlockingHighMediumLowTrivial
Logical bug82241183
Security6141971
Performance2924162
Maintainability0318339
Testing0211216
Style0042824

Where issues concentrate

Severity by type, at a glance

The heatmap crosses every comment type with its severity. Darker cells mean more findings, so you can instantly see where the serious problems cluster: logical bugs skew high, style skews trivial.
Surfaced1,840 · 100%
Passed the gate↓ 74%1,360 · 74%
Posted to GitHub↓ 73%990 · 54%
Addressed↓ 62%612 · 33%

From found to fixed

Follow comments through the whole funnel

Track where comments drop off: findings surfaced by the agent, those that pass the quality gate, the ones posted to GitHub, and finally the ones addressed after merge. A tight funnel means high signal and low noise.