Other AI reviewers guess. We verify.

Connect a repository and review pull requests inside GitHub. Findings include evidence so you can check the issue before you change the code.

Sign-in is handled by WorkOS, our identity provider. You'll see an authkit.app address.

We lead the field on real defects.

Public board comparison

Board snapshot, (trailing month)

ReviewerF1PRF0.5
Projection
Veridicalprojected
6475.855.370.6
Public board listings
Gemini Code Assist
59.272.949.866.7
Greptile
57.174.546.366.4
Claude
55.864.149.360.5
CodeRabbit
55.064.947.760.5
Cubic Dev AI
54.071.843.363.4
Cursor
52.773.741.063.6
Qodo
48.862.340.256.1
GitHub Copilot
48.462.039.655.7

Veridical is a projection. Other rows are published board scores. F0.5 is calculated from precision and recall. Source: public board

On the same pull requests, Veridical scored F1 67-72 on real defects, versus 50-58 for the three tools tested. The leaderboard uses a different measure: our F1 64 is a projection, not a live listing.

See exactly what we caught

Not a wall of suggestions. The handful of findings that would have 500'd a request or leaked a tenant - each posted on the line, with the failing input that proves it.

A different catch every few seconds

Each one a confirmed bug - the failing input that proves it and a safe-to-merge read-out, posted inline. Data loss, auth leaks, crashes, races.

github.com/discourse/discourse
Auth disclosureblocking

app/models/topic_link_click.rb:95

Veridicalbot

A link-click fallback returns a stored link’s URL without re-running the visibility check - a user can confirm and obtain redirect URLs for links inside private topics they cannot access.

verifiedcreate_from(mismatched post/topic) → returns link.url, no can_see? check
safe-to-merge0.11

gate requires ≥ 0.95 to merge

Real catches · hover to pause

The verdict on the PR

Every finding ranked by what it costs you, behind one gate you can merge against.

Veridical · 2 findings · 1 blocking
Blocked - 1 unresolved regression
14 files reviewed+218 −96ranked worst-first

Link-click fallback skips the visibility check

app/models/topic_link_click.rb:95Auth disclosure

create_from(mismatched post/topic) → returns link.url, no can_see?

0.12

Visibility guard silently drops valid clicks

app/models/topic_link_click.rb:107Silent data drop

link.post == nil on a public topic → create_from returns nil

0.40
Gate: safe-to-merge ≥ 0.95currently 0.18

PR summary · gated on safe-to-merge

One number your merge policy can use.

Every review carries an evidence-backed advisory score. Your repository owns the threshold and the merge decision, while Veridical supplies the findings, execution evidence, and exact-head check.

Merge box · GitHub
github.com/getsentry/sentry/pull/118240
j-rivera wants to merge 2 commits intomain

Some checks were not successful

1 failingand3 successful checks

  • CI / build(20.x)Successful
  • CI / unit342 passedSuccessful
  • CI / lintno problemsSuccessful
  • Veridical / safe-to-merge1 counterexampleFailing
Veridicalsafe-to-merge
0.18

HOLD - safe-to-merge 0.18counterexample attached

ConfigStore.get('signupLocalities') === undefined → .includes() throws

Merging is blocked - a required check is failing.

Illustrative mockup

.veridical.ymlmain
.veridical.ymlYAMLvalid
1version: 123# Gate the merge button on a calibrated score4auto_merge:5 gate: safe-to-merge >= 0.956 require_clean_ci: true78# Hold & comment on anything below the bar9on_hold:10 attach_counterexample: true11 block_merge: true12 comment: "veridical/findings"
required check activegate ≥ 0.95YAML · LF · UTF-8

Illustrative configuration

Straightforward pricing.

Choose the review capacity your work needs. Start free, or upgrade for more reviews and repository tools.

One workspace, one owner. Upgrade when you need repository-wide tooling.

Launch tier

Free

Evidence-backed pull-request reviews for public and private repositories.

$0

per workspace

Reviews only · no card required

Start free

5

reviews / month

The first 50 workspaces to connect a repository qualify.

What's included

  • Public and private GitHub repositories
  • Exact-head GitHub review
  • Verified inline findings
  • Complete review summary and verdict
  • Review history and evidence receipts

Standard

Production pull-request reviews without the wider repository operations suite.

$39

/month

Choose Standard

15

reviews / month

100,000 reviewed lines included monthly across connected repositories.

Review credit and size limits

What's included

  • Exact-head GitHub review
  • Verified inline findings
  • Complete review summary and verdict
  • Review history and evidence receipts

Pro

Recommended

Higher review capacity plus the repository, security, and support tools around each change.

$69

/month

Choose Pro

40

reviews / month

270,000 reviewed lines included monthly across connected repositories.

Review credit and size limits

What's included

  • Everything in Standard
  • Manual and scheduled codebase scans
  • Repository knowledge and code graph
  • CLI early access (work in progress)
  • 24/7 priority support

Sign-in is handled by WorkOS, our identity provider. You'll see an authkit.app address.

Free reviews and app access for open source projects.

Open-source projects start on Launch: 5 reviews a month per workspace, for public and private repositories, for the first 50 workspaces. No card is required. A separate per-project grant opens only after Launch fills.

See the open-source path

How plan allowances work

What counts toward the monthly allowance?View
Each completed pull-request review counts toward the monthly review allowance shown on its plan. On paid plans, the count depends on pull-request size: a normal pull request counts as 1 review, a large one as 2, and a very large one as 3. Each review's GitHub check says how many reviews it used. If the remaining allowance cannot cover a pull request, no review runs and nothing is charged. Launch and open-source grants have their own allowances.
Are reviewed lines also limited?View
Each paid plan's reviewed-line allowance has room for every included review at the very large size (up to 20,000 lines, counted as 3 reviews), so it never runs out before your monthly reviews do. These line allowances are included monthly:
  • Standard: 100,000 reviewed lines.
  • Pro: 270,000 reviewed lines.
  • Team Standard: 100,000 reviewed lines per seat.
  • Team Pro: 270,000 reviewed lines per seat.

Team plans require at least three seats and pool capacity.

What does the free Launch tier include?View
5 reviews per workspace each UTC calendar month, shared across all connected public and private repositories. Launch is review-only: repository scans, repair workflows, and the wider Pro suite are not included. The allowance does not grow when you connect more repositories.
What pull-request sizes are supported, and how do they count?View
On paid plans, the size of a pull request sets how many reviews it uses from the monthly allowance.
Normal
Up to 2,000 lines, 50 files, and 256 KiB
Counts as 1 review
Large
Up to 8,000 lines, 200 files, and 1 MiB
Counts as 2 reviews
Very large
Up to 20,000 lines, 500 files, and 2.5 MiB
Counts as 3 reviews
Beyond
A clear, capped quote before the review starts
Do credits roll over?View
Credits refresh each month and do not roll over. There is no automatic overage. Change seats or contact us before you need more pooled capacity.