Question 1

What is Modak?

Accepted Answer

Modak is an AI code reviewer for GitHub. It installs as a GitHub App, reviews every pull request in shadow mode using 8 specialist personas, and calibrates its verdicts against your team's actual approvals on a per-persona, per-path-tier basis. Auto-merge is a per-path opt-in, earned after the calibration matrix clears a threshold.

Question 2

How is Modak different from CodeRabbit, Greptile, or Bugbot?

Accepted Answer

Generalist AI review bots post a single comment per PR and leave threshold tuning to the user. Modak votes 8 specialists per path tier, exposes a per-team calibration dashboard, and earns auto-merge rights one path at a time. The defensible surface is per-team, per-path trust — a calibration artifact nobody else ships, because auto-merge is a liability unless you have done the math.

Question 3

Will Modak work on a small repo with 30 PRs a week?

Accepted Answer

Yes. The primary calibration signal is human approve or request-changes labels under shadow mode, not reverts. At 30 PRs a week you accumulate roughly 120 labels a month against persona verdicts. Most path tiers clear the 30-label hold threshold in 4 to 8 weeks.

Question 4

Does Modak train on my code?

Accepted Answer

No. Model calls run on the Anthropic API under zero-retention enterprise terms — nothing from your diffs is retained by the model provider and nothing is used for model training. ProductLove, Inc. does not use your diffs to train or improve persona prompts, the calibration model, or anything shared across customers. PII is redacted before any model call.

Question 5

What happens if an auto-merged PR gets reverted?

Accepted Answer

The revert signal is attributed per persona and per path tier. The personas whose confidence contributed most to the bad call get their weight on that path tier docked. The threshold on that tier rises on the next weekly recalibration. If revert-rate on any auto-merge-enabled path exceeds 2% in a rolling 28-day window, Modak flips that path back to shadow and posts an incident to Slack.

Question 6

Do I have to turn on auto-merge to get value?

Accepted Answer

No. The calibration dashboard alone is sellable. 'Here is where our AI reviewer tracks our senior engineers, broken out by path' is a useful artifact for any engineering org. Plenty of teams live on Pro forever with every path in shadow.

Question 7

How much does Modak cost?

Accepted Answer

Free forever on one repo in shadow mode. Pro is $49 per repo per month with path-by-path auto-merge. Team is $199 per month for up to 10 repos with SSO and SIEM audit stream. Enterprise is custom and includes SOC 2 Type II and air-gapped deploy.

Question 8

How is Modak related to The Collective?

Accepted Answer

Modak is part of The Collective — a ProductLove, Inc. product. It's designed to be adopted standalone, without using the rest of the Collective platform. We prove this by using Modak at The Collective exactly the way you'd use it: we install the GitHub App, sign up on modak.sh, pay per repo, and get value from the calibration matrix. If you're already a Collective client, bundled access is available on Team and Enterprise plans.

Question 9

Can it review Dependabot or AI-authored PRs?

Accepted Answer

Yes. Bot-authored and AI-authored PRs go through the identical decision path. Modak doesn't know or care how a diff was written — it reviews the diff. Dependency bumps that don't touch FORBIDDEN paths and pass persona review will be auto-merge eligible on the same per-path terms as human PRs.

Data Processing Addendum

Sub-processors

Data residency

Contact