Skip to content
← All projects

AI/ML · Full Stack

ReviewPilot

Multi-tenant GenAI code-review SaaS

Status
Complete
Year
2026
Live application
Runs locally with Docker Compose. Billing is a mock; not publicly deployed.
Review detail page with findings on a diff
deterministic review rules
17
deterministic review rules
tenant roles with server-side enforcement
4
tenant roles with server-side enforcement
automated tests across layers
123
automated tests across layers

01 Problem

AI code review is only useful if findings point at real code. ReviewPilot runs 17 deterministic rules first, then a grounded model pass whose findings must quote the exact diff lines they reference. Usage is metered against plan limits in a multi-tenant SaaS shell.

02 Product overview

A NestJS API with session auth and tenant guards accepts diffs by paste, upload or HMAC-signed webhook. A BullMQ worker runs the review pipeline (parse, static rules, model, validate, persist) and streams progress over SSE. Findings can be triaged, commented on, compared across versions and exported to JSON, CSV, Markdown or SARIF 2.1.0.

Implemented

  • Organizations with Owner, Admin, Reviewer and Viewer roles; email-bound invitations; audit log
  • Cross-tenant access returns 404, never 403
  • 17 deterministic rules followed by a grounded model pass, streamed over SSE
  • Triage (accept, dismiss, false positive, reopen), comments, versions and compare
  • Export to JSON, CSV, Markdown and SARIF 2.1.0
  • Plan limits, usage metering, org API tokens, idempotent submissions and retention

Planned, not yet built

  • MFA / SSO
  • Real billing provider
  • Production mail transport
  • Git-host write-back
  • Cloud deployment

03 System architecture

Next.jsdashboard · triageCI webhookHMAC-signedNestJS APIauth · tenant guardBullMQreview jobsOrchestratorrules → model → validatePostgreSQLPrismaRedisqueue · pub/subOllamaqwen3:4b
Rules run first; the model's findings are kept only if they quote the diff lines they cite.clientservicestoremodelqueue

04 Core technologies

Backend

  • NestJS
  • Prisma
  • PostgreSQL 16
  • BullMQ
  • Redis 7
  • Zod
  • argon2id

AI

  • Ollama (qwen3:4b-instruct)
  • Grounding validator

Frontend

  • Next.js 16
  • React 19
  • TanStack Query
  • Tailwind 4
  • Plotly

Quality

  • Vitest
  • Playwright
  • GitHub Actions
  • gitleaks

05 Engineering challenges

A validator that was too strict

The first grounding validator rejected all five suggestions from the model. After fixing how quotes were matched, four were kept and one was correctly rejected.

Failing safely

If the model is unavailable, reviews degrade to rule-only results instead of failing.

Tenant isolation

Cross-tenant requests return 404 so resource existence is never leaked.

06 Technical decisions

  1. 01Server-side sessions instead of JWTs
  2. 02Rules first, model second, and the model must quote the diff
  3. 03Custom unified-diff viewer instead of Monaco
  4. 04A labelled fixture LLM for deterministic tests

07 Verified test results

Backend unit
43
Backend integration (real Postgres + Redis)
63
Frontend unit
8
Playwright
9

Latest GitHub Actions run on main: passing. Counts as reported in the repository's README and testing docs.

08 Screenshots

Review detail page with findings on a diff
Review detail with grounded findings
Finding evidence and triage controls
Evidence quoting the diff, with triage
Review page in dark theme
Dark theme
Live review progress streamed over SSE
Live progress over SSE

Screenshots captured from the running application and published in the repository's docs.

09 Links

No public deployment. Runs locally with Docker Compose. Billing is a mock; not publicly deployed.