Skip to content

Excellent vs GitHub Copilot code review: the review you are already paying for

The reviewer already in your plan, versus evidence from checks that actually ran.

curl -fsSL https://excellent.so/install.sh | sh
Jump to comparison

GitHub Copilot code review in one line

GitHub's built-in AI reviewer. Copilot reviews a pull request with full project context and can pass suggestions to the Copilot cloud agent. It is included with the paid Copilot plans.

Best for
Almost every team, as a floor. It is already in the plan, already in the pull request, and costs nothing extra to switch on.
Limits
It reads code. GitHub's own docs describe the agentic part as gathering project context and handing suggestions to the cloud agent, not running your tests. CodeQL and coverage come from GitHub Code Quality, a separate feature, not from the reviewer.
Stronger than us at
Distribution, and it is not close. Zero setup, no new vendor, no new invoice, and it lives exactly where the developer already works. For a lot of teams that clears the bar on its own.
Price 2026-09-23
Included with paid Copilot (Pro, Pro+, Business, Enterprise)

Excellent in one line

A verification system for agentic tasks. It records what the agent attempted, runs your checks against the claim, and binds the result to evidence you can open.

Best for
Teams that want agent work checked before they trust or promote it.
Limits
There is no hosted option. You run it on your machines. Verification evidence stays on the machine that produced it and does not sync to teammates yet. No SSO, and no Mac app has shipped. It does not write tests, and it does not review your diff.
Stronger than them at
Keeping the attempt record, running your own checks as the oracle, and trialling prompt, model and tool changes on held-out work from your repository.
Price 2026-09-23
Free to install and run (Consulting from $10,000 / month)

The capabilities that decide it

Capability by capability, with GitHub Copilot code review on the left and Excellent on the right. Prices are the vendor's own, read on 2026-09-23.

CapabilityGitHub Copilot code reviewExcellent
Runs your tests and buildNoYes
Costs nothing extra if you already pay for CopilotYesFree to install and run
Records each agent attempt and the claim it madeNoYes
Independent of the agent that wrote the codeSame vendor as the Copilot coding agentSeparate from the agent and from its completion claim
Deterministic analysisCodeQL and coverage come from GitHub Code Quality, a separate featureYour own tests, builds, browser checks and CI are the oracle
Tests prompt, model and tool changes on held-out workNoYes
Published price (checked 2026-09-23)Included in Copilot Pro, Pro+, Business and Enterprise; not in Free. GitHub estimates a review consumes $0.05–$1 of AI credits on “Lite” effort and $0.25–$5 on “Balanced”.Free to install and run. Consulting starts at $10,000 / month.

When to pick which

Leave Copilot code review on. Relative to what you already spend it is free, and it catches things. Add Excellent when someone asks you to prove it: a check that ran, an artifact you can open, and the record of every attempt that got there.

Pick GitHub Copilot code review if

Almost every team, as a floor. It is already in the plan, already in the pull request, and costs nothing extra to switch on.

Add Excellent if

You want agent work captured as attempts, checked against evidence you can open, and promoted only when the result is defensible to someone outside the team.

Trust the evidence, not the agent's word

curl -fsSL https://excellent.so/install.sh | sh