# Scan: AI Reviewer > GAMMA-Ray v0.0.155 (beta, for review; every rating is experimental). An example GAMMA-Ray beta rating of AI Reviewer: freedom 1, 1, 1, 1 across its configurations; deployment governance not assessed. > Page: https://gamma-ray.sgit.ai/scans/codacy-ai-reviewer/ · Source: data/scans/codacy-ai-reviewer.json Example · beta rating · a product as its vendor documents it · read 2026-11-10 · not seen by the vendor Opt-in pull request reviewer on GitHub that combines Codacy's static analysis with a language model, reads the PR, linked Jira or Linear tickets and repository instructions, and posts a review with a verdict, a summary, test suggestions and inline comments with suggested fixes. It can run automatically on the first review of a PR or on demand (button or public API). A scan of a product as its vendor documents it, not of any one deployment. Made by the report studio: a researcher-assessor, a challenger, then the scorer. Part of the first Portuguese cohort. Built only from Codacy's own public pages (product, documentation, blog, customer stories, legal and security pages). Nothing was tested. If you are the vendor and something here is wrong, the correction will be made and dated. *Figure. The label for this rating; its contents are in the text.* 1 Freedom as shipped Answers 1 Freedom at most Answers 5 Controls it brings as shipped n/a Deployment governance not assessed ## How to read it This is a product, not a deployment. A product has no owner, no policy in force and no mandate until somebody runs it, so it is given **no governance level and no level held**: those belong to a deployment. What a product has is a freedom level for each way it can be configured, and a list of the controls each configuration brings. *Figure. The freedom level of each configuration; the table has the same.* | Configuration | What changes | Freedom | Controls | Turned on by the operator | |---|---|---|---|---| | **As shipped** | AI Reviewer with its documented defaults. | 1 Answers | 5 | nothing | | **Ai reviewer** | An admin has turned on AI Reviewer for the repository or organization; GitHub only, Team and Business plans. | 1 Answers | 6 | it is a vendor's assistant, used as supplied; it works across several domains or systems; it connects to external tools or services across a trust boundary; there is a channel to report problems with it or contest its output | | **Auto first review** | AI Reviewer is on and its Run reviewer setting is Automatically (first review only). | 1 Answers | 5 | nothing | | **Manual review** | AI Reviewer is on and its Run reviewer setting is Manually: each review starts from Run Reviewer or an API call. | 1 Answers | 5 | the person operates: every action is prompted and controlled by them | The same product is a different agent in each row. A rating of a deployment starts by saying which row it is. An indicator with no evidence is reported as not evidenced; it is never read as a no. ## The profile *Figure. One square per indicator, by question; every answer is listed below.* ## The grant: what it can actually do The questions measure what is said about an agent: its purpose, its rules, its controls. The grant is the other half: what its permissions let it do, capability by capability, and what stands in the way of each. This is RiskMandate's measurement, and it depends on the permissions a deployment was given. **Not measured.** Not measured. No deployment shape for this product is published in the capability grammar. ## Seen, and not credited - A page sentence that the reviewer follows review.md Re-read the Codacy AI docs page (fetched 2026-11-10, raw/ans-006.html) and the AI Reviewer product page (raw/ans-008.html): neither says the reviewer obeys or is bound by review.md; the docs say the file helps it understand the code, logic and preferences. The I47 credit no longer rests on that claim. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) - A limit on the reviewer written as a rule in prose (I47) Re-read on 2026-11-10 (raw/ans-009.html). The docs say teams can write custom instructions in a review.md file ('These instructions are specified in a review.md file') that 'help the AI Reviewer understand the structure of the code, the business logic of the project, and your own preferences'; the out-of-scope line is part of an example prompt for drafting that file, and the Learning from your reviews section describes adapting from replies and reactions. No sentence says the reviewer is limited by or must follow the file, so the credit is withdrawn rather than stretched. Whether a team-written instruction file counts as a limit in prose is a question for Dinis. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) ## What its evidence reaches *Figure. The mashup graph with this agent's evidenced indicators lit.* ## Every answer, with its source ### What is the agent built on? - **Available, if the operator turns it on.** It is a vendor's assistant, used as supplied. The AI Reviewer is one of the vendor's optional AI features inside its hosted platform, used as supplied once an admin turns it on. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) (documented) - *Not evidenced.* It runs on an AI platform with the organisation's own data, without executing arbitrary code. - *Not evidenced.* It is configured on a low-code or no-code builder and acts on real organisational data. - *Not evidenced.* It generates and executes code with local or cloud privileges. - *Not evidenced.* It is built in-house: the organisation controls its identity, tools and boundaries. ### Does it act, or only answer and recommend? - *Not evidenced.* It follows fixed rules, with no reasoning. - *Not evidenced.* It retrieves information and recommends actions; a person acts. - *Not evidenced.* It executes actions itself. - **As shipped.** It is in production: a public source names a customer or gives usage figures for what it does on its own. A vendor-published case study names BFI Finance, which switched off its previous AI review tool, and its summary list puts the AI reviewer in daily work for around 170 developers (a team headcount, not a count of reviews); the closing paragraph's list of tools in daily work omits the reviewer. [Source](https://resources.codacy.com/resources/case-study-bfi-finance) (documented) ### How far does it reach? - *Not evidenced.* It works in one domain's data. - **Available, if the operator turns it on.** It works across several domains or systems. The reviewer combines GitHub pull request data, Codacy findings and a linked Jira or Linear ticket. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) (documented) - **Available, if the operator turns it on.** It connects to external tools or services across a trust boundary. The reviewer sends pull request context to OpenAI models through Amazon Bedrock and reads tickets from Jira or Linear, services outside Codacy. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) (documented) ### Does it work with other agents? - *Not evidenced.* Several agents coordinate inside the organisation. - *Not evidenced.* Agents operate across organisational boundaries or disparate stacks. - *Not evidenced.* There is a published protocol or communication layer between agents. - *Not evidenced.* Others build on it: third parties publish integrations, skills or agents for it. - *Not evidenced.* It exposes an agent interface: a published MCP server, an agent card, or an API documented for agents to call. ### What is the person's role? - **Available, if the operator turns it on.** The person operates: every action is prompted and controlled by them. In the Manually mode a person starts each review by clicking Run Reviewer in the pull request summary comment, or by a call to the public API. [Source](https://docs.codacy.com/repositories-configure/integrations/github-integration/) (documented) - *Not evidenced.* The agent suggests; the person reviews and approves each action. - *Not evidenced.* The agent handles routine tasks; the person is consulted on exceptions. - *Not evidenced.* The agent works independently; the person approves critical decisions only. - *Not evidenced.* The agent has full autonomy within boundaries; the person monitors. ### Is what it is for written down? - **As shipped.** Its purpose and permitted tasks are stated in writing. The docs state what the reviewer does: comment on Codacy issues worth attention, summarise the rest, and check changes against requirements and project logic. [Source](https://docs.codacy.com/repositories-configure/integrations/github-integration/) (documented) - *Not evidenced.* Its autonomy limits and the tools it may use are defined. - **As shipped.** Its limits and known failure cases are documented for those who use it. The limits page gives the reviewer's size limit (270,000 tokens or a 1 MB diff) and what it does above it; the Codacy AI docs page says it runs on GitHub only. [Source](https://docs.codacy.com/faq/code-analysis/does-codacy-place-limits-on-the-code-analysis/) (documented) ### Does it have its own identity and only the access it needs? - *Not evidenced.* What it can reach is enumerated: scopes, permissions, tools. - *Not evidenced.* Its authorisation is published as metadata that anyone can read. - **As shipped.** It asks for narrower access than the whole account. The AI Reviewer is a setting of Codacy's GitHub integration; the permissions page lists the Codacy GitHub App's access per scope, with repository contents and metadata read-only and pull requests, checks and issues read and write, and its pull requests row covers creating comments and suggestions. The page does not mention the AI Reviewer: the credit is for the platform's GitHub App, shared by all Codacy features. [Source](https://docs.codacy.com/getting-started/which-permissions-does-codacy-need-from-my-account/) (documented) - *Not evidenced.* It has its own identity, separate from any person's. - *Not evidenced.* Its identity is cryptographic and can be checked by others. - *Not evidenced.* Its tokens are bound to the service they were issued for and are not passed on. ### Is it in a registry, with an owner? - *Not evidenced.* The organisation keeps a registry of its agents. - *Not evidenced.* Each agent has a named owner. - *Not evidenced.* Agents are retired by a defined process. ### Who is accountable for it? - *Not evidenced.* A named executive or body is accountable for the organisation's agents. - *Not evidenced.* Roles and responsibilities for AI risk are documented. ### Is there a policy that governs it? - *Not evidenced.* A governance policy for agents is published. - *Not evidenced.* Agents and use cases are classed by risk. - *Not evidenced.* The laws that apply to it are identified. - *Not evidenced.* New agents pass an approval or review before they run. ### Can a person step in or stop it? - *Not evidenced.* High-impact actions need a person's approval. - *Not evidenced.* There is a way to pause or stop it. - *Not evidenced.* There is a defined escalation path. ### Is what it does logged? - *Not evidenced.* Its actions are logged. - *Not evidenced.* The log is tamper-evident and kept for a stated time. ### Is it watched while it runs? - *Not evidenced.* It is monitored in operation. - *Not evidenced.* Anomalies are detected in real time and raise alerts. ### What stands between it and what it should not do? - *Not evidenced.* A limit on it is enforced by something outside its own reach. - *Not evidenced.* A limit on it is a setting that its own account could change. - *Not evidenced.* A limit on it is a rule in prose. - *Not evidenced.* Policy is enforced as machine-readable rules. - *Not evidenced.* The difference between what it can reach and what it is for is stated. ### Is it tested, and are the results shown? - *Not evidenced.* Test or evaluation results are published. - *Not evidenced.* It is tested for safety and security, including by attack. - *Not evidenced.* People who did not build it take part in assessing it. ### What happens when it goes wrong? - *Not evidenced.* There is an incident process for agents. - *Not evidenced.* Incidents and errors are communicated to those affected. - *Not evidenced.* There is a plan for a failure of a third party it depends on. ### Do people know it is an AI, and can they answer back? - *Not evidenced.* It tells the people it talks to that it is an AI. - **Available, if the operator turns it on.** There is a channel to report problems with it or contest its output. People can contest a review comment by replying in the pull request, and the reviewer learns from those replies and reactions. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) (documented) - **As shipped.** It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card. An llms.txt resolves at codacy.com and an OpenAPI 3.0.1 description resolves at api.codacy.com/api/api-docs/swagger.yaml; both are the vendor's platform-wide files, in which the AI Reviewer is one entry. [Source](https://www.codacy.com/llms.txt) (observed) ### What data does it use, and under what rules? - **As shipped.** The data it uses is described. The docs list the context sent to the model, what Codacy stores and does not store, and that secrets are redacted before sending. [Source](https://docs.codacy.com/codacy-ai/codacy-ai/) (documented) - *Not evidenced.* There are data quality rules for what it reads. - *Not evidenced.* Its privacy risk has been examined. ### What does it depend on from others? - *Not evidenced.* The models and third-party components it uses are listed. - *Not evidenced.* Third-party components are monitored and have risk controls. ### Has anyone independent checked? - *Not evidenced.* A public certificate or audit report covers it. - *Not evidenced.* Compliance evidence is produced continuously, ready for a regulator. ### Is the organisation behind it ready? - *Not evidenced.* There is a stated strategy for agents. - *Not evidenced.* The people who work with it are trained. - *Not evidenced.* Its value is measured. - *Not evidenced.* It is improved on a regular cycle. - *Not evidenced.* The organisation's risk management covers agents. ## The vault This rating, its evidence list, its grant and the questions it was made against are kept in a public sgit vault (`u6a01jwq`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_af2cc62b777e2d6af5fdb41b6ec2899e95fe143c11859904fa56fbedea727f2f:u6a01jwq` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_af2cc62b777e2d6af5fdb41b6ec2899e95fe143c11859904fa56fbedea727f2f:u6a01jwq`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.