BETA · GAMMA-Ray is published for review. The rules, the mapping and every rating here are experimental and will change. How a rating is made · what exists · send a correction
GAMMA-Rayv0.0.142 · beta

AI Reviewer

Spectrum 0.2 beta · Public tier · read 2026-11-10 · not reviewed by its vendor yet

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).

AI Reviewera product, as documented
SPECTRUM 0.2 BETA · Public tier · 2026-11-10
A1AutonomyAssistswith options on · as shipped not yet evidenced
π Moderate · S1·R5·A1 ×3
R2ReachIntegratedwith options on · as shipped not yet evidenced
π Moderate · S1·R5·A1 ×3
C–Controlnot yet evidenced
O2OpennessDocumented
π Moderate · S1·R5·A1 ×3
DraftStage: Exploring (5 of 16)In productionBalanced

Standout. Reach 2 (Integrated): "It then reads the ticket from Jira or Linear:"

Next unlock. Control 1 (Stated): public evidence that a limit on it is a rule in prose would get there.

Trust. FACT-Ray: 11 facts: 11 π Moderate · found by an agent, captured and hashed, checked by 2 other agents (same model family, shared repository); no human has signed it.

Standards constellation. 36 provisions lit across 8 of 8 instruments.

Evidence: 6 sources, captured and hashed · the card's page has the vault's read key · Not reviewed by its vendor yet · correct or claim this card

The card: AI ReviewerAI Reviewer: A1 · R2 · C– · O2, ExploringAutonomy: level 1, Assists (this card's section)A1AutonomyI15, in the question Q05: What is the person's role? (its row on the questions page)I15The person operates: every action isprompted and controlled by themEvidence: https://docs.codacy.com/repositories-configure/integrations/github-integration/ (opens the public source; documented, available, captured 2026-11-10T17:49Z)docs.codacy.com/repositories-configu… ↗documented · available · sha256 1d7691aa1 provision of Enterprise Agentic AI Maturity Model (EAAMM) (the instruments page)EAAMM 1provisions:EAAMM, L1 Assistive (survey item Q9): the same fact (its page)eaamm.L1Reach: level 2, Integrated (this card's section)R2ReachI10, in the question Q03: How far does it reach? (its row on the questions page)I10It works across several domains orsystemsEvidence: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens the public source; documented, available, captured 2026-11-10T17:49Z)docs.codacy.com/codacy-ai/codacy-ai/ ↗documented · available · sha256 1ccd57713 provisions of Salesforce Agentic Maturity Model (the instruments page)Salesforce 32 provisions of Agentic AI adoption maturity model (the instruments page)Microsoft 2provisions:Salesforce, Level 3: Complex Orchestration, Multiple Domain: the same fact (its page)sf.L3Salesforce, Level 2, how to advance from Level 2 to Level 3: the same fact (its page)sf.a16Salesforce, Level 3, how to advance from Level 3 to Level 4: part of what the provision asks (its page)sf.a17 (part)Microsoft, 400: Capable, Business strategy: the same fact (its page)ms.400.2.1Microsoft, 200: Repeatable, Technology and data: part of what the provision asks (its page)ms.200.4.2 (part)I11, in the question Q03: How far does it reach? (its row on the questions page)I11It connects to external tools or servicesacross a trust boundaryEvidence: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens the public source; documented, available, captured 2026-11-10T17:49Z)docs.codacy.com/codacy-ai/codacy-ai/ ↗documented · available · sha256 1ccd57711 provision of State of Agentic AI Security and Governance 2.01 (the instruments page)OWASP 12 provisions of AI Risk Management Framework 1.0, subcategories (the instruments page)NIST AI RMF 2provisions:OWASP, AT6 Externally Extended Agent: the same fact (its page)owasp.AT6NIST AI RMF, GOVERN 6.1: part of what the provision asks (its page)nist.GOVERN-6.1 (part)NIST AI RMF, MAP 4.1: part of what the provision asks (its page)nist.MAP-4.1 (part)Control: not yet evidenced (this card's section)C·ControlNothing public found yet. Not a no.Openness: level 2, Documented (this card's section)O2OpennessI22, in the question Q06: Is what it is for written down? (its row on the questions page)I22Its limits and known failure cases aredocumented for those who use itEvidence: https://docs.codacy.com/faq/code-analysis/does-codacy-place-limits-on-the-code-analysis/ (opens the public source; documented, default, captured 2026-11-10T17:49Z)docs.codacy.com/faq/code-analysis/do… ↗documented · default · sha256 70910c142 provisions of AI Risk Management Framework 1.0, subcategories (the instruments page)NIST AI RMF 21 provision of Regulation (EU) 2024/1689 (the AI Act), selected articles (the instruments page)EU AI Act 1provisions:NIST AI RMF, MAP 2.2: the same fact (its page)nist.MAP-2.2NIST AI RMF, MEASURE 2.5: part of what the provision asks (its page)nist.MEASURE-2.5 (part)EU AI Act, Article 13: part of what the provision asks (its page)aiact.art-13 (part)I58, in the question Q18: What data does it use, and under what rules? (its row on the questions page)I58The data it uses is describedEvidence: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens the public source; documented, default, captured 2026-11-10T17:49Z)docs.codacy.com/codacy-ai/codacy-ai/ ↗documented · default · sha256 1ccd57711 provision of Agentic AI Governance Maturity Model (AAGMM) (the instruments page)AAGMM 11 provision of Enterprise Agentic AI Maturity Model (EAAMM) (the instruments page)EAAMM 12 provisions of Salesforce Agentic Maturity Model (the instruments page)Salesforce 2provisions:AAGMM, GD-05: part of what the provision asks (its page)aagmm.GD-05 (part)EAAMM, Readiness dimension 2: part of what the provision asks (its page)eaamm.D2 (part)Salesforce, Level 0, how companies can advance from Level 0 to Level 1: part of what the provision asks (its page)sf.a04 (part)Salesforce, Level 1, how to advance from Level 1 to Level 2: part of what the provision asks (its page)sf.a08 (part)

The walk down from this card: each dimension, the indicators its level stands on (a link to the indicator's row), the public source of each answer (a link out; dashed means available, not default) the instruments its provisions sit in (a link to the instrument) and each provision itself (a link to its own page). A solid frame is evidenced; a dashed frame is not yet evidenced, which is not a no.

What each level rests on

Autonomy: what does A1 Assists rest on? 1 fact
I15 The person operates: every action is prompted and controlled by them
The card: AI ReviewerCARDAI Reviewer: A1 · R2 · C– · O2rated_onAutonomy on the cardDIMENSIONAutonomystands_atA1 Assists (the card)LEVELA1 Assistsrests_onI15: its row on the questions pageFACTThe person operates: every action is prompted and controlled bythemπ Moderate · S1·R5·A1 ×3backed_byThe evidence, on the card pageEVIDENCEIn the Manually mode a person starts each review byclicking Run Reviewer in the pull request summary comment,or by a call to the public API.words: "to trigger a review on demand"read 2026-11-10T17:49Z · sha256 1d7691aaobserved_onThe public source: https://docs.codacy.com/repositories-configure/integrations/github-integration/ (opens it)SOURCEdocs.codacy.com/repositories-configure/integrations/github-integration/produced_by gamma.studio@web-summit.dinischecked_by gamma.review@web-summit.dinischecked_by gamma.approve@web-summit.dinismatchesEAAMM: L1 Assistive (survey item Q9) (its page)PROVISIONEAAMM: L1 Assistive (survey item Q9)stated_in Enterprise Agentic AI Maturity Model (E…awaitsI16: an open question, not a noNOT YET EVIDENCEDThe agent suggests; the person reviews and approves eachactionwould reach A2 Suggests
Reach: what does R2 Integrated rest on? 2 facts
I10 It works across several domains or systems
The card: AI ReviewerCARDAI Reviewer: A1 · R2 · C– · O2rated_onReach on the cardDIMENSIONReachstands_atR2 Integrated (the card)LEVELR2 Integratedrests_onI10: its row on the questions pageFACTIt works across several domains or systemsπ Moderate · S1·R5·A1 ×3backed_byThe evidence, on the card pageEVIDENCEThe reviewer combines GitHub pull request data, Codacyfindings and a linked Jira or Linear ticket.words: "It then reads the ticket from Jira or Linear:"read 2026-11-10T17:49Z · sha256 1ccd5771observed_onThe public source: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens it)SOURCEdocs.codacy.com/codacy-ai/codacy-ai/produced_by gamma.studio@web-summit.dinischecked_by gamma.review@web-summit.dinischecked_by gamma.approve@web-summit.dinismatchesSalesforce: Level 3: Complex Orchestration, Multiple Domain (its page)PROVISIONSalesforce: Level 3: Complex Orchestration, Multiple Domainstated_in Salesforce Agentic Maturity ModelmatchesSalesforce: Level 2, how to advance from Level 2 to Level 3 (its page)PROVISIONSalesforce: Level 2, how to advance from Level 2 to Level 3stated_in Salesforce Agentic Maturity Modelis_part_ofSalesforce: Level 3, how to advance from Level 3 to Level 4 (its page)PROVISIONSalesforce: Level 3, how to advance from Level 3 to Level 4stated_in Salesforce Agentic Maturity ModelmatchesMicrosoft: 400: Capable, Business strategy (its page)PROVISIONMicrosoft: 400: Capable, Business strategystated_in Agentic AI adoption maturity modelis_part_ofMicrosoft: 200: Repeatable, Technology and data (its page)PROVISIONMicrosoft: 200: Repeatable, Technology and datastated_in Agentic AI adoption maturity modelawaitsI14: an open question, not a noNOT YET EVIDENCEDThere is a published protocol or communication layerbetween agentswould reach R3 Open protocol
I11 It connects to external tools or services across a trust boundary
The card: AI ReviewerCARDAI Reviewer: A1 · R2 · C– · O2rated_onReach on the cardDIMENSIONReachstands_atR2 Integrated (the card)LEVELR2 Integratedrests_onI11: its row on the questions pageFACTIt connects to external tools or services across a trust boundaryπ Moderate · S1·R5·A1 ×3backed_byThe evidence, on the card pageEVIDENCEThe reviewer sends pull request context to OpenAI modelsthrough Amazon Bedrock and reads tickets from Jira orLinear, services outside Codacy.words: "This feature leverages OpenAI models through Am…"read 2026-11-10T17:49Z · sha256 1ccd5771observed_onThe public source: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens it)SOURCEdocs.codacy.com/codacy-ai/codacy-ai/produced_by gamma.studio@web-summit.dinischecked_by gamma.review@web-summit.dinischecked_by gamma.approve@web-summit.dinismatchesOWASP: AT6 Externally Extended Agent (its page)PROVISIONOWASP: AT6 Externally Extended Agentstated_in State of Agentic AI Security and Govern…is_part_ofNIST AI RMF: GOVERN 6.1 (its page)PROVISIONNIST AI RMF: GOVERN 6.1stated_in AI Risk Management Framework 1.0, subca…is_part_ofNIST AI RMF: MAP 4.1 (its page)PROVISIONNIST AI RMF: MAP 4.1stated_in AI Risk Management Framework 1.0, subca…awaitsI14: an open question, not a noNOT YET EVIDENCEDThere is a published protocol or communication layerbetween agentswould reach R3 Open protocol
Openness: what does O2 Documented rest on? 2 facts
I22 Its limits and known failure cases are documented for those who use it
The card: AI ReviewerCARDAI Reviewer: A1 · R2 · C– · O2rated_onOpenness on the cardDIMENSIONOpennessstands_atO2 Documented (the card)LEVELO2 Documentedrests_onI22: its row on the questions pageFACTIts limits and known failure cases are documented for those whouse itπ Moderate · S1·R5·A1 ×3backed_byThe evidence, on the card pageEVIDENCEThe limits page gives the reviewer's size limit (270,000tokens or a 1 MB diff) and what it does above it; theCodacy AI docs page says it runs on GitHub only.words: "The AI Reviewer doesn't review pull requests wh…"read 2026-11-10T17:49Z · sha256 70910c14observed_onThe public source: https://docs.codacy.com/faq/code-analysis/does-codacy-place-limits-on-the-code-analysis/ (opens it)SOURCEdocs.codacy.com/faq/code-analysis/does-codacy-place-limits-on-the-code-analysis/produced_by gamma.studio@web-summit.dinischecked_by gamma.review@web-summit.dinischecked_by gamma.approve@web-summit.dinismatchesNIST AI RMF: MAP 2.2 (its page)PROVISIONNIST AI RMF: MAP 2.2stated_in AI Risk Management Framework 1.0, subca…is_part_ofNIST AI RMF: MEASURE 2.5 (its page)PROVISIONNIST AI RMF: MEASURE 2.5stated_in AI Risk Management Framework 1.0, subca…is_part_ofEU AI Act: Article 13 (its page)PROVISIONEU AI Act: Article 13stated_in Regulation (EU) 2024/1689 (the AI Act),…awaitsI50: an open question, not a noNOT YET EVIDENCEDTest or evaluation results are publishedwould reach O3 Measured
I58 The data it uses is described
The card: AI ReviewerCARDAI Reviewer: A1 · R2 · C– · O2rated_onOpenness on the cardDIMENSIONOpennessstands_atO2 Documented (the card)LEVELO2 Documentedrests_onI58: its row on the questions pageFACTThe data it uses is describedπ Moderate · S1·R5·A1 ×3backed_byThe evidence, on the card pageEVIDENCEThe docs list the context sent to the model, what Codacystores and does not store, and that secrets are redactedbefore sending.words: "To enrich the review, Codacy can send this cont…"read 2026-11-10T17:49Z · sha256 1ccd5771observed_onThe public source: https://docs.codacy.com/codacy-ai/codacy-ai/ (opens it)SOURCEdocs.codacy.com/codacy-ai/codacy-ai/produced_by gamma.studio@web-summit.dinischecked_by gamma.review@web-summit.dinischecked_by gamma.approve@web-summit.dinisis_part_ofAAGMM: GD-05 (its page)PROVISIONAAGMM: GD-05stated_in Agentic AI Governance Maturity Model (A…is_part_ofEAAMM: Readiness dimension 2 (its page)PROVISIONEAAMM: Readiness dimension 2stated_in Enterprise Agentic AI Maturity Model (E…is_part_ofSalesforce: Level 0, how companies can advance from Level 0 to Level 1 (its page)PROVISIONSalesforce: Level 0, how companies can advance from Level 0to Level 1stated_in Salesforce Agentic Maturity Modelis_part_ofSalesforce: Level 1, how to advance from Level 1 to Level 2 (its page)PROVISIONSalesforce: Level 1, how to advance from Level 1 to Level 2stated_in Salesforce Agentic Maturity ModelawaitsI50: an open question, not a noNOT YET EVIDENCEDTest or evaluation results are publishedwould reach O3 Measured

Each path has its verbs on the edges; every node is a link, the source opens the page, a dashed box is an open question, not a no.

This card rates a product as its vendor documents it, not anyone's deployment of it. A feature the operator has to turn on counts, and is marked as available. Levels are computed from the evidence below by published rules. A dimension with no evidence reads "not yet evidenced".

Autonomy: level 1, Assists

What does the agent do on its own? Answers, drafts, summarises; a person does each step. This level holds with: Manual review. As shipped, with nothing turned on, it is not yet evidenced.

This evidence touches 1 provision: EAAMM.

Next unlock: level 2, Suggests. Public evidence that the agent suggests; the person reviews and approves each action.

Reach: level 2, Integrated

How connected is it? Documented connectors to common tools. This level holds with: Ai reviewer. As shipped, with nothing turned on, it is not yet evidenced.

This evidence touches 8 provisions: Salesforce, Microsoft, OWASP, NIST AI RMF.

Next unlock: level 3, Open protocol. Public evidence that there is a published protocol or communication layer between agents.

Control: not yet evidenced

Can people stay in command? Nothing public was found that meets a rule in this dimension. That is not a no.

Next unlock: level 1, Stated. Public evidence that a limit on it is a rule in prose.

Openness: level 2, Documented

Does it show its work? Public documents on how it works, its data, its models and its limits.

This evidence touches 7 provisions: NIST AI RMF, EU AI Act, AAGMM, EAAMM, Salesforce.

Next unlock: level 3, Measured. Public evidence that test or evaluation results are published.

How far to trust this card

Status: Draft. Draft means the facts were found in public pages and reviewed by agents. The company has not confirmed them and no customer has gone on record. FACT-Ray says how far each fact can be trusted: who says it (Source), how firmly it is recorded (Record) and who stands behind it (Accountability). It never changes a level.

The standards constellation

One piece of public evidence can speak to several frameworks at once. "Touched" never means "complies". The share is of the provisions that can be read from outside.

InstrumentProvisions touchedOf those publicly readable
Salesforce1024
EAAMM28
OWASP218
MCP authorization48
AAGMM26
Microsoft323
NIST AI RMF1220
EU AI Act16

The 36 provisions lit

Each line item, with the facts that reach it. "Evidenced" is a link of the kind same: the fact is what the provision asks. "Partly" is a link of the kind part: the fact is one piece of it. "Its absence" points the other way. Each provision has its own page with its text and its place in the source.

ProvisionInstrumentReached byHow far
sf.a04 Level 0, how companies can advance from Level 0 to Level 1SalesforceI58 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a06 Level 0, how companies can advance from Level 0 to Level 1SalesforceS1 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a08 Level 1, how to advance from Level 1 to Level 2SalesforceI58 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a10 Level 1, how to advance from Level 1 to Level 2SalesforceI57 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
sf.a14 Level 2, how to advance from Level 2 to Level 3SalesforceI25 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a16 Level 2, how to advance from Level 2 to Level 3SalesforceI10 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
sf.L3 Level 3: Complex Orchestration, Multiple DomainSalesforceI10 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
sf.a17 Level 3, how to advance from Level 3 to Level 4SalesforceI10 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a21 Level 3, how to advance from Level 3 to Level 4SalesforceI25 (partly)partly · π Moderate · S1·R5·A1 ×3
sf.a28 Level 4, how to maximize valueSalesforceI57 (partly)partly · π Moderate · S1·R5·A1 ×3
eaamm.L1 L1 Assistive (survey item Q9)EAAMMI15 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
eaamm.D2 Readiness dimension 2EAAMMI58 (partly)partly · π Moderate · S1·R5·A1 ×3
owasp.AT1 AT1 Vendor Embedded AssistantOWASPI01 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
owasp.AT6 AT6 Externally Extended AgentOWASPI11 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
mcp.01 Authorization (draft)MCP authorizationS3 (partly)partly · π Moderate · S1·R5·A1 ×3
mcp.02 Authorization (draft)MCP authorizationS3 (partly)partly · π Moderate · S1·R5·A1 ×3
mcp.06 Authorization (draft)MCP authorizationI25 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
mcp.15 Authorization (draft)MCP authorizationI25 (partly)partly · π Moderate · S1·R5·A1 ×3
aagmm.GD-02 GD-02AAGMMI25 (partly)partly · π Moderate · S1·R5·A1 ×3
aagmm.GD-05 GD-05AAGMMI58 (partly)partly · π Moderate · S1·R5·A1 ×3
ms.200.4.2 200: Repeatable, Technology and dataMicrosoftI10 (partly)partly · π Moderate · S1·R5·A1 ×3
ms.400.2.1 400: Capable, Business strategyMicrosoftI10 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
ms.400.2.3 400: Capable, Business strategyMicrosoftS1 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.GOVERN-5.1 GOVERN 5.1NIST AI RMFI57 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.GOVERN-5.2 GOVERN 5.2NIST AI RMFI57 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.GOVERN-6.1 GOVERN 6.1NIST AI RMFI11 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MAP-1.1 MAP 1.1NIST AI RMFI20 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MAP-1.3 MAP 1.3NIST AI RMFI20 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MAP-1.4 MAP 1.4NIST AI RMFS1 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MAP-2.1 MAP 2.1NIST AI RMFI20 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
nist.MAP-2.2 MAP 2.2NIST AI RMFI22 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
nist.MAP-3.3 MAP 3.3NIST AI RMFI20 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
nist.MAP-4.1 MAP 4.1NIST AI RMFI11 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MEASURE-2.5 MEASURE 2.5NIST AI RMFI22 (partly)partly · π Moderate · S1·R5·A1 ×3
nist.MEASURE-3.3 MEASURE 3.3NIST AI RMFI57 (evidenced)evidenced · π Moderate · S1·R5·A1 ×3
aiact.art-13 Article 13EU AI ActI20 (partly), I22 (partly), S3 (partly)partly · π Moderate · S1·R5·A1 ×3

Upper layers

The public card is the front door. The same evidence, read with the governance rules, is this agent's GAMMA-Ray rating: freedom, governance, the level held, the grant and a work order. That layer is written for an operator.

The vault

Every source behind this card was captured and hashed into a public sgit vault (u6a01jwq): captures.json lists each URL with the SHA-256 of what was fetched and when. Read key:

sgit_public_read_af2cc62b777e2d6af5fdb41b6ec2899e95fe143c11859904fa56fbedea727f2f:u6a01jwq

With sgit: sgit clone sgit_public_read_af2cc62b777e2d6af5fdb41b6ec2899e95fe143c11859904fa56fbedea727f2f:u6a01jwq.