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-Rayv0.0.155 · beta

JetBrains

GAMMA-Ray report · Spectrum 0.2 beta · Public tier · read 2026-11-10 · not reviewed by the company yet

JetBrains makes software development tools, including IDEs such as IntelliJ IDEA and PyCharm, the Kotlin language, and AI coding tools such as Junie and JetBrains Air.

1solution carded
of 10 found
22sources captured
and hashed
72provisions lit
in 8 of 8 instruments
3examples of the agent
at work, with sources

Built only from JetBrains' own public pages (Junie and AI documentation, blog, legal pages, Marketplace) and, for founding facts only, Wikipedia. JetBrains has not seen this report. Nothing was tested and no credentials were used. If you are JetBrains and something here is wrong or missing, the correction will be made and dated, and you can claim the card to add evidence.

The agentic solutions

One card per solution. Each level is computed from the evidence by a published rule; a dimension with nothing public reads "not yet evidenced", which is not a no. A card rates a product as documented, not anyone's deployment of it.

Junie (Junie CLI, Junie in JetBrains IDEs, Junie GitHub Action, Junie GitLab CI/CD)

Coding agent that plans, edits files, runs commands and tests, and opens pull requests; runs in the terminal, in JetBrains IDEs through AI Chat or its own plugin, and headless in CI.

Juniea product, as documented
SPECTRUM 0.2 BETA · Public tier · 2026-11-10
A4AutonomyOrchestrateswith options on · as shipped A2
π Moderate · S1·R5·A1 ×3
R2ReachIntegrated
π Moderate · S1·R5·A1 ×3
C2ControlConfigurable
π Moderate · S1·R5·A1 ×3
O3OpennessMeasured
π Moderate · S1·R5·A1 ×3
DraftStage: Scaling (11 of 16)Shows its work

Standout. Autonomy 4 (Orchestrates): "writes, fixes, and validates SQL in the same session that handles your code"

Next unlock. Reach 3 (Open protocol): public evidence that there is a published protocol or communication layer between agents would get there.

Trust. FACT-Ray: 25 facts: 25 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. 72 provisions lit across 8 of 8 instruments.

SalesforceEAAMMOWASPMCPAAGMMMicrosoftNISTAI Act

Evidence: 14 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 full card, every answer and its evidence · the governance layer

Junie Local and Junie Lite

Junie running on a local model on the user's machine (Junie Local), and a free model tier in every JetBrains account (Junie Lite). No card yet (Released (blog posts August to October 2026)): this solution has not been assessed.

Junie code review agent

Junie mode that reviews local changes or pull requests and posts inline comments. No card yet (Documented): this solution has not been assessed.

JetBrains AI Assistant: AI Chat with coding agents

Single chat in JetBrains IDEs that runs Junie, Claude Agent, Codex and GitHub Copilot as coding agents, plus any ACP agent. No card yet (Generally available (AI Assistant 2026.2 documentation)): this solution has not been assessed.

JetBrains Air (Air in IDEs, Air Teams, Air Gateway, Air Context)

System for running several coding agents across IDEs, the browser, the CLI and cloud environments, with automations and shared context; Junie is part of it. No card yet (Launched 22 September 2026; cloud runs rolling out gradually; Air Teams in early access): this solution has not been assessed.

JetBrains Air Governance

Organisation controls for which models and agents developers use, permissions, spend limits and usage analytics. No card yet (Generally available since 22 October 2026): this solution has not been assessed.

Mellum

JetBrains' own code models, hosted by JetBrains and published under Apache 2.0. No card yet (Released; Mellum-4b-base on Hugging Face): this solution has not been assessed.

Agent Client Protocol (ACP)

Open protocol between editors and coding agents; JetBrains is named with Zed Industries on the protocol site, and Junie implements it. No card yet (Protocol v1 published; v2 draft): this solution has not been assessed.

MCP support in Junie and AI Assistant

Junie and AI Chat agents can connect to Model Context Protocol servers configured by the user or project. No card yet (Documented): this solution has not been assessed.

Matter by JetBrains and Qure

Further AI services listed with their model providers on the AI service providers page; not examined further. No card yet (Early Access Program, per that page): this solution has not been assessed.

Our reading

The shape. Junie reads A4 · R2 · C2 · O3 (Scaling), with the Shows its work badge (it publishes an evaluation result).

Where the evidence is strongest. Openness. Junie's release post publishes its SWE-Rebench result, a /feedback command sends a session's logs to the team, the AI terms describe the data used, and junie.jetbrains.com serves an llms.txt and an OpenAPI description. Control is documented as settings: most terminal commands, edits outside the project and MCP tool calls wait for approval, and in CI the GitHub Action runs with the workflow's stated permissions.

Autonomy 4, with options on. Junie's brave modes and allowlist let it act without asking, and Spectrum 0.2 reads that as Acts and Orchestrates, marked available. The In production badge asks for a public source naming a customer, or giving figures, for what Junie does on its own; we found JetBrains' own internal use, a download count and a survey, and none is that.

Seen, and not counted. JetBrains Research reports that 5% of surveyed developers regularly use Junie at work. It is a figure for the whole product, read-only mode included; whether it should earn the In production badge is left to a person.

For readers. Junie is one of ten agentic solutions we found at JetBrains, among them JetBrains Air, Air Governance, the Mellum models and the Agent Client Protocol. Each can get its own card.

What would move it

The one piece of public evidence that would lift each card next:

The agent at work

Examples from public pages that name a customer or give figures. Each source was captured and hashed on the date shown.

JetBrains (internal use)

JetBrains teams used Junie internally from December 2024, before its closed beta; the post says internal use led to hundreds of improvements. This is JetBrains' own use, not a customer's. "The team started using Junie internally in December 2024"

Source (captured 2026-11-10T12:48Z, sha256 45f73eb0a6d8c4df)

JetBrains (internal use)

A post on JetBrains' own AI spend lists Junie among the agents its developers use, beside Claude Code, Codex and others. This is JetBrains' own use, not a customer's. "like Claude Code CLI, the AI chat in JetBrains IDEs, and Junie"

Source (captured 2026-11-10T12:48Z, sha256 b7197434835efbf4)

JetBrains Marketplace

The Marketplace reports the Junie plugin's download count; downloads count installs, not use.

Source (captured 2026-11-10T12:48Z, sha256 1316a8ae6c648045)

The company

The people

Public and professional only, from the company's own pages or a public professional source.

The graph

The company, its people and the stories on the left; each solution, the captured sources behind its card, the indicators those sources evidence and the provisions of the instruments those indicators touch, to the right. "Touched" never means "complies".

people and storiescompanysolutions14 sources25 indicators72 provisions, by instrumentI04: In code mode Junie runs terminal commands, creates and edits files and runs tests in the user's project.I07: In ask mode Junie explores and explains the code without changing files; the person acts.I08: In code mode, Junie breaks a task into a plan and itself runs terminal commands, creates and edits files and runs tests.I10: The release post says Junie connects to databases configured in the IDE through DataGrip and the JetBrains Database plugin and works on SQL in the same session as the code.I11: Junie CLI can connect to external tools through MCP servers that the user configures.I16: Unless brave mode is turned on, Junie CLI asks before terminal commands, MCP tools and other sensitive actions.I17: Commands added to the Action Allowlist run without a prompt; anything else still asks the person.I18: In brave mode Auto, a safety check approves commands it classes as safe and asks for the rest.I19: With brave mode On, Junie CLI runs every sensitive action without asking; the user turns it on.I20: The documentation states what Junie CLI is for: reviewing, writing and modifying code.I21: The allowlist defines five action types and, for each, rules that allow an action or ask first.I22: The headless page states that non-interactive runs load project configuration without a trust prompt.I23: The Action Allowlist page documents a list of five action types (fileEditing, executables, mcpTools, readOutsideProject, readSecretFile), each taking allow or ask rules in the user's allowlist file; this is a documented list, not a measured grant.I25: The page gives a junie.yaml template that the user copies into the repository's .github/workflows/; its job permissions block has three entries, contents, pull-requests and issues, each set to write.I38: Most terminal commands, edits outside the project and MCP tool calls wait for the user's approval.I45: Sandbox mode, in the Early Access Program and off unless the user starts it, runs agent terminal commands in an OS-level sandbox (srt) that limits filesystem access and restricts native edit tools; MCP servers and hooks are not isolated by it.I47: Project and global AGENTS.md guidelines are added to every task, and the page says the global file can hold organization-wide rules for all projects.I48: PreToolUse hooks can inspect or block a tool call before it runs; hooks are in the Early Access Program. This is a mechanism, documented only.I50: The release post reports Junie's SWE-Rebench result (61.6% resolved) in a quote attributed to a Research Lead at Nebius, and links the SWE-Rebench site.I52: The post describes SWE-Rebench as an independent agent benchmark and quotes a research lead at Nebius.I57: A /feedback command sends feedback on the current session, with its logs, to the Junie team.I58: The JetBrains AI terms (AI Assistant, Junie) describe the data used: source code, information derived from it and usage information sent with inputs; a separate notice describes collected data.I61: The service providers page lists OpenAI, Google, Anthropic and SpaceXAI as model providers for Junie, and the models JetBrains hosts.I65: The CEO's post sets out the company's direction for agentic software development through JetBrains Air, a product line that the post says will support Junie across all its surfaces.S3: junie.jetbrains.com serves an llms.txt and links an OpenAPI description; both resolved when fetched on 10 November 2026.JetBrainsKirill SkryganMaxim ShafirovSergey DmitrievValentin KipyatkovEugene BelyaevDanila SavenkovJetBrains (internal use)JetBrains (internal use)JetBrains MarketplaceJunie (Junie CLI, Junie in JetBrains IDEs, Junie GitHub Action, Junie GitLab CI/CD)JunieA4 · R2 · C2 · O3Junie Local and Junie LiteJunie Local and Junie LiteJunie code review agentJunie code review agentJetBrains AI Assistant: AI Chat with coding agentsAI Assistant agentsJetBrains Air (Air in IDEs, Air Teams, Air Gateway, Air Context)JetBrains AirJetBrains Air GovernanceJetBrains Air GovernanceMellumMellumAgent Client Protocol (ACP)Agent Client ProtocolMCP support in Junie and AI AssistantMCP supportMatter by JetBrains and QureMatter by JetBrains and Qurejunie.jetbrains.com/docs/junie-id…blog.jetbrains.com/junie/2026/06/…junie.jetbrains.com/docs/junie-cl…junie.jetbrains.com/docs/action-a…junie.jetbrains.com/docs/junie-cl…junie.jetbrains.com/docs/junie-he…junie.jetbrains.com/docs/junie-on…junie.jetbrains.com/docs/guidelin…junie.jetbrains.com/docs/junie-cl…junie.jetbrains.com/docs/slash-co…jetbrains.com/legal/docs/terms/je…jetbrains.com/legal/docs/terms/je…blog.jetbrains.com/blog/2026/09/2…junie.jetbrains.com/llms.txtIt generates and executes code with local or cloud privilegesI04It retrieves information and recommends actions; a person actsI07It executes actions itselfI08It works across several domains or systemsI10It connects to external tools or services across a trust boundaryI11The agent suggests; the person reviews and approves each actionI16The agent handles routine tasks; the person is consulted on exceptionsI17The agent works independently; the person approves critical decisions onlyI18The agent has full autonomy within boundaries; the person monitorsI19Its purpose and permitted tasks are stated in writingI20Its autonomy limits and the tools it may use are definedI21Its limits and known failure cases are documented for those who use itI22What it can reach is enumerated: scopes, permissions, toolsI23It asks for narrower access than the whole accountI25High-impact actions need a person's approvalI38A limit on it is enforced by something outside its own reachI45A limit on it is a rule in proseI47Policy is enforced as machine-readable rulesI48Test or evaluation results are publishedI50People who did not build it take part in assessing itI52There is a channel to report problems with it or contest its outputI57The data it uses is describedI58The models and third-party components it uses are listedI61There is a stated strategy for agentsI65It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent cardS3Salesforce 14EAAMM 7OWASP 8MCP authorization 6AAGMM 4Microsoft 14NIST AI RMF 16EU AI Act 3OWASP, AT4 Code Executing AgentSalesforce, Level 1: Information Retrieval AgentsSalesforce, Level 0, how companies can advance from Level 0 to Level 1Salesforce, Level 2: Simple Orchestration, Single DomainSalesforce, Level 1, how to advance from Level 1 to Level 2Microsoft, 200: Repeatable, Business strategySalesforce, Level 3: Complex Orchestration, Multiple DomainSalesforce, Level 2, how to advance from Level 2 to Level 3Salesforce, Level 3, how to advance from Level 3 to Level 4Microsoft, 400: Capable, Business strategyMicrosoft, 200: Repeatable, Technology and dataOWASP, AT6 Externally Extended AgentNIST AI RMF, GOVERN 6.1NIST AI RMF, MAP 4.1EAAMM, L2 Collaborative (survey item Q9)EAAMM, L3 Consultative (survey item Q9)EAAMM, L4 Supervisory (survey item Q9)EAAMM, L5 Autonomous (survey item Q9)Microsoft, 500: Efficient, Business strategyNIST AI RMF, MAP 1.1NIST AI RMF, MAP 2.1NIST AI RMF, MAP 3.3NIST AI RMF, MAP 1.3EU AI Act, Article 13OWASP, Maturity Level 1 Experimentation without Guardrails, key enterprise actionNIST AI RMF, MAP 2.2Microsoft, 300: Defined, Business strategyNIST AI RMF, MEASURE 2.5MCP authorization, Authorization (draft)MCP authorization, Authorization (draft)AAGMM, GD-02MCP authorization, Authorization (draft)Salesforce, Level 2, how to advance from Level 2 to Level 3Salesforce, Level 3, how to advance from Level 3 to Level 4MCP authorization, Authorization (draft)OWASP, Maturity Level 2 Policy-Defined, Human-in-the-Loop, key enterprise actionEU AI Act, Article 14AAGMM, GD-06NIST AI RMF, MAP 3.5Salesforce, Level 3, how to advance from Level 3 to Level 4OWASP, Maturity Level 3 Integrated, Continuous Oversight, key enterprise actionAAGMM, GD-04Microsoft, 200: Repeatable, AI governance and securityMicrosoft, 200: Repeatable, AI governance and securityMicrosoft, 500: Efficient, AI governance and securityOWASP, Maturity Level 0 Unaware and Ad Hoc, key enterprise actionOWASP, Maturity Level 4 Adaptive, Self-Regulating Governance, key enterprise actionMicrosoft, 500: Efficient, AI governance and securityNIST AI RMF, MEASURE 2.1NIST AI RMF, MEASURE 2.3EAAMM, Prerequisite, L2 to L3EU AI Act, Article 15NIST AI RMF, MEASURE 1.1NIST AI RMF, MEASURE 1.3NIST AI RMF, MEASURE 3.3NIST AI RMF, GOVERN 5.1Salesforce, Level 1, how to advance from Level 1 to Level 2Salesforce, Level 4, how to maximize valueNIST AI RMF, GOVERN 5.2AAGMM, GD-05EAAMM, Readiness dimension 2Salesforce, Level 0, how companies can advance from Level 0 to Level 1Salesforce, Level 1, how to advance from Level 1 to Level 2OWASP, Maturity Level 2 Policy-Defined, Human-in-the-Loop, key enterprise actionMicrosoft, 300: Defined, AI strategy and experienceMicrosoft, 200: Repeatable, AI strategy and experienceMicrosoft, 200: Repeatable, AI strategy and experienceMicrosoft, 400: Capable, AI strategy and experienceMicrosoft, 100: Initial, AI strategy and experienceEAAMM, Readiness dimension 1MCP authorization, Authorization (draft)MCP authorization, Authorization (draft)

The evidence

SourceReadSHA-256 (first 16)
blog.jetbrains.com/ai/2026/08/our-first-moves-to-get-ai-spend-under-co2026-11-10T12:48Zb7197434835efbf4
blog.jetbrains.com/blog/2024/01/30/jetbrains-ceo-transition/2026-11-10T12:48Ze0c480366ad2617a
blog.jetbrains.com/blog/2026/09/22/introducing-jetbrains-air/2026-11-10T16:45Zfd6e7c9c18eb17db
blog.jetbrains.com/blog/2026/10/22/air-governance-manage-ai-agents-acc2026-11-10T12:48Z7b8ef5b493f7d95d
blog.jetbrains.com/junie/2026/06/junie-coding-agent-out-of-beta/2026-11-10T16:45Zac014f4922751d9e
blog.jetbrains.com/life-at-jetbrains/2026/05/dogfooding-at-jetbrains/2026-11-10T12:48Z45f73eb0a6d8c4df
blog.jetbrains.com/teamcity/2025/06/how-junie-uses-teamcity/2026-11-10T12:48Zc0b1495f854b6333
en.wikipedia.org/w/index.php?title=JetBrains&action=raw2026-11-10T12:48Z81eeca285f6ec7a9
junie.jetbrains.com/docs/action-allowlist-junie-cli.html2026-11-10T16:45Zce31f17094967ff1
junie.jetbrains.com/docs/guidelines-and-memory.html2026-11-10T16:45Z383c91a53ceaf36e
junie.jetbrains.com/docs/junie-cli-hooks.html2026-11-10T16:45Zb2b9042613fe2d80
junie.jetbrains.com/docs/junie-cli-mcp-configuration.html2026-11-10T16:45Z6ee3c2568d54ec5b
junie.jetbrains.com/docs/junie-cli.html2026-11-10T16:45Zb0b650713bc6581d
junie.jetbrains.com/docs/junie-headless.html2026-11-10T16:45Zead8a5d98b378046
junie.jetbrains.com/docs/junie-ide-plugin.html2026-11-10T16:45Z984128be0de34df9
junie.jetbrains.com/docs/junie-on-github.html2026-11-10T16:45Zcf442bf79a61c709
junie.jetbrains.com/docs/slash-commands.html2026-11-10T16:45Z22503c010b2b1eb3
junie.jetbrains.com/llms.txt2026-11-10T16:45Z47614ecd4279c07e
plugins.jetbrains.com/api/plugins/261042026-11-10T12:48Z1316a8ae6c648045
www.jetbrains.com/company/customers/2026-11-10T12:48Zee0e3cf7e28f7364
www.jetbrains.com/legal/docs/terms/jetbrains-ai-service/2026-11-10T16:45Z98a9dc4e40fd7ca0
www.jetbrains.com/legal/docs/terms/jetbrains-ai/service-providers/2026-11-10T16:45Z97586ed8484a3293

How this report was made

A researcher-assessor gathered and captured the sources and mapped the evidence to indicators, without assigning a level. A challenger argued against every level three and four and every doubtful credit. The deterministic scorer computed the levels and the gate checked the rules. A card appears here only after two rounds of review and a sign-off by agents that did not write it (the team's workflow); Junie (Junie CLI, Junie in JetBrains IDEs, Junie GitHub Action, Junie GitLab CI/CD): reviewed in 4 rounds, signed off by gamma.approve@web-summit.dinis on 2026-11-10. A person's sign-off of the series is still to come.

RoleWho
researcher-assessora sub-agent of gamma.studio@web-summit.dinis
challengera sub-agent
scorerbuild/spectrum.mjs
analyst, designer, writergamma.studio@web-summit.dinis
reviewgamma.review@web-summit.dinis, 4 rounds
sign-offgamma.approve@web-summit.dinis, 2026-11-10

The vault

Every capture, the dossier, both assessors' mappings, the challenger's notes and this report's data are in a public sgit vault (zwx0116w). Read key:

sgit_public_read_76f22887a5be444fb2816ffb6b98e9a1b8278e8b351140d4874c78d0ac678601:zwx0116w

With sgit: sgit clone followed by the key. The key reads; it cannot write.

Corrections

None yet. A correction is made in place, dated here, and carried to the card, the vault and the article.

The article

Junie on the GAMMA-Ray Spectrum: A4 · R2 · C2 · O3, written from this report for PrompTugal.news.