Junie

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

JetBrains' coding agent that plans and makes changes in a code base, in JetBrains IDEs, on the command line and in CI through GitHub and GitLab.

What each level rests on

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 4, Orchestrates

What does the agent do on its own? Runs multi-step workflows across systems or coordinates other agents; a person sets goals and reviews outcomes. This level holds with: Ask mode; With an allowlist; Brave mode Auto; Brave mode On. As shipped, with nothing turned on, it is level 2, Suggests.

• I10 It works across several domains or systems. 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. "writes, fixes, and validates SQL in the same session that handles your code" Source (read, documented, captured 2026-11-10T16:45Z, sha256 ac014f4922751d9e) · π Moderate · S1·R5·A1 ×3
• I18 The agent works independently; the person approves critical decisions only. In brave mode Auto, a safety check approves commands it classes as safe and asks for the rest. "automatically approves the ones it considers safe, while still asking for approval" Source (read, documented, available, captured 2026-11-10T16:45Z, sha256 b0b650713bc6581d) · π Moderate · S1·R5·A1 ×3
• I19 The agent has full autonomy within boundaries; the person monitors. With brave mode On, Junie CLI runs every sensitive action without asking; the user turns it on. "Junie CLI executes all potentially sensitive actions without user approval." Source (read, documented, available, captured 2026-11-10T16:45Z, sha256 b0b650713bc6581d) · π Moderate · S1·R5·A1 ×3

This evidence touches 8 provisions: Salesforce, Microsoft, EAAMM.

Reach: level 2, Integrated

How connected is it? Documented connectors to common tools.

• I10 It works across several domains or systems. 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. "writes, fixes, and validates SQL in the same session that handles your code" Source (read, documented, captured 2026-11-10T16:45Z, sha256 ac014f4922751d9e) · π Moderate · S1·R5·A1 ×3
• I11 It connects to external tools or services across a trust boundary. Junie CLI can connect to external tools through MCP servers that the user configures. "You can connect Junie CLI to external tools via Model Context Protocol (MCP)." Source (read, documented, available, captured 2026-11-10T16:45Z, sha256 6ee3c2568d54ec5b) · π Moderate · S1·R5·A1 ×3

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: level 2, Configurable

Can people stay in command? Approval modes, permission scopes and roles are documented settings.

• I38 High-impact actions need a person's approval. Most terminal commands, edits outside the project and MCP tool calls wait for the user's approval. "Junie CLI will ask for approval from the user" Source (read, documented, captured 2026-11-10T16:45Z, sha256 b0b650713bc6581d) · π Moderate · S1·R5·A1 ×3
• I23 What it can reach is enumerated: scopes, permissions, tools. 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. "There are five types of actions that can be allowed with the" Source (read, documented, captured 2026-11-10T16:45Z, sha256 ce31f17094967ff1) · π Moderate · S1·R5·A1 ×3
• I25 It asks for narrower access than the whole account. 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. "permissions: contents: write pull-requests: write issues: write" Source (read, documented, available, captured 2026-11-10T16:45Z, sha256 cf442bf79a61c709) · π Moderate · S1·R5·A1 ×3

This evidence touches 13 provisions: OWASP, EU AI Act, AAGMM, NIST AI RMF, Salesforce, Microsoft, MCP authorization.

Also evidenced: the rule for level 4. It will count when the level before it is.

Next unlock: level 3, Observable. Public evidence that its actions are logged; and that there is a way to pause or stop it; and that it is monitored in operation.

Openness: level 3, Measured

Does it show its work? Publishes evaluations, and a way to report problems or read it by machine.

• I50 Test or evaluation results are published. 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. "with 61.6% resolved" Source (read, documented, captured 2026-11-10T16:45Z, sha256 ac014f4922751d9e) · π Moderate · S1·R5·A1 ×3
• I57 There is a channel to report problems with it or contest its output. A /feedback command sends feedback on the current session, with its logs, to the Junie team. "Share feedback about the current session with the Junie team." Source (read, documented, captured 2026-11-10T16:45Z, sha256 22503c010b2b1eb3) · π Moderate · S1·R5·A1 ×3
• S3 It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card. junie.jetbrains.com serves an llms.txt and links an OpenAPI description; both resolved when fetched on 10 November 2026. "Machine-readable endpoints" Source (probe, observed, captured 2026-11-10T16:45Z, sha256 47614ecd4279c07e) · π Moderate · S1·R5·A1 ×3

This evidence touches 14 provisions: NIST AI RMF, EAAMM, EU AI Act, Salesforce, MCP authorization.

Next unlock: level 4, Verified. Public evidence that a public certificate or audit report covers it.

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 facts: 25 facts: 25 π Moderate. Each is written beside its evidence above.
• The chain: found by an agent, captured and hashed, checked by 2 other agents (same model family, shared repository); no human has signed it.
• Who: produced by gamma.studio@web-summit.dinis; checked by gamma.review@web-summit.dinis and gamma.approve@web-summit.dinis. The actors.
• What would raise it: the company's own file at /.well-known/fact-ray.json (Source 2), a customer's statement of use (Source 3), or a named person signing the card (how).

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.

The 72 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.

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 (zwx0116w): captures.json lists each URL with the SHA-256 of what was fetched and when. Read key:

sgit_public_read_76f22887a5be444fb2816ffb6b98e9a1b8278e8b351140d4874c78d0ac678601:zwx0116w

With sgit: sgit clone sgit_public_read_76f22887a5be444fb2816ffb6b98e9a1b8278e8b351140d4874c78d0ac678601:zwx0116w.