Replit Agent

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

Replit's AI agent that builds, runs, tests and publishes software from a description in plain language, inside a Replit project.

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: Plan mode on; App Testing on; Background changes applied automatically; With connectors and MCP servers. As shipped, with nothing turned on, it is level 3, Acts.

• I10 It works across several domains or systems. With connectors added, Agent reads and writes to several external services such as BigQuery, Linear, Slack and Notion. "Read and write to external services like BigQuery, Linear, Slack, Notion" Source (read, documented, available, captured 2026-11-10T05:44Z, sha256 7dee387f587385fc) · π Moderate · S1·R5·A1 ×3
• I18 The agent works independently; the person approves critical decisions only. In the default build mode Agent plans, writes code, sets up infrastructure, tests and deploys on its own from a description. "Agent handles the rest, from planning to deployment" Source (read, documented, captured 2026-11-10T05:44Z, sha256 351087bd1f78f841) · π Moderate · S1·R5·A1 ×3
• I19 The agent has full autonomy within boundaries; the person monitors. Background tasks wait for review by default; the person can switch on automatic apply of their changes. "You can enable Automatically apply changes in the background build options." Source (read, documented, available, captured 2026-11-10T05:44Z, sha256 1c2834bd959ed8d7) · 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. This level holds with: With connectors and MCP servers. As shipped, with nothing turned on, it is level 1, Contained.

• I10 It works across several domains or systems. With connectors added, Agent reads and writes to several external services such as BigQuery, Linear, Slack and Notion. "Read and write to external services like BigQuery, Linear, Slack, Notion" Source (read, documented, available, captured 2026-11-10T05:44Z, sha256 7dee387f587385fc) · π Moderate · S1·R5·A1 ×3
• I11 It connects to external tools or services across a trust boundary. The MCP list states Agent connects to external tools and data sources through MCP servers the user installs. "Replit Agent connects to external tools and data sources through the" Source (read, documented, available, captured 2026-11-10T05:44Z, sha256 8f0d0d44edb190fb) · π Moderate · S1·R5·A1 ×3

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

Next unlock: level 4, Ecosystem. Public evidence that agents operate across organisational boundaries or disparate stacks.

Control: level 2, Configurable

Can people stay in command? Approval modes, permission scopes and roles are documented settings. This level holds with: Enterprise workspace. As shipped, with nothing turned on, it is level 1, Stated.

• I38 High-impact actions need a person's approval. Changes made by background tasks are held for the person to review before they are applied to the main version. "Review the task’s work log, test results, and preview before applying changes." Source (read, documented, captured 2026-11-10T05:44Z, sha256 d4df1864788c5069) · π Moderate · S1·R5·A1 ×3
• I25 It asks for narrower access than the whole account. On Enterprise an organisation can bring its own OAuth app and set the exact scopes builders can request for a connector. "control the exact scopes your builders can request" Source (read, documented, available, captured 2026-11-10T05:44Z, sha256 29d5d4195ad021dd) · π Moderate · S1·R5·A1 ×3

This evidence touches 11 provisions: OWASP, EU AI Act, AAGMM, NIST AI RMF, Salesforce, Microsoft, MCP authorization.

Next unlock: level 3, Observable. Public evidence that it is monitored in operation.

Openness: level 2, Documented

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

• I22 Its limits and known failure cases are documented for those who use it. The help page documents known failure cases such as Agent freezing, looping and adding unrequested features, with what to do. "Agent is looping or repeating the same steps" Source (read, documented, captured 2026-11-10T05:44Z, sha256 c787756fd19c0948) · π Moderate · S1·R5·A1 ×3
• I58 The data it uses is described. The page describes the content used for model improvement: prompts, instructions, context and generated responses. "including your prompts, instructions, context, and responses generated for you" Source (read, documented, captured 2026-11-10T05:44Z, sha256 b330256ef72ada55) · π Moderate · S1·R5·A1 ×3
• I61 The models and third-party components it uses are listed. The subprocessor list names the providers of AI models (Anthropic, OpenAI, Google); it lists providers, not which model Agent uses. Source (read, documented, captured 2026-11-10T05:44Z, sha256 43bd18511a5644e7) · π Moderate · S1·R5·A1 ×3

This evidence touches 9 provisions: NIST AI RMF, EU AI Act, AAGMM, EAAMM, Salesforce, OWASP.

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 facts: 28 facts: 28 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 76 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 (micbbanr): captures.json lists each URL with the SHA-256 of what was fetched and when. Read key:

sgit_public_read_a835cecf0324b1147350caf9a8566f08f8c1c10df7eb007bd866eb156f228154:micbbanr

With sgit: sgit clone sgit_public_read_a835cecf0324b1147350caf9a8566f08f8c1c10df7eb007bd866eb156f228154:micbbanr.