Cursor
Cursor is a coding agent that runs in the terminal, collaborates in Slack and reviews pull requests in GitHub, distributed as a desktop application with a macOS download. Users can choose between models from OpenAI, Anthropic, Gemini, SpaceXAI and Cursor's own — named as written on the page — or bring their own model; tools and MCP servers are invoked with @, and skills and commands with /. Cursor offers a targeted-edit mode and what it calls a full autonomy agentic version, and always-on agents can be set to run on schedules or triggers to build, maintain and fix software. Agents use their own computers to build, test and demo features end to end for the user to review, which is the only oversight point the page describes and one that comes after the work. Cursor says it is trusted by over half of the Fortune 500. Against that deployment claim, the page checked publishes no certification, no regulatory posture, no retained record of agent actions, no pricing at all, no AI liability cover or indemnity, and no outcome-linked payment term.
14 fields evidenced · 45 with no public information. Every value below links to the document it came from and the date we checked it.
11 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist
2 of those are flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated them yet.
1 absence has been read back against the source by an editor and confirmed.
Trust gap
How this is scoredAre scope, spend, and authority enforced while the agent runs?
A review point is described — agents "build, test, and demo features end to end for you to review" — but review is after the fact. No enforced limit on scope, spend or authority is published, and no permission scoping is described.
Counts Human oversight, each cited below.
How this gap gets closed →Is there a tamper-evident record of what it actually did?
No public evidence found. The page checked publishes no record of agent actions, no log retention and no tamper-evidence claim.
How this gap gets closed →Are compliance obligations attached per engagement?
No public evidence found. The page checked names no certification, attestation or regulatory posture, despite claiming deployment across more than half of the Fortune 500.
How this gap gets closed →Does payment depend on a verified result?
No outcome-linked payment term is published, and the page checked carries no pricing evidence at all — no price, no charging basis, no escrow, milestone release or clawback.
How this gap gets closed →Can the deployment be insured, and is the customer indemnified?
No public evidence found. The page checked publishes no AI liability cover for a customer deploying Cursor, no named carrier, no policy limits, no customer indemnity and no liability cap.
How this gap gets closed →Assurance
- Insurance available
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Own liability cover
- no public informationcursor.com · checked Sep 5, 2026 · source did not state this
- Insurance carriers
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Coverage limits
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Indemnification
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Liability cap
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Audit trail
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Tamper-evident log
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Explainability
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Runtime governance
- no public informationcursor.com · checked Aug 3, 2026 · absence verified against this source
- Permission scopes
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Compliance certifications
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Regulatory alignment
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Outcome-based pricing
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Settlement mechanism
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Asset custody
- no public informationcursor.com · checked Sep 5, 2026 · source did not state this
- Dispute process
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- SLA terms
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Evaluation coverage
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Self-reported performance
- no public informationcursor.com · checked Sep 12, 2026 · source did not state this
Agency
- Autonomy level
- full autonomy agentic version
“In Cursor, you can do Cmd+K for targeted edits, or let it rip with the full autonomy agentic version.”
cursor.com · checked Aug 3, 2026 - Human oversight
“Agents use their own computers to build, test, and demo features end to end for you to review.”
cursor.com · checked Aug 3, 2026- Goal complexity
“Ask Cursor to plan or build anything”
cursor.com · checked Aug 3, 2026- Action space
“Plan, search, build anything”
cursor.com · checked Aug 3, 2026- Operating environment
“Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
cursor.com · checked Aug 3, 2026- Initiative
“Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
cursor.com · checked Aug 3, 2026
Safety
- Safety evaluations
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Red teaming
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Safety policy
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Usage restrictions
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Model or system card
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Incident reporting
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Third-party evaluations
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Data handling
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
Practicality
- Pricing model
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Price point
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Availability
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Deployment options
- Desktop application; macOS download offered on the homepage
“Download for macOS”
cursor.com · checked Aug 3, 2026 - Integrations
“Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
cursor.com · checked Aug 3, 2026- Supported regions
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Support model
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
Foundation models
- Base models
- Models from OpenAI, Anthropic, Gemini, SpaceXAI and Cursor's own; named as written on the page
“Choose between every cutting-edge model from OpenAI, Anthropic, Gemini, SpaceXAI, and Cursor.”
cursor.com · checked Aug 3, 2026 - Model provider
“Choose between every cutting-edge model from OpenAI, Anthropic, Gemini, SpaceXAI, and Cursor.”
cursor.com · checked Aug 3, 2026- Model swappable
“bring-your-own-model”
cursor.com · checked Aug 3, 2026- Open weights
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Fine-tuning
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
cursor.com · checked Aug 3, 2026 - Context window
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
Ecosystem
- Protocols supported
“type @ for tools & MCPs”
cursor.com · checked Aug 3, 2026- Tool use
“type @ for tools & MCPs, / for skills and commands”
cursor.com · checked Aug 3, 2026- Multi-agent
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
cursor.com · checked Aug 3, 2026 - API access
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Open source
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Marketplace presence
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
Impact
- User base
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Deployment scale
“Trusted by over half of the Fortune 500 to accelerate development, securely and at scale.”
cursor.com · checked Aug 3, 2026- Target sectors
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- High-risk domains
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Documented incidents
- no public informationcursor.com · checked Aug 3, 2026 · source did not state this
- Market recognition
- no public informationcursor.com · checked Sep 5, 2026 · source did not state this
Compared with
Side-by-side on the fields where Cursor and the other entry are both on record and actually differ.