agent · ai-coding-agents
Augment Code
29 fields evidenced · 26 with no public information. Every value below links to the document it came from and the date we checked it.
Trust gap
How this is scoredRuntime governance
2/3
Are scope, spend, and authority enforced while the agent runs?
Scored from 2 evidenced field(s): runtime_governance, permission_scopes. Automated score; capped at 2 pending review.
Audit trail
2/3
Is there a tamper-evident record of what it actually did?
Scored from 3 evidenced field(s): audit_trail, audit_trail_immutable, explainability. Automated score; capped at 2 pending review.
Compliance
unscored
Are compliance obligations attached per engagement?
Outcome settlement
unscored
Does payment depend on a verified result?
Insurance & indemnity
1/3
Can the deployment be insured, and is the customer indemnified?
Scored from 1 evidenced field(s): indemnification. Automated score; capped at 2 pending review.
How this gap gets closed →Assurance
- Insurance available
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Insurance carriers
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Coverage limits
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Indemnification
- Indemnified in our terms
“Indemnified in our terms”
augmentcode.com · checked Aug 1, 2026 - Liability cap
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Audit trail
- Audit logs + SIEM Replayable runs
“Audit logs + SIEM Replayable runs”
augmentcode.com · checked Aug 1, 2026 - Tamper-evident log
- Replayable runs
“Replayable runs”
augmentcode.com · checked Aug 1, 2026 - Explainability
- posts a plain-English diagnosis as a PR comment with a suggested fix.
“posts a plain-English diagnosis as a PR comment with a suggested fix.”
augmentcode.com · checked Aug 1, 2026 - Runtime governance
- Human-in-the-loop policies
“Human-in-the-loop policies”
augmentcode.com · checked Aug 1, 2026 - Permission scopes
- Granular RBAC
“Granular RBAC”
augmentcode.com · checked Aug 1, 2026 - Compliance certifications
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Regulatory alignment
- GDPR · CCPA · HIPAA
“GDPR · CCPA · HIPAA”
augmentcode.com · checked Aug 1, 2026 - Outcome-based pricing
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Settlement mechanism
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Dispute process
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- SLA terms
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Evaluation coverage
- SWE-Bench Pro
“SWE-Bench Pro”
augmentcode.com · checked Aug 1, 2026
Agency
- Autonomy level
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Human oversight
- Every action that matters approved by a human.
“Every action that matters approved by a human.”
augmentcode.com · checked Aug 1, 2026 - Goal complexity
- From design doc to shipped feature
“From design doc to shipped feature”
augmentcode.com · checked Aug 1, 2026 - Action space
- Reads a PR end-to-end — logic, edge cases, naming, security surface, and test completeness — then posts detailed inline comments with an approve / request-changes verdict.
“Reads a PR end-to-end — logic, edge cases, naming, security surface, and test completeness — then posts detailed inline comments with an approve / request-changes verdict.”
augmentcode.com · checked Aug 1, 2026 - Operating environment
- Codebase
“Codebase”
augmentcode.com · checked Aug 1, 2026 - Initiative
- Scans open tickets, applies a triage rubric, and dispatches the right expert as a worker.
“Scans open tickets, applies a triage rubric, and dispatches the right expert as a worker.”
augmentcode.com · checked Aug 1, 2026
Safety
- Safety evaluations
- SOC 2 Type II ISO/IEC 42001-certified
“SOC 2 Type II ISO/IEC 42001-certified”
augmentcode.com · checked Aug 1, 2026 - Red teaming
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Safety policy
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Usage restrictions
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Model or system card
- ISO/IEC 42001-certified Artificial Intelligence Management System
“ISO/IEC 42001-certified Artificial Intelligence Management System”
augmentcode.com · checked Aug 1, 2026 - Incident reporting
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Third-party evaluations
- SWE-Bench Pro
“SWE-Bench Pro”
augmentcode.com · checked Aug 1, 2026 - Data handling
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
Practicality
- Pricing model
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Price point
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Availability
- Try Cosmos
“Try Cosmos”
augmentcode.com · checked Aug 1, 2026 - Deployment options
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Integrations
- Slack · GitHub · Jira · CI
“Integrations Slack · GitHub · Jira · CI”
augmentcode.com · checked Aug 1, 2026 - Supported regions
- Data residency controls
“Data residency controls”
augmentcode.com · checked Aug 1, 2026 - Support model
- Dedicated account team
“Dedicated account team”
augmentcode.com · checked Aug 1, 2026
Foundation models
- Base models
- Prism (Claude + Gemini)
“Prism (Claude + Gemini)”
augmentcode.com · checked Aug 1, 2026 - Model provider
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Model swappable
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Open weights
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Fine-tuning
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Context window
- Gemini 2.5 Pro Long context tasks
“Gemini 2.5 Pro Long context tasks”
augmentcode.com · checked Aug 1, 2026
Ecosystem
- Protocols supported
- MCP Registry
“MCP Registry”
augmentcode.com · checked Aug 1, 2026 - Tool use
- Triggered on any failed GitHub Actions run — reads the log, identifies the root-cause step, and posts a plain-English diagnosis as a PR comment with a suggested fix.
“Triggered on any failed GitHub Actions run — reads the log, identifies the root-cause step, and posts a plain-English diagnosis as a PR comment with a suggested fix.”
augmentcode.com · checked Aug 1, 2026 - Multi-agent
- Orchestrate agents across your SDLC
“Orchestrate agents across your SDLC”
augmentcode.com · checked Aug 1, 2026 - API access
- Proof-of-Possession API
“Proof-of-Possession API”
augmentcode.com · checked Aug 1, 2026 - Open source
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- Marketplace presence
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
Impact
- User base
- Trusted by leading enterprises
“Trusted by leading enterprises”
augmentcode.com · checked Aug 1, 2026 - Deployment scale
- Cosmos runs your software agents at scale
“Cosmos runs your software agents at scale”
augmentcode.com · checked Aug 1, 2026 - Target sectors
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this
- High-risk domains
- HIPAA BAA available
“HIPAA BAA available”
augmentcode.com · checked Aug 1, 2026 - Documented incidents
- no public informationaugmentcode.com · checked Aug 1, 2026 · source did not state this