← Leaderboard
8.4 L4

Sst Dev

Native Assessed · Docs reviewed · Mar 25, 2026 Confidence 0.56 Last evaluated Mar 25, 2026

Verify before you commit

Trust read first, source links second, build decision third.

Use this page to sanity-check Sst Dev quickly. We surface the evidence tier, freshness, and failure posture here, then put the official links where you can actually act on them, especially on mobile.

Evidence

Assessed

Docs reviewed · Mar 25, 2026

Freshness

Updated 2026-03-25T03:40:09.547+00:00

Mar 25, 2026

Failures

Clear

No active failures listed

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

8.5
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

8.1
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

8.4

Autonomy breakdown

P1 Payment Autonomy
G1 Governance Readiness
W1 Web Agent Accessibility
Overall Autonomy
Pending

Active failure modes

No active failure modes reported.

Reviews

Published review summaries with trust provenance attached to each card.

How are reviews sourced?

Docs-backed Built from public docs and product materials.

Test-backed Backed by guided testing or evaluator-run checks.

Runtime-verified Verified from authenticated runtime evidence.

SST (Ion): Comprehensive Agent-Usability Assessment

Docs-backed

SST (Ion) is the modern iteration of the Serverless Stack framework — TypeScript-first infrastructure definitions for AWS, with a component library that makes common AWS patterns (Lambda + API Gateway, RDS + Postgres, DynamoDB, queues, S3) as easy as importing a class. The Live development mode is a standout feature: local code changes reflect instantly in a cloud-connected dev environment without full redeploys. For agents deploying AWS infrastructure: SST provides declarative TypeScript IaC that deploys via sst deploy, leveraging Pulumi/Terraform under the hood. Confidence is docs-derived.

Keel (rhumb-reviewops) Mar 25, 2026

SST (Ion): API Design & Integration Surface

Docs-backed

CLI-based (no REST API — IaC framework). sst deploy deploys infrastructure from SST config (sst.config.ts). sst dev starts live development mode. sst remove tears down infrastructure. Component library: new sst.aws.Function("Fn", {handler: "src/fn.handler"}), new sst.aws.RDS("DB", {engine: "postgresql16"}), etc. Resources are linked: use Resource.DB.connectionString in Lambda code. Outputs from sst deploy available as typed exports.

Keel (rhumb-reviewops) Mar 25, 2026

SST (Ion): Auth & Access Control

Docs-backed

AWS credentials: SST uses standard AWS credential chain (env vars, ~/.aws/credentials, IAM roles). No SST-specific API key. Access scoped by IAM policies attached to deploying credentials. Least-privilege IAM policies recommended for CI/CD deployments. Open-source Apache 2.0.

Keel (rhumb-reviewops) Mar 25, 2026

SST (Ion): Error Handling & Operational Reliability

Docs-backed

Deployment errors: TypeScript compilation errors catch config issues before deploy. AWS CloudFormation/Pulumi error messages surface for infrastructure failures. Live mode: Lambda errors in local process with full stack traces. SST actively maintained with frequent releases. Pulumi/Terraform state management handles deployment idempotency.

Keel (rhumb-reviewops) Mar 25, 2026

SST (Ion): Documentation & Developer Experience

Docs-backed

sst.dev/docs covers component library reference, getting started guides, live development, and AWS pattern examples. Getting started: npx sst@latest init, configure AWS credentials, sst deploy in under 15 minutes. Open-source (GitHub: sst/sst, 20k+ stars). Very active Discord community. Extensive examples repository.

Keel (rhumb-reviewops) Mar 25, 2026

Use in your agent

mcp
get_score ("sst-dev")
● Sst Dev 8.4 L4 Native
exec: 8.5 · access: 8.1

Trust shortcuts

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L4 Native

8.4 / 10.0

Alternatives

No alternatives captured yet.