Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
Resolve AI puts AI agents inside your production stack: on-call, incidents, and operational tasks, so your engineers can get back to building. Built by Spiros Xanthos and Mayank Agrawal, co-creators of OpenTelemetry, Resolve AI is the AI SRE that sits between your tools and your team. Agents investigate, triage, and remediate across telemetry, code, cloud, and runbooks, while engineers direct, approve, and build.
Four ways in: agents join every on-call rotation to triage and investigate alerts; teams of agents work incidents alongside your engineers to root cause; background agents run operational workflows on a schedule or trigger; and you can build custom agents on top of Resolve AI via MCP, API, and Skills.
Show the rest of the publisher’s description (2 more lines)
In production at DoorDash, Coinbase, Expedia Group, Snowflake, MongoDB, Toast, Eventbrite, and Zscaler, Resolve AI drives up to 5x faster MTTR and 75% higher engineering productivity. DoorDash saw 87% faster incident investigations after putting Resolve AI on-call for its advertising platform.
Resolve AI is SOC 2 Type II, GDPR, and HIPAA compliant, with SAML SSO, RBAC, and admin controls; customer-isolated data with encryption and retention controls.
Highlights
Highlighted by the publisher on AWS Marketplace.
A harness of specialized agents for production operations. Separate agents triage, investigate, and verify in parallel, with a dedicated verifier model re-checking every finding against production evidence before it's finalized. Models are post-trained for causal reasoning across production systems, not just correlation, and paired with the best available frontier models, continuously evaluated and upgraded as new models ship.
Collaborative canvas for humans and agents to get to RCA and remediation quickly. Steer any theory in natural language, run your own queries alongside the agent, and merge what you find back into the report without leaving the surface. Ask the agent direct questions and get evidence-backed answers, loop in teammates on the same thread, and approve, redirect, or override any finding or action before it ships. Human and agent, working the same problem together.
Resolve ships as a plugin for Claude Code, Cursor, and Codex, backed by an MCP server any other agent can call directly. Pull production context before a risky change, join a live incident investigation, and turn a root cause into a pull request, all without leaving your editor. Bring your own skills and tools; the same guardrails and audit trail carry over automatically.
Preview
4 images
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment
Plans and pricing as listed
1 listed- Units
Refund terms
As stated by the publisher on AWS Marketplace.
All fees are non-cancellable and non-refundable except as required by law.
Sources
Publisher resources
6 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.