Resolve AI
AI SRE that goes on call for engineering teams: a team of specialized agents triages alerts and investigates incidents in parallel, background agents run operational tasks, and actions wait for human approval by default.
Resolve AI builds an AI SRE that goes on call on a team's behalf. The On-call Agent holds the pager and triages alerts, the Incident Resolution Agent investigates with a team of domain specialized agents that pursue hypotheses in parallel and have a dedicated reviewer check findings against production evidence, and Issue Remediation works recurring problems and hands production context to coding agents.
Background agents run operational tasks such as deploy health checks, daily digests and resource reports on a schedule, when a matching message appears in a Slack or Microsoft Teams channel, or on demand, starting from a template library. Engineers follow an evidence trail and a Workbench view of what each agent is doing, and can redirect agents or add context mid investigation.
Action is gated. Resolve proposes alert silences in Grafana, Datadog, AlertManager, Kloudfuse or Sumo Logic and fix pull requests, and these run only after a person approves them in the Resolve UI or Slack. GitHub Actions workflow tools, in preview, also default to approval, and an admin can let an individual tool run on its own.
The model that proposes actions never calls write APIs itself, and every proposal is recorded with who proposed it, who approved or rejected it and what was affected. Teams guide investigations with Team Knowledge and skills in the open Agent Skills format, held at organization, team and personal level.
The agent proposes runbook and doc updates from conversations and completed investigations, and teams tune accuracy by rating reports and re-running the same alert after a change to compare results.
Resolve connects to about 40 observability, cloud, code and ticketing systems, directly or through a Satellite agent that keeps credentials inside the customer's infrastructure, and runs as a shared multi tenant service or a dedicated single tenant deployment with customer keys. It exposes a REST API, an MCP server and plugins for Claude Code, Codex and Cursor, holds SOC 2 Type II, GDPR and HIPAA, and prices through credit metered contracts with no public rates.
From our comparison video
Resolve AI vs Traversal (2026): Which Should You Choose?
Our 5 minute video puts Resolve AI side by side with Traversal. It covers what each one does and how each is priced, then when to choose which.
Recorded in October 2026. The profile here is live and updates as research is verified.
Vendor details
Canonical URL
https://resolve.ai
Category
SRE / DevOps agent
Subcategory
AI SRE agent
Funding status
Independent, founded by former Splunk engineers behind OpenTelemetry and Log Insight. Valued at $1.5 billion after a $40 million extension of its Series A in April 2026, led by DST Global and Salesforce Ventures, with more than $190 million raised in total. Named customers include Coinbase, DoorDash, MSCI, Salesforce, Zscaler, MongoDB, Toast, Snowflake, Robinhood, and Pinecone.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Resolve connects to about 40 systems, including AWS, GCP, Datadog, Dynatrace, Splunk, Grafana, New Relic, Honeycomb, Sentry, PagerDuty, ServiceNow, Snowflake, GitHub, Atlassian and Glean, with Slack and Microsoft Teams apps. A Satellite agent in Kubernetes or ECS reaches on premises tools. It exposes a REST API, an MCP server, alert webhooks and a Temporal integration.
In practice
An incident spans logs, metrics, traces and three services and your on call engineer is guessing. Resolve runs specialized agents on parallel hypotheses and a reviewer checks the root cause against production evidence.
Alerts pile up overnight before anyone looks. Resolve's On-call Agent holds the pager and triages alerts, escalating with context.
You want the SRE agent inside your own automation, not a separate dashboard. Resolve exposes a REST API, an MCP server and assistant plugins to trigger and read investigations.
Sources & related URLs
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
An integration catalog of about 40 systems covers AWS, GCP, Azure, Datadog, Dynatrace, Splunk, Grafana, New Relic, PagerDuty, ServiceNow, Sentry, Snowflake, GitHub, Atlassian, Slack and Microsoft Teams, plus any connected MCP server. On approval the agent creates silences, downtimes or mutes in Grafana, Datadog, AlertManager, Kloudfuse and Sumo Logic, opens fix pull requests and dispatches GitHub Actions workflows. SourceResolve docs llms.txt index, Mitigation Actions and Security and Administration; docs.resolve.ai/mitigation-actionsread 2026-10-22 |
|
| Workflow Orchestration | Full |
|
A team of domain-specialized agents investigates in parallel, pursuing hypotheses that engineers can redirect, and verifies findings against production evidence, with a dedicated reviewer validating them. Custom agents compose Resolve's MCP, API and skills into the customer's workflows, and Temporal connects orchestration platforms. Sourceresolve.ai/product/incidentsread 2026-10-22 |
|
| Knowledge Grounding & RAG | Full |
|
Team Knowledge is a maintained store of runbooks, docs, dashboard guidance and skills at organization, team and personal level that Resolve activates dynamically during investigations, examining all knowledge tied to the alert and its owning teams. Skills follow the open Agent Skills format and load on demand, and Hivemind adds production state awareness across alerts and incidents. Sourcedocs.resolve.ai/team-knowledgeread 2026-10-22 |
|
| Human Oversight & Guardrails | Full |
|
Alert silences and fix pull requests run only after a person approves them in the Resolve UI or Slack. GitHub Actions workflow tools, in preview, also default to approval, and an admin can let an individual tool run on its own. The model that proposes actions never calls write APIs, which a separate engine executes, and write permissions are enabled per integration. Sourcedocs.resolve.ai/security-and-administrationread 2026-10-22 |
|
| Security, Identity & Governance | Full |
|
Customers get SSO (Google, Okta, Azure AD), SCIM directory sync with sign in enforcement, RBAC, access limited to roles, environments or namespaces, and audit logs. Compliance covers SOC 2 Type II, GDPR and HIPAA, backed by a trust center. SourceResolve security page and docs llms.txt index (Security and Administration pages); resolve.ai/securityread 2026-10-22 |
|
| Observability & Auditability | Full |
|
Each investigation shows an Evidence Trail with timestamps and verification and a Workbench of what each agent is doing. An Activity Dashboard records every action, including who proposed it, who approved or rejected it, when, and what was affected. Sourcedocs.resolve.ai/mitigation-actionsread 2026-10-22 |
|
| Memory & State Persistence | Partial |
|
The agent keeps learnings it has accumulated, which its tasks can read, and proposes new runbooks and edits to team docs from a conversation or by reviewing completed investigations for lessons. Resolve does not say how those learnings are stored, reviewed or deleted, and Team Knowledge itself is written by people. Sourcedocs.resolve.ai/tasksread 2026-10-22 |
|
| Deployment & Data Residency | Partial |
|
Customers choose between a shared multi tenant cloud and a dedicated single tenant cloud deployment with bring your own keys. The Satellite agent runs in the customer's Kubernetes or ECS, keeps credentials local and proxies queries into Resolve's cloud. There is no region list or customer environment option. Sourcedocs.resolve.ai/resolve-satelliteread 2026-10-22 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Separately named agents ship for their own jobs, namely the On-call Agent that holds the pager and triages alerts, the Incident Resolution Agent for root cause and mitigation, and Issue Remediation for recurring problems. Background agents for operational tasks start from a template library that includes a deploy health monitor, a daily digest, an alert triager and a resource report. Sourceresolve.ai/product/operational-tasksread 2026-10-22 |
|
| Triggers & Channel Coverage | Full |
|
The On-call Agent goes on call on the customer's behalf, holding the pager and triaging alerts. Alerts arrive by PagerDuty, Splunk On-Call and alert webhooks from any source. Tasks run on a schedule or cron, when a matching message appears in a watched Slack or Microsoft Teams channel, or on demand, and the Teams app investigates alerts posted to alert channels. Sourcedocs.resolve.ai/tasksread 2026-10-22 |
|
| Model Flexibility & Routing | Not documented |
|
Resolve uses frontier LLM models combined with domain-specific models, without naming a provider, and customers cannot choose a model. Sourceresolve.airead 2026-10-22 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API at app0.resolve.ai with bearer personal or organization tokens triggers, lists and reads investigations, alongside a Resolve MCP server, plugins for Claude Code, Codex and Cursor, and skills in the open Agent Skills format. Sourcedocs.resolve.ai/resolve-rest-apiread 2026-10-22 |
|
| Testing, Debugging & Optimization | Full |
|
A change can be evaluated against an earlier result. After updating knowledge or integrations, Reinvestigate alert re-runs the same alert so the new result can be compared against the original, and thumbs up or down verdicts on each report collect under Analytics, Feedback. Sourcedocs.resolve.ai/tuning-accuracyread 2026-10-22 |
|
| Browser & Computer Use | Not documented |
|
Work runs through integrations, a Satellite proxy, Slack, Microsoft Teams, a REST API and an MCP server, with no browser, desktop or computer control. SourceResolve docs llms.txt index and Incidents page; resolve.ai/product/incidentsread 2026-10-22 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Resolve AI officially launched its AI Production Engineer, an agentic AI system designed to automate production engineering tasks. The platform autonomously troubleshoots issues, manages operational tasks, and investigates incidents by leveraging context from source code, telemetry, and cloud infrastructure.
Bears on: Agent capability
View sourceResolve AI announced a $125 million Series A funding round led by Lightspeed Venture Partners. This brings its total funding to over $150 million and values the company at $1 billion, providing capital to scale research and development for its production AI agents.
Bears on: Agent capability
View sourcePricing
Contact sales. Contracts are metered in credits, and no rates are published.
Credits per unit of work, consumed by chats and tasks, investigations, incidents and triages. The credit cost of each is defined in the contract.
Included quota
A credit allowance defined in the contract. No public tiers.
What is public
The credit meter, meaning which actions consume credits, and the monthly cap on automated work are public. No dollar figures, tiers or credit costs are.
Billing mechanics
Enterprise contracts are metered in credits for the work Resolve does, and each action's credit cost is set in the contract. A monthly cap on automated work pauses background runs until the month ends or the cap is raised.
Cost watchouts
Every chat, task, investigation, incident and triage consumes credits at contract rates, so alert volume drives spend.
Variable cost rationale
Resolve meters credits. Every chat, task, investigation, incident and triage consumes credits at a cost set in the contract, so spend grows with alert and investigation volume and with how much automated work runs. An optional monthly cap limits it. Once automated work reaches the cap, background runs pause until the month ends or the cap is raised, while manually started work continues.
Additional watchouts
Cost follows how much automated triage and investigation runs, and always on agents keep drawing credits up to the monthly cap, or without limit when no cap is set. Nothing numeric is published.
Overage / add-ons
No overage rate is published. A monthly credit cap pauses automated work, never manually started work.
Sales call required
Yes, required for paid access
Free / trial
Enterprise evaluations and proofs of value through sales. No self serve trial.
Lowest paid plan
Not published. Enterprise contracts only.
Commercial notes
Resolve AI is independent, valued at $1.5 billion with more than $190 million raised, and was founded by the people behind OpenTelemetry and Log Insight. Coinbase cites ten times productivity and 73 percent faster RCA, and DoorDash up to 87 percent reduction in time to RCA.
Key ambiguities
The credit meter is published, but credit prices and any included allowance are not.
Related vendors
- AlertD — AI agents for AWS operations that run read only in the customer's…
- Anyshift — AI SRE built on a versioned knowledge graph of infrastructure, apps…
- Avesha — Obliq, Avesha's autonomous AI SRE for Kubernetes and agentic…
- Better Stack — Better Stack offers incident management with built in on call,…
- Bluebricks — Context and control layer that lets AI agents operate cloud…
- Cased — AI workflows for infrastructure and platform engineers: default and…
Alternatives to Resolve AI
The closest documented capability profiles to Resolve AI among SRE and DevOps agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Better Stack9.5 / 14A lighter documented profile than Resolve AI
- Bluebricks10.5 / 14Fuller documented coverage on Deployment & Data Residency
- Fabrix.ai12.5 / 14Adds documented Model Flexibility & Routing
- PagerDuty10.5 / 14Fuller documented coverage on Deployment & Data Residency
- TierZero11.5 / 14Fuller documented coverage on Memory & State Persistence and Deployment & Data ResidencyResolve AI vs TierZero →
- Edge Delta12.0 / 14Adds documented Model Flexibility & Routing
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded