Custom agents

Build custom agents on Resolve AI

Compose Resolve AI primitives into your own agents and existing workflows. Use context, investigation, and remediation without rebuilding them

Get a demo

See how it works

01Build 02Workflow 03Skills

01Build

Build your own agents on Resolve

Resolve is exposed as MCP, API, and Skills. Your agents call Resolve for production context, investigation, and remediation, without rebuilding the primitives

~/orders-platform · Claude Code · 110x47

Claude Code v2.1.141

>I noticed checkout-service has been slow today. Is the CPU utilization high?

resolve-prod · resolve_query_telemetry (MCP)(service: "checkout-service", window: "today")

2 anomalies found

resolve-prod · resolve_get_investigation (MCP)(canvasId: "01KQHYG…ZQ4F")

Status: concluded · 8 evidence items

Root cause: Connection pool exhaustion, not CPU. RDS CPU is ~10% (baseline). All 80 connections on the primary are held by one long-running reporting query (running 8m), blocking new checkout transactions since 14:18 UTC.

Recommendations from Resolve:

Terminate blocking query pid 18472 to free connections immediately.
Suggested fix: Add statement_timeout = '30s' to the reporting-service DB role at db/roles/reporting.tf:42.
Follow-up: rewrite the aggregation in report_engine.go:142 to avoid full scans.

View in Resolve: app.resolve.ai/chat/01KRKY…XQ4F

? for shortcuts

02Workflow

Use Resolve in the workflows your team already lives in

Call Resolve from Slack, your CLI, your IDE, or another agent. Production context and remediation surface wherever your engineers already work

cmd/support-monitor/main.goGo

// When customer tickets cluster on a theme, // hand them to Resolve to investigate. func onTicketCluster(c *support.Cluster) { resolve.Investigations.Create(&resolve.NewInvestigation{ Trigger: "support-cluster", Title: c.Summary(), Services: c.LikelyServices, Context: resolve.Context{ "ticket_count": c.Size, "common_symptom": c.Theme, "sample_ids": c.SampleIDs[:5], "first_seen_at": c.FirstSeen, }, Runbook: "customer-symptom-investigation", }) }

POST/v1/investigations

Triaged· 8sjust now

12 customer tickets in 15m: “can’t complete checkout”

support-clusterfrom:support-monitorservice:checkout-service

Runbook attached: customer-symptom-investigation

Context attached

ticket_count: 12
common_symptom: “can’t complete checkout”
sample_ids: [INC-4821, INC-4824, INC-4829, +2]
first_seen_at: 4m ago

03Skills

Plug your skills into Resolve

Resolve consumes the runbooks, internal tools, and tribal knowledge your team has already built. Every investigation uses what you already have

Skills

Add

pg-replication-lag

Sourceacme-platform/sre-skills · postgres/pg-replication-lag/SKILL.md

Last syncedabout 18 hours ago

kafka-consumer-lag

Sourceacme-platform/sre-skills · kafka/kafka-consumer-lag/SKILL.md

Last syncedabout 18 hours ago

deploy-health-check

Sourceacme-platform/sre-skills · deploy/deploy-health-check/SKILL.md

Last syncedabout 18 hours ago

rds-cpu-investigation

Sourceacme-platform/sre-skills · infra/rds-cpu-investigation/SKILL.md

Last syncedabout 18 hours ago

oncall-handoff

Authored byDaniel Park

Last edited3 days ago

incident-postmortem

Authored byMaya Lin

Last edited9 days ago

Used and loved by engineers

Removing the toil of investigations, war rooms, and on-call

We pull fewer engineers into war rooms, on-call is materially better, and that translates directly to advertiser trust and revenue protection.

Shahrooz Ansari

Sr. Director of Engineering, DoorDash

I don't need more numbers or more data. What I need is a root cause.

Chris Umbel

AIOps Lead & SRE, Zscaler

Resolve AI proved it could deliver real results in a constrained environment. It identified dependencies, surfaced accurate root causes 73% faster than our teams, all while integrating cleanly into our existing stack.

Angelo Marletta

Staff Software Engineer, Coinbase

Resolve AI makes our junior on-call engineers as effective as our seniors, flattening the experience curve. We've seen a 2x productivity lift while eliminating the runbook gap.

A.D.

Sr. Director of Engineering, Financial Services Company

We pull fewer engineers into war rooms, on-call is materially better, and that translates directly to advertiser trust and revenue protection.

Shahrooz Ansari

Sr. Director of Engineering, DoorDash

I don't need more numbers or more data. What I need is a root cause.

Chris Umbel

AIOps Lead & SRE, Zscaler

Angelo Marletta

Staff Software Engineer, Coinbase

Resolve AI makes our junior on-call engineers as effective as our seniors, flattening the experience curve. We've seen a 2x productivity lift while eliminating the runbook gap.

A.D.

Sr. Director of Engineering, Financial Services Company

Recent updates

Shipping every week

See all updates

May 2026
MCP server beta
Call Resolve from any MCP-compatible client
May 2026
Skills SDK
Define agent skills in Python or TypeScript
May 2026
Slack action surface
Trigger investigations from Slack threads
April 2026
Public API
Programmatic access to Resolve primitives

Frequently asked questions

Build agents that fit your stack

Request a demo

Read the docs

Social

Build custom agents on Resolve AI

Build your own agents on Resolve

Use Resolve in the workflows your team already lives in

12 customer tickets in 15m: “can’t complete checkout”

Plug your skills into Resolve

pg-replication-lag

kafka-consumer-lag

deploy-health-check

rds-cpu-investigation

oncall-handoff

incident-postmortem

Used and loved by engineers

Shipping every week

MCP server beta

Skills SDK

Slack action surface

Public API

Frequently asked questions

How do I get started building a custom agent?

What can I bring from my existing setup?

How do agents access internal tools?

Is this only for technical teams?

What is the security model?

Can I run Resolve fully self-hosted?

Build agents that fit your stack

Machines on call for humans

Join the conversation