José Miguel Gómez

Back to the home page

Resolvo

Autonomous incident triage and remediation with human-in-the-loop

Technical title: Enterprise Agentic Triage Engine

The code lives in a private repository; this sheet and the demo, when there is one, show the work.

Draft. Written from the program notes and pending the author’s review.

Status
Now showing
Type
Enterprise AI system
Running time
November 2026 – December 2026
Role
Architect and sole engineer
Domains
ITSM, AIOps
Cast
Python, LangGraph, Java, Spring Boot, PostgreSQL, pgvector, Kafka, MCP, OpenTelemetry

Context and problem

Agent-driven triage for enterprise incidents: classify, enrich and route in seconds, with a human in the loop.

L1/L2 teams spend about 18k EUR per month on manual triage (assumption documented in docs/pitch.md).

Support teams lose hours per incident to manual triage. Resolvo turns alerts into reviewed remediations in minutes, with every action logged and approved.

Architecture and interfaces

Provides
events incident.*, mcp resolvo, api resolvo-api
Consumes
mcp threadline, events outage.* (tideline)
Shared keys
user_code, request_id, endpoint, error_code

Case study in preparation

The full case study adds these sections when it is published:

  • Constraints
  • Architecture diagrams (C4 context and containers)
  • Three key decisions
  • What went wrong
  • Results with dated evidence
  • Demo video
  • What I would do differently

In the project mesh

  • Specgate, zero effort: 2 shared keys (endpoint, error_code) and both expose an api or mcp interface
  • Tideline, zero effort: interface outage.* provided by one and consumed by the other
  • Forgeline, low effort: shared resources llm-gateway; a standard interface exists
  • Revela, low effort: shared resources llm-gateway; a standard interface exists
  • Sublingua, low effort: shared resources llm-gateway; a standard interface exists
  • Vigilo, low effort: shared keys endpoint; a standard interface exists

Highlights

durable agents, human in the loop, MCP tools, OpenTelemetry GenAI, hybrid RAG