§2 Selected work

TracePilot

Evidence-grounded incident investigation for distributed systems

Status
Feature-complete local system and hosted-demo template
Role
Sole public repository contributor; designed and implemented the application, evaluation gates, safety boundaries, and deployment template.
Domain
Observability / Distributed Systems
Figure 1Shows the incident path from OpenTelemetry input through time and topology scoping to correlation and an evidence-cited diagnosis. The incident identifier and its seven linked signals are an illustrative walkthrough, not a recorded incident, and no latency or accuracy figures appear.
§1Brief

The problem this had to solve.

Turn fragmented incident telemetry into reviewable root-cause candidates without allowing a diagnostic model or public demo to become an unrestricted remediation control plane.

TracePilot brings service topology and operational telemetry into one incident context, correlating Prometheus metrics, Loki logs, Jaeger traces, and change evidence.

The platform ranks plausible root causes, retrieves runbooks, cites supporting evidence, and tracks model evaluation and human feedback. Reproducible Kubernetes fault experiments and controlled sandbox recovery keep investigation behavior testable and reviewable.

Constraints

  1. Telemetry collection uses fixed, bounded, read-only queries and persists immutable checksummed bundles before analysis.
  2. The learned models are trained on generated laboratory incidents, not real production incidents.
  3. Experiments and the single recovery action run only through separately trusted local workers with closed, typed interfaces.
  4. The hosted profile is a deployment template; it has not been deployed to a cloud provider or measured under production load.
§2Architecture

How the system is put together.

Service graph

Distributed-system topology and alert context

source

Incident

Unifies the active investigation scope

process

Evidence correlation

Logs, metrics, traces, topology, and changes

process

Root-cause ranking

Orders candidate causes against collected evidence

decision

Evidence-cited diagnosis

Returns auditable conclusions and runbook context

output
§3Decisions

What was chosen, and what it cost.

Replay immutable evidence

Choice
Store checksum-addressed telemetry bundles in MinIO and perform RCA against replayed artifacts rather than querying live systems during analysis.
Rationale
An investigation can be reproduced and its evidence remains tied to the incident window that produced it.
Cost
Collection failures and missing signals stay visible; the system does not silently backfill them from a later live state.

Gate learned models against a deterministic baseline

Choice
Retain the root-cause ranker as an unpromoted candidate when its held-out result underperforms the graph baseline.
Rationale
A passing absolute score is insufficient when a simpler deterministic method performs better.

Close the action surface

Choice
Expose seven read-only investigations and one typed, human-approved local recovery action instead of arbitrary shell, Kubernetes, or provider commands.
Rationale
Diagnosis and recovery remain separate reviewable capabilities with a bounded blast radius.
Cost
The safety boundary intentionally limits automation and is not a general remediation framework.
§4Validation

How it was checked.

  • The repository records passing lint, strict type checking, backend/frontend tests, production builds, deterministic OpenAPI export, and eight Compose-backed integration tests.
  • A generated 180-incident laboratory dataset evaluates the ranker at Top-1 0.854 and the deterministic baseline at Top-1 1.0; the ranker correctly remains ineligible for promotion.
  • The production profile validation, deterministic security scan, PostgreSQL backup/restore test, and local Kind readiness checks are documented as passing.
  • The bounded localhost liveness smoke test completed 40/40 requests with p50 52.628 ms and p95 97.919 ms; it is not a capacity benchmark.
§5Evidence

What was measured.

Each figure states the conditions it was measured under. None of them describe production traffic.

5

evidence channels

Metrics, logs, traces, topology, and change evidence are correlated.

Auditable

root-cause ranking

Diagnoses retain evidence citations for review.

§6Limits

Where this stops being true.

  • No real incident corpus, telemetry shift study, privacy review, fairness assessment, threshold tuning, or production SLO evidence exists.
  • The checked-in models cover five synthetic fault classes and must not be used for operational decision-making.
  • The hosted template still requires provider-managed secrets, TLS, ingress controls, durable object storage, and digest-specific vulnerability scanning.
  • The Kubernetes and Chaos Mesh environment is a local Kind laboratory, not a production deployment target.
§7Technology

What it is built with.

Runtime & interface

  • Python
  • FastAPI
  • Next.js

Data & evaluation

  • PostgreSQL
  • pgvector
  • Redis
  • MLflow

Infrastructure & providers

  • Kubernetes
  • Prometheus
  • Loki
  • Jaeger
  • OpenTelemetry
  • MinIO
Next documentReal-Time Fraud Detection Pipeline