spanshot

Investigate failures from the telemetry your system already emits.

spanshot turns OpenTelemetry signals into focused, inspectable investigations for AI agents and developers.

Silent animation: services emit traces, metrics and logs. An error triggers context capture. An agent inspects the evidence, tests and revises a fix, then proposes a pull request for review. Click the animation or use Enter or Space to play or pause.

Failures leave signals. Investigations still start from scratch.

Distributed systems continuously emit traces, logs and events. But that evidence is fragmented across tools. Before they can reason about a failure, AI agents and engineers still have to find, correlate and reconstruct the relevant context.

Start from the investigation. Choose what happens next.

Harness ownership

Your harness

spanshot harness

PUSHOn event
PULLOn demand
Agent / workflow+ spanshot webhooksHermes · n8n · Temporal · …
spanshot agentEvent-triggered loop
Coding agent+ spanshot MCPCodex · omp · Cursor · …
API gateway, services, database, queue, worker and cache continuously send signals to spanshot for detection and investigation. On an event, spanshot can activate your agent or workflow through webhooks, or its own harness. On demand, your coding agent can retrieve investigation context through spanshot MCP. Examples include Hermes, n8n and Temporal for event-driven workflows, and Codex, omp and Cursor for coding agents. The animation shows detection, push activation, a quiet interval, then a pull request and returned context. Telemetry remains live throughout.

Principles behind every investigation

Telemetry-triggered

The failure starts the investigation.

spanshot begins from failure signals as they happen, instead of waiting for someone to assemble the evidence.

Prepared for reasoning

Ready for an AI agent or an engineer to investigate.

The behavior relevant to a failure is organized before the analysis begins.

Grounded and inspectable

See what the analysis is based on.

The original telemetry stays available alongside the investigation, you inspect the evidence, not just an AI conclusion.

What spanshot is not

Not error monitoring

Error monitoring tells you that something broke, how often, and where it was thrown.

instead

spanshot organizes the behavior around one failure across services, so it can actually be reasoned about.

Not a general coding agent

An agent working from the repository infers what probably happened from the code it can read.

instead

spanshot hands it the runtime evidence of what did happen, from the telemetry the system emitted.

Not a dashboard with a chat box

Asking questions over charts still leaves you assembling context and trusting a summary.

instead

The original telemetry stays attached to a focused investigation. The system is open source and OpenTelemetry-native, with no proprietary instrumentation.

Start the investigation from the telemetry you already have.

spanshot prepares a focused, inspectable investigation for developers and AI agents.