Harbor

Overview

How testing, scoring, and guardrails work together.

Agents don't fail like traditional software. A prompt tweak, a model upgrade, or a new tool can change behavior in ways unit tests never exercise — and because agents take actions, a bad trajectory isn't just a wrong answer. It's a refund issued, an email sent, a record deleted.

Most teams discover agent risk in production, one incident at a time. Harbor replaces that with a loop you run on every release.

Testbefore releaseScorein productionGuardat runtimefindingssignalshits become next release's test cases

Each stage feeds the next: what testing finds, scoring watches for; what scoring surfaces, guardrails contain.

How Harbor connects

Harbor ingests OpenTelemetry traces from your agent through one of two paths. Both produce the same traces and power the same risk assessment — they differ in what they can see and how much you have to change.

SDKGateway
What you changeA few lines in your agentYour LLM base URL, nothing else
Sees tool callsWith their actual execution resultsAs the model proposes them
Enforces guardrailsInline, in your processInline, on the wire
Covers many agents at onceOne integration eachYes, via one URL swap

Running both is the highest-assurance setup, not a conflict: the SDK enforces at ground truth while the gateway guarantees capture. Spans are deduplicated by trace and span id, so a call captured twice appears once.

Test with Adversarial Testing

White-box maps every AI system in your repositories — agents, tools, system prompts, memory, retrieval, MCP connections — and builds a dependency graph for each one. When a change lands, Harbor compares the changed files against those graphs, works out which systems the change can actually reach, and scans only those against our vulnerability cookbook of AI-specific exploit patterns.

Connect your repository so every pull request is assessed.

Review white-box findings on the systems each change affects.

With those findings, black-box adversarial testing runs attack scenarios against a provisioned instance of your agent — inspect the resulting attack trajectories.

Outcome: every release ships with a documented assessment instead of an assumption.

Score with Risk Score

In production, Harbor runs its proprietary risk assessment on every trace and trajectory it ingests, producing a risk score you can baseline, trend, and alert on.

Instrument your agent with the SDK or route it through the Gateway.

Explore scored traces and trajectories to see where risk concentrates.

Set thresholds and alerts so risky behavior surfaces immediately.

Outcome: risk becomes a number you can track per agent, per release.

Guard with Guardrails

Guardrails cap the inputs of your agent's tools — amounts, recipients, scopes, and anything else an agent passes along. Enforcement runs inline through the Gateway or the SDK, so a call that exceeds its cap never reaches the tool.

Define input caps per tool, informed by what testing and scoring found.

Enforce them inline via the Gateway or the SDK.

Review guardrail hits alongside risk scores.

Outcome: a confused or compromised agent is bounded by policy, not by luck.

The loop closes

Guardrail hits and high-risk trajectories become adversarial test cases for your next release.

Next steps

On this page