← All posts
Methodology

A finding isn't real until it reproduces three ways

An attack that works once might be luck. Before a security team can act on a finding, someone has to know whether it recurs. Here's how we turn one-off jailbreaks into evidence a release decision can stand on.

01
Strict
Exact same steps, verbatim
02
Guided
Same strategy, reworded
03
Free
Whole campaign regenerated
Deterministicaudit-ready
Reproducibleaudit-ready
Probabilisticmonitor
Anecdotalnote only
Three replay modes → four confidence tiers · filter to the highlighted band for release decisions

Here’s a situation every red team knows. You run a campaign, something breaks, you write it up — and then someone asks “does it always do that?” and you don’t actually know. You saw it once.

For research, one is enough to be interesting. For a release decision, one is a coin you flipped once. A security owner can’t tell engineering to hold a launch over a bug that might have been a fluke, and engineering can’t prioritize a fix for something that might never recur. A finding you can’t reproduce isn’t evidence. It’s an anecdote.

So Fisher doesn’t stop when an attack lands. That’s where the real work starts.

Replay it three ways

When Fisher lands a breach, it re-runs the finding under three conditions, each looser than the last. The point is to pull apart why it worked.

  1. Strict replay — the exact same steps, verbatim. Does the identical sequence break the agent again? This tells you whether the vulnerability is deterministic.
  2. Guided replay — same strategy and key decision points, but the wording is regenerated. This tests whether the approach works, not just the one lucky phrasing.
  3. Free replay — only the strategy name is kept; the whole campaign is generated fresh. This tests whether the vulnerability class is robust, or whether you caught the model on a bad day.

A finding that survives all three is a systematic weakness. A finding that only ever works with one exact string is an edge case worth noting but not worth blocking a launch over. The three modes let you tell those apart instead of guessing.

Four tiers, so you can filter

From how consistently a finding recurs across those modes, Fisher assigns one of four confidence tiers:

Now a governance team has a knob. Before a release, filter to deterministic and reproducible and ignore the rest. You’re making the call on the findings that will actually recur in production, not on the long tail of one-offs. “Show me only the findings that reproduce reliably” becomes a real query instead of a wish.

What the distribution looks like at scale

We’ve run this across a large body of evidence — tens of thousands of episodes replayed. Roughly a third land in the deterministic tier, a smaller slice in reproducible, with the rest spread across probabilistic and anecdotal.

The headline that matters for a buyer: the deterministic-plus-reproducible band is the review-ready subset. When we tell a customer “these findings reproduce,” we mean it in a specific, checkable way — not “our tool flagged it,” but “we replayed it under controlled conditions and it recurred.” That’s the difference between a number you report and a number you can defend.

Why this beats a single pass/fail

Most tools run each test once and give you pass or fail. That’s fine for a smoke test. It’s the wrong tool for a risk decision, because a single run can’t distinguish a deterministic hole from a stochastic hiccup — and both show up as “fail.” You end up either over-reacting to noise or under-reacting to a real, recurring failure, and you can’t tell which mistake you’re making.

Reproducibility tiers make that distinction the first thing you see about a finding, before you read a word of the transcript. A finding arrives already labeled: this one always fires, this one is a fluke. Your triage starts from confidence instead of from a shrug.

There’s a quieter benefit too. Because every reported finding has already been replayed, a customer doesn’t pay to re-run work that’s already been validated. The confidence tier travels with the finding into the report, the ticket, and the auditor’s packet.

Fisher replays every finding strict / guided / free and confidence-rates it before it reaches your report — so a “confirmed” finding means it reproduced, not that a tool flagged it once. See the tiers on your own agent with an 30-Day Agent Assurance Assessment from Molt AI.

Request an Assessment →

More from the blog