Skip to content
Docs
foxborne.comRequest a pilot

AI models

Where Foxborne uses AI models, where they run and what checks each proposal before anything changes. None of them writes evidence or a finding.

ExplanationMarkdown
On this page5

Foxborne uses AI models in six places. Each is a job that a fixed rule or a hand-written parser cannot do well: reading a log format nobody wrote a parser for, finding the events that mark one moment on two clocks, checking what an engineer wrote against the records, turning an investigation into a rule, explaining a raw record, and searching by meaning.

The models never write evidence, a finding or an evidence level, and they make no before or after claim. Order still comes from the clock bounds, and conclusions still come from the engineer. A model proposes, deterministic code checks the proposal, and a person accepts it or not.

Where they are used#

FeatureWhat the model doesWhat checks itWho accepts it
Parsers for new log formatsReads the first lines of an unfamiliar text log and proposes the time column, its clock, and which columns say what happened and which are measurementsThe parser runs over every line before anyone saves it: records read, times that go backwards, empty measurementsAn admin saves the parser
Matching events to align a clockFinds events on an unaligned clock that have a counterpart on an aligned oneThe delay between the two is learned from aligned runs. The offset and its bound are arithmetic, and a pair seen on too few aligned runs cannot be usedThe investigator applies the alignment
Checking a finding against the recordsLists what the finding claims: times, time differences, values, parameters and words that state a causeEach claim is matched to the records: a time to an event, a difference to two records and their combined clock bound, a parameter to the run's parameter setNobody. It marks the text and never changes it
Rules suggested from investigationsReads the findings of incidents for two rules that fire in order on one vehicleThe time between the two on the incident is measured, and the runs where both fired in 90 days are countedAn admin creates the rule
Reading a raw recordExplains the fields of a flight log message, journal entry, receive record or process sample, and says what the record does not showValues are converted by code, such as KiB to MiB. The record stays on screen above the readingNobody. It is a reading aid
Search by meaningFinds evidence that says the same thing in other words, such as USB disconnects and telemetry gaps for "radio"Every result is an event with its ID, and opening it opens the recordNobody

Where they run#

The models run on an inference node inside your deployment, next to the workers. In the example deployment that is one g4dn.2xlarge node with one GPU in AWS GovCloud (US-West). Hosting shows it inside the data boundary as Inference node, and lists it under Nodes as Inference (AI models).

  • Nothing goes to a model provider. Outbound connections lists AI model providers as None: "Nothing. The models run on the inference node in your account. No record, prompt or result leaves it."
  • The models ship in the signed release bundle, like the parsers, and air-gapped installs receive them the same way. Settings shows Foxborne models 1.0, in the signed 1.4.2 bundle with the SHA-256 of the weights. See Upgrades.
  • They read only what the person using them can open. Export-controlled evidence stays behind the US person check, as Export control describes.
  • Nothing is used to train a model.

Foxborne works without them. A deployment with no inference node, or with the models turned off, hides the six features and changes nothing else: parsing, alignment, rules, reports and exports run as before.

Turn them off#

Admins manage the models in Settings, under AI models:

Use AI models
A switch. Off hides every feature below it. "Evidence, rules and reports are unaffected."
Where they run
The inference node and your account.
Models
The model release and the bundle it came in, with the SHA-256 of the weights.
What they can read
"Only what the person using them can open. Export-controlled evidence stays behind the US person check."
What they never do
"Change evidence, write a finding, or run a rule nobody created. Nothing is used to train a model."
Features
The six features. Edit turns each on or off for everyone.

Each change is recorded in the audit log as Changed AI settings, such as Models off or Reading a raw record off.

In the audit log#

Every accepted proposal is in the audit log with the person who accepted it:

ActionDetail
Saved parserThe columns, the clock and the file it was proposed from
Created ruleVersion 1.0, with from a suggestion on and the incident
Dismissed a rule suggestionThe suggestion and the incident it came from
Aligned clock by handThe offset and bound, ending from a suggested pair
Changed AI settingsWhat was turned on or off

A finding check and a record explanation change nothing, so they add no entry of their own. Viewing evidence is recorded as Viewed evidence, as always.

Next#