AI in Feith · Custom prompts

Custom AI prompts, run where your records live.

Prompt Runner takes a plain-English instruction and runs it across a whole record set, extracting metadata, classifying content, reading records against policy, and triaging what comes in. The model runs inside your security boundary, so the records never leave to be read.

Request a walkthrough All six capabilities ›

1 Prompt, thousands of recordsPlain English, no code; it behaves like a classifier you write yourself

0 Records copied outThe model runs inside your boundary; bring your own

Any Document layoutReads the whole record, whatever its layout

1 Taxonomy, normalized toEvery value lands in your fields: dates, currencies, names

What it does

One prompt. Thousands of records.

Your team writes plain-English instructions that behave like modular classifiers and extractors — no code, no model training, no rules to write. Each result is written straight back as record metadata.

Reads complete documents end to end, so it works on contracts, invoices, and forms whose layout varies.
Normalizes what it extracts: dates land in one format, currencies parse, names match your taxonomy.
Reads each record against your policy stated in plain English: the model does the interpretive reading, and deterministic rules make the calls that must be exact and repeatable.
Triages what comes in by urgency, topic, and target team, so the workflow can route it to the right queue, dashboard, or reviewer.
Works retroactively: surfaces metadata that was locked inside records captured years ago.

Prompt Runner runs on its own, on a schedule, or as one optional AI step inside a Workflow iQ workflow.

Worked example

One prompt

“Extract renewal date, ceiling value, FAR clauses, and party names from each contract.”

Prompt Runner runs in your boundary

Reads each record in full

Whole documents, any layout.

Structured output

renewal: 2026-09-30 ceiling: $4.2M FAR 52.217-9 party: ACME LLC

Written back as record metadata; renewal alerts fire automatically.

normalized to your taxonomy audit entry written

How it works

The model comes to where the records live.

Prompt Runner runs your prompt against records already in the vault, with a language model you've authorized running inside the same boundary. Nothing is exported to be read; the structured result is written straight back.

Records in your vault

Prompt Runner

Your prompt runs on each record

Your model, inside your boundary (bring your own)

Why it's different

Your model, your boundary

Bring your own LLM. Prompt Runner runs it inside the boundary your records already live in: Azure Government, AWS GovCloud, on premises, or an air-gapped enclave. Records are never sent to a public AI service.

Reads whole records

Layout doesn't matter: it reads the document itself, not a set of fixed field positions.

Auditable by design

Every run writes to the audit trail, and you can route low-confidence results to a person before anything is committed.

How you run it

One step, three ways to run it.

Prompt Runner is the AI step: run it by itself or drop it into a larger Workflow iQ process.

On demand

Point Prompt Runner at a record set, write a prompt, and run it once to backfill the metadata you wish you'd captured.

On arrival or on a schedule

Set a prompt to run on any object that lands in a file cabinet, or on a schedule. It is configured in Prompt Runner itself, so fresh records are enriched the moment they land with no workflow to build.

As one step in a workflow

Drop Prompt Runner in as the AI step inside a Workflow iQ workflow. It reads, classifies, or extracts, then hands the result to the next step.

See Workflow iQ ›

In practice

Metadata extraction, use case by use case.

The same engine, pointed at a different record set with a different prompt. A few of the jobs agencies run it on:

Invoice processing

Invoice number, date, total due, payment status

Payables match and reconcile without manual keying.

Service-desk triage

Issue type, urgency, location

Tickets route to the right queue; SLA compliance climbs.

Safety incident reports

Risk indicators, personnel involved, measures taken

Speeds compliance reporting and root-cause analysis.

Historical archives

Meaning read from handwritten field notes

Researchers get searchable access far sooner.

Asset capture

Serial numbers read from equipment photos

The asset database updates in near real time.

NARA attributes at capture

Creator, creation date, identifier, record schedule

Zero-click NARA compliance the moment a record lands.

Explore the rest of AI in Feith

Five more capabilities, each its own deep-dive.

These are the other capabilities in the AI in Feith family — separate tools that each share the same permission model, the same audit trail, and your choice of large language model.

Back to AI in Feith ›

Get started

Turn the metadata you wish you had into metadata you have.

Bring a record set and a plain-English prompt. We'll run Prompt Runner across it live and show the normalized fields written back to your records, inside your boundary.