Back to workflows
Personal productivityEnrich and routePersonal

Photo and document archive

Read dates, places, people, and document types, then propose a searchable filing structure.

What this workflow does

Read dates, places, people, and document types, then propose a searchable filing structure. It resolves identity, enriches the case with approved evidence, and shows why the proposed route is appropriate before anything is assigned.

What you gain

Files become findable without hours of manual renaming.

What the AI agent changes

How this worked before

Rule-based routing handled only clean, predefined fields and broke when the request was incomplete or written in natural language.

What the AI agent changes

The agent can interpret unstructured context, gather missing evidence, explain its recommendation, and pause when confidence is low.

Agent trigger

A new batch of photos or scanned documents enters the inbox folder.

Inputs

  • Process context: images, document text, timestamps, existing folders, and naming rules
  • Approved policies, ownership, and exception rules

Agent flow

  1. 1

    Resolve the case identity and validate source freshness.

  2. 2

    Enrich the case with approved context and show every scoring signal.

  3. 3

    Prepare search tags, names, and destination folders with confidence and exceptions.

  4. 4

    Create the approved assignment and notify its owner.

Human decisions

After step 3

The accountable process owner approves search tags, names, and destination folders.

Outcome

  • Approved searchable archive structure
  • Evidence, exceptions, and audit trail

Guardrails

  • Do not route low-confidence identity matches automatically.
  • Use an allowlist of destinations and writable fields.

Risks and mitigations

A wrong identity match can send a case to the wrong owner.

Require deterministic identifiers and expose the routing rationale.

Sources and evidence