Back to workflows
Research & learningInvestigate and reportPersonal

Shopping shortlist research

Compare specifications, reviews, stock, and price against your real constraints.

What this workflow does

Compare specifications, reviews, stock, and price against your real constraints. It separates observed facts from inference, surfaces conflicting evidence, and delivers a review-ready finding set instead of an opaque answer.

What you gain

Less tab-hopping and fewer bad-fit purchases.

What the AI agent changes

How this worked before

Traditional automation could collect records, but a person still had to compare sources, resolve conflicts, and write the conclusion.

What the AI agent changes

The agent can plan a search, inspect multiple sources, distinguish facts from inference, and return a cited report.

Agent trigger

The user provides a purchase goal, budget, and non-negotiable constraints.

Inputs

  • Process context: product requirements, retailer pages, reviews, price, and availability
  • Approved policies, ownership, and exception rules

Agent flow

  1. 1

    Collect source material from the approved systems and record its timestamp.

  2. 2

    Cross-check conflicting signals and separate facts from inference.

  3. 3

    Prepare a cited shortlist with trade-offs and rejected options with citations, unknowns, and confidence.

  4. 4

    Deliver the approved report and preserve its evidence set.

Human decisions

After step 3

The accountable process owner approves a cited shortlist with trade-offs and rejected options.

Outcome

  • User-reviewed buying shortlist
  • Evidence, exceptions, and audit trail

Guardrails

  • Label inference separately from observed facts.
  • Do not close the investigation while required sources are unavailable.

Risks and mitigations

Missing or stale evidence can produce a confident but incomplete finding.

Show source coverage, conflicts, timestamps, and unanswered questions.

Sources and evidence