Composite study

This is a product-class write-up, not a named-client story and not a results press release. Counts below describe the pack we actually write (approach points, tools, layers) — not invented bug totals or conversion lifts.

4
Approach points
4
Tools in the pack
4
Layers covered
3
Challenges documented

Overview

The brief sounded helpful: strengths, gaps, suggested questions. One gap was “no leadership” for a candidate whose CV listed a team lead role the retriever missed. Another brief mixed companies from a different applicant.

Interviewers pasting the brief into personal Gmail was a DPA issue the product had not designed for (copy button with no watermark or warning).

Industry pattern this is grounded in

Hallucinated employment history is an adverse action waiting to happen. Isolation between requisitions is as important as summary quality.

Highlights

Typical launch bar: Block until pass rules hold on the money, identity, or safety path.

Challenges

01

PDF CVs parsed poorly; the model filled missing sections.

02

Calendar tools pulled attendee names from the wrong event.

03

Managers wanted “probing questions” that implied medical or family status — illegal in some jurisdictions.

How we tested

01

Ground every biographical claim in the application packet.

02

Canary fields per candidate to detect mixups.

03

Interviewer sees only assigned reqs.

04

Export and copy UX that does not pretend the brief is a system of record.

Starting point vs what we required

Starting point versus the controls we required
Starting pointWhat we required
PDF CVs parsed poorly; the model filled missing sections.Ground every biographical claim in the application packet.
Calendar tools pulled attendee names from the wrong event.Canary fields per candidate to detect mixups.
Managers wanted “probing questions” that implied medical or family status — illegal in some jurisdictions.Interviewer sees only assigned reqs.

What we delivered

01

RAG quality

  • Ragas — Faithfulness to the packet
02

Adversarial evals

  • Promptfoo — Disallowed interview questions
03

API / contract

  • Postman — Interviewer RBAC
04

Journeys / UI

  • Playwright — Brief, notes, no cross-req leak

Outcomes

Unsupported bio claims failed. Question suggestions were filtered against a disallowed-topic list. Mixup canaries failed the suite.

We added a “from application, not inferred” label and blocked auto-copy of full packets to mailto links.

Stack

Testing stack used on this product class
LayerToolWhat we validated
RAG qualityRagasFaithfulness to the packet
Adversarial evalsPromptfooDisallowed interview questions
API / contractPostmanInterviewer RBAC
Journeys / UIPlaywrightBrief, notes, no cross-req leak

Same method as the rest of our work: severity-ranked findings, pass rules in writing, and a ship / wait / block call. See the evaluation method and tool comparison.