Skip to content
Cookbook

Clear security questionnaires without guessing

Draft every answer from an approved library with citations, then verify each one before it ships.

Customer Engineeringadvanced

What this does

  • Parses every question from the incoming file into a row-by-row list
  • Drafts each answer from the approved library, citing its source
  • Runs a second-pass sub-agent that tries to refute every drafted answer
  • Grows the answer library and flags open rows for sign-off

Workflow

  1. Trigger

    New questionnaire lands

    Dropped in the drive folder or attached to a Salesforce opportunity.

  2. Shell

    Parse the file

    Extract every question from the XLSX/CSV/PDF into a row-by-row list.

  3. Prompt

    Draft from the library

    Match each question to the approved-answer library, cite the source.

  4. Prompt

    Second-pass review

    A sub-agent checks every drafted answer against the library and policy docs.

  5. Result

    Deliver for sign-off

    Completed file plus a flagged-answers summary posted to Slack.

Recommended skills

Reusable skills the recipe pulls in, add them once, every agent can use them.

Answer library maintenanceGrow and version the approved-answer library from every completed questionnaire
Evidence citationEvery answer cites the policy doc, control, or prior answer it came from
Adversarial reviewSecond-pass check that tries to refute each drafted answer before it ships

How to use this recipe

  1. 1Connect Drive, the answer library sheet, Salesforce, and Slack to the agent
  2. 2Set the trigger, a new file in the drive folder or an opportunity attachment
  3. 3Paste the prompt and adjust which categories always need human review
  4. 4It answers its first-run questions once and remembers; you review flagged and open rows
Copy the prompt
Install the "Clear security questionnaires without guessing" recipe from the Eluu cookbook.
1. Fetch https://eluu.ai/cookbook/security-questionnaire/skill.md and save it into your skills folder as "security-questionnaire".
2. Ask me its first-run questions and store my answers in memory.
3. Offer to schedule the recurring jobs listed in the skill; only create the ones I approve.
4. Then run the skill once end to end so we can review the output together.
eluu.ai/cookbook/security-questionnaire.md

Paste it into any agent. It fetches the recipe file and pulls in the skills and prompts on its own, the prompt stays short, the detail lives at the URL.

The best human teams have agentic teams.

Your AI team is ready, are you?