Course overview
Lesson 8 of 9 · 3 promptsAI for Salesforce Administrators
LESSON 08 OF 9

Documenting And Testing Changes

3 prompts for Salesforce Administrators

Prompts for Salesforce Administrators: copy one, fill it in, paste it into your AI.

Track progress as a member

In this lesson

  1. 01Write a Solution Design SummaryUse this when you have built a non-trivial Salesforce change and need a short design summary for reviewers, release notes, or future maintainers.
  2. 02Build A Test Plan For A ChangeUse this when a Salesforce change is heading to production and you need test cases that prove it works and did not break anything nearby.
  3. 03Draft A Sandbox To Production Deployment ChecklistUse this when you're moving Salesforce metadata from a sandbox to production and want the sequence, dependencies, and rollback documented before you start.
1Copy the promptClick Copy on the prompt you need.
2Paste it into your AIChatGPT, Claude, Gemini or Copilot.
3Fill in the {{brackets}}Your own details, or let the AI ask you.
4Follow up and checkUse the follow-ups, then check the facts.
01

Write a Solution Design Summary

Use this when you have built a non-trivial Salesforce change and need a short design summary for reviewers, release notes, or future maintainers.

Prompt

Role You are a Salesforce administrator who writes short solution design summaries. You optimise for a document a reviewer or future admin can read in minutes and trust.

Context you provide

  • {{change_name}}: name of the build
  • {{business_problem}}: what was broken, slow, or manual
  • {{audience}}: release board, team, or auditor
  • {{objects_and_fields}}: objects, fields, and record types touched
  • {{automation_built}}: flows, validation rules, approvals, Apex
  • {{user_personas}}: profiles, permission sets, roles affected
  • {{constraints}}: sharing, licence, integration, or limit constraints
  • {{testing_done}}: sandboxes used and acceptance results
  • {{deployment_path}}: change set, package, or pipeline
  • {{open_questions}}: known gaps and follow-ups
  • {{target_length}}: word count you want

Instructions

  1. Ask for any missing inputs, then write the summary. Do not start without {{change_name}}, {{business_problem}}, and {{testing_done}}.
  2. Open with two sentences: what the change does and the business outcome it serves.
  3. Describe the design in the order a user experiences it: objects, automation, data flow.
  4. Explain why this approach beat the obvious alternative, using only the constraints supplied.
  5. Summarise the testing done and name what was not tested.
  6. State the deployment path and the post-deployment checks.
  7. Close with risks, assumptions, and open questions as short bullets.

Output format Markdown with headings: Purpose, What Changed, Design Decisions, Testing, Deployment, Risks and Open Questions. Short paragraphs and bullets. Stay within {{target_length}} words. Plain business language, Salesforce terms only where they add precision. No code dumps, no screenshot descriptions, no marketing language.

Guardrails

  • Use only the names and results supplied. Never invent metadata names, limits, API versions, or test outcomes.
  • Flag every assumption and mark unverified items as "to confirm".
  • Tell the user to check Salesforce release notes, sandbox behaviour, and internal change management approval before circulating this.

Example change_name "Renewal reminder flow", business_problem "CSMs miss renewal dates", audience "release board", testing_done "UAT in full sandbox with 12 CSMs".

Open as its own page

02

Build A Test Plan For A Change

Use this when a Salesforce change is heading to production and you need test cases that prove it works and did not break anything nearby.

Prompt

Role You are a Salesforce release test planner working with a Salesforce administrator. Optimise for a test plan that proves the change works and that nothing nearby broke.

Context you provide

  • {{change_summary}}: what is changing and the business reason
  • {{target_orgs}}: the sandbox used for testing and the production org
  • {{objects_and_fields}}: objects, fields, record types and layouts touched
  • {{automation_touched}}: flows, validation rules, approval processes, triggers
  • {{user_personas}}: profiles and permission sets that use the change
  • {{integrations_and_jobs}}: connected apps, external systems, scheduled jobs affected
  • {{rollback_plan}}: how the change is reverted if release fails

Instructions

  1. Ask for any missing inputs, then wait for the answers before writing the plan.
  2. Summarise scope in one paragraph and list what is out of scope.
  3. List test cases in a table: ID, type, persona, steps, expected result, plus blank actual result and status columns.
  4. Cover each persona with a positive case, and add a regression case for every object, automation item, and integration the change could touch.
  5. Add negative cases that confirm validation rules and error messages still behave.
  6. Define entry and exit criteria, name the sign-off owner, and end with a pre-deployment checklist tied to the rollback plan.

Output format Markdown with headings: Scope, Out of scope, Environments, Test cases, Entry and exit criteria, Sign-off, Pre-deployment checklist. Keep it under two pages, use short imperative steps and checklist language. Leave out code, data scripts, and marketing text.

Guardrails

  • Do not invent Salesforce limits, object names, API names, or metadata. Leave a placeholder when an input is missing.
  • Mark each assumption and note any test that needs a sandbox refresh or seeded data.
  • Tell the user to have a second admin or the business owner review cases touching permissions, integrations, or regulated data.

Example Change: new Opportunity discount approval flow; target orgs: UAT sandbox, production; personas: Sales Rep, Sales Manager.

Open as its own page

03

Draft A Sandbox To Production Deployment Checklist

Use this when you're moving Salesforce metadata from a sandbox to production and want the sequence, dependencies, and rollback documented before you start.

Prompt

Role You are a Salesforce release coordinator drafting deployment checklists for administrators moving metadata from sandbox to production. Optimise for a sequence a colleague can follow and reverse.

Context you provide

  • {{source_org}} — sandbox type and name
  • {{target_org}} — production org
  • {{change_inventory}} — components deploying, with API names where known
  • {{deployment_method}} — change set, CLI, DevOps Center, or package
  • {{known_dependencies}} — what must deploy before what
  • {{test_evidence}} — what was tested in sandbox and the result
  • {{deployment_window}} — date, time, expected user impact
  • {{rollback_options}} — what can be reverted and what cannot
  • {{approvers}} — pre and post sign-off

Instructions

  1. Ask for any missing inputs, then wait before drafting.
  2. Group the inventory into batches ordered so dependencies resolve first.
  3. Write pre-deployment steps: back up or retrieve current metadata, notify users, freeze conflicting edits.
  4. List the deployment sequence, one component or batch per step, with the expected result of each.
  5. Add validation checks to run in production after each batch and who confirms them.
  6. Add post-deployment steps: permission checks, user communication, first-day monitoring.
  7. Add rollback triggers and exact reversal steps, flagging anything that cannot be undone.

Output format Markdown with five bold headings: Pre-Deployment, Sequence, Validation, Post-Deployment, Rollback. Sequence as a table: Step, Component, Owner, Expected Result. Under 700 words. Plain operational language, no code samples.

Guardrails

  • Do not invent API names, test results, org limits, or release dates. Mark gaps as TODO.
  • Flag any step that deletes or overwrites data and note it needs business owner sign-off.
  • Tell the user to check the steps against current Salesforce Help documentation and their change management policy before running them in production.

Example Source: UAT full sandbox; target: production; changes: 3 flows, 2 validation rules, 1 permission set; method: change set; window: Saturday 02:00 to 05:00.

Open as its own page

Skills for these tasks

Give your AI these skills and it does these tasks the expert way. Connect your AI once and it picks them up by itself.