AI Prompt Engineering Companion

Beyond the Prompt

A deeper companion to Zach’s Guide to AI Prompt Engineering.

Better prompting is the starting point. Better AI workflows are the next step. This guide helps teams move from asking better questions to using AI tools more strategically, responsibly, and consistently at work.

Start here

Download Zach’s AI Prompt Engineering 101 guide.

This companion builds on Zach’s quick-start guide, which introduces the core habits of better prompting: defining the output, adding context, increasing clarity, and using feedback to improve results.

Use the guide for:

  • Prompting basics
  • Quick examples
  • Team-friendly reminders
  • A simple framework to share

Start with the 4 pillars.

Output, Context, Clarity, and Feedback are the foundation of stronger prompting. Click each card for a practical example.

Output

Be clear about what you want the AI to create.

Try: “Draft a one-page memo with a recommendation, rationale, risks, and next steps.”

Context

Give the AI the background it needs to respond well.

Try: “The audience is senior leaders at a 500-person healthcare organization.”

Clarity

Remove ambiguity. Say what to include, avoid, prioritize, and format.

Try: “Use plain language. Avoid jargon. Include three options ranked by ease of implementation.”

Feedback

Use the first answer as the beginning of the process.

Try: “Revise this for a more skeptical audience and identify assumptions I should verify.”

A strong prompt gives AI direction. A strong workflow gives it the right setup, context, and review.

Build a better prompt.

Use the 4 pillars to turn a vague request into a stronger starting prompt.

Want to make it stronger?

Copy this prompt into your AI tool, then paste in the starter prompt you built above.

Improve this starter prompt. Make it clearer, more specific, and easier for an AI tool to follow. Preserve my intent. Ask up to three clarifying questions if needed.

Move from a prompt mindset to a workflow mindset.

The best AI results rarely come from a single perfect prompt. They come from choosing the right tool, giving it useful context, setting clear instructions, and reviewing the output with human judgment.

“How do I ask this better?”

Prompting focuses on the immediate request: the wording, the task, the tone, the format, and the next revision.

“What setup will help us get a better result?”

Workflow thinking considers the tool, source materials, reusable instructions, privacy boundaries, review process, and how the output will be used.

Prompt

What are we asking?

Tool

Which AI tool fits the task?

Context

What information should ground the answer?

Instructions

What should stay consistent?

Review

How will humans check it?

Make AI more useful with personalization.

Personalization helps move AI chat from generic to useful by giving the tool recurring context about your role, preferences, audience, and work.

Custom instructions

Reusable preferences for how the tool should respond, such as tone, format, audience, or level of detail.

Saved memories

Facts the tool may remember across chats. Review them periodically and remove anything that is not useful.

Chat history

Past conversations that may influence future responses, depending on your tool and settings.

Try this prompt

Ask me five questions about my role, audience, recurring tasks, preferred formats, and communication style. Then draft a set of custom instructions I can review and edit.

Choose the right setup for the task.

Chat is useful for quick, one-off work. Projects, notebooks, and connected files become more useful when you need persistent context or repeated reference materials.

What are you trying to do?

Use chat

Chat is often the simplest option for quick ideas, drafts, summaries, and one-off questions.

Ground AI in trusted materials.

Retrieval-augmented generation, often called RAG, helps AI answer from a specific knowledge base or set of documents. It can make outputs more useful, but it does not remove the need for human review.

Question

The user asks something.

Search

The tool searches trusted materials.

Retrieve

Relevant context is pulled in.

Generate

The AI creates an answer.

Review

A human checks the result.

Grounding improves usefulness. It does not replace judgment.

Where teams can use projects and notebooks.

Projects and notebooks are especially helpful when teams need AI to reference the same approved documents, templates, policies, or examples across sessions.

HR

Store approved policy language, benefits information, and templates so outputs stay consistent across roles and requests.

Sales

Reference competitor briefs, customer profiles, and battle cards for pre-call prep and account planning.

Finance

Load budgets, prior reports, and variance notes so teams can ask better questions across periods.

Operations

Use SOPs, runbooks, workflow specs, and process documents as a persistent reference set.

IT

Reference runbooks, escalation guides, known issues, and service desk knowledge bases.

AI in Excel can help, but check everything.

AI can help generate formulas, clean data, produce visualizations, and run analysis. Clear instructions make the work easier to verify.

Tell the tool not to edit the original data.
Ask it to put analysis in a new worksheet.
Request formulas, not just raw numbers.
Convert data to an Excel Table with named columns.
Break complex actions into steps.
Double-check outputs before using or sharing them.

Use AI with judgment.

AI can accelerate thinking, drafting, analysis, and decision support. It can also create risks when outputs are accepted too quickly or used without review.

Errors or hallucinations
Bias
Misuse
Intellectual property
Confidential information
Wasted time
Reputational damage
AI can accelerate your thinking. It should not replace your judgment.

Is your team ready to use AI well?

Use this quick check to identify where your team may need clearer guidance, shared standards, or live training.

Check the boxes that are true for your team.

Want help turning this into a team workflow?

Northeastern’s AI education programs can be customized around your team’s tools, roles, policies, and real work.

A guide can introduce the concepts. A live course helps your team apply them.

Northeastern’s AI learning programs help teams build practical AI skills through instructor-led, hands-on learning shaped around your organization’s roles, tools, goals, and workflows.

Designed for real-world application.

Customized to your context.

Built to keep momentum going.