Ahmad Salama Back
AI Systems Prompt Engineering Multi‑Model Workflows

I build AI‑powered systems that feel reliable, useful, and production‑ready.

Not “chatbots for vibes”. I design prompts, model routing, guardrails, and evaluation loops so the output stays clean—even when the input is messy.

See proof
Focus
Prompt structure, reliability, UX
Strength
Turning ideas → usable products
Output
Fast iteration + measurable improvements

What I do

AI, but with structure. I treat prompts like product requirements.

🧭

Model selection & routing

Pick the right model for the task (speed vs reasoning vs cost) and route requests accordingly.

  • multi‑model strategy
  • fallback behavior
  • cost control
🧪

Prompt engineering

Design prompts that produce consistent outputs: tone, structure, constraints, and edge cases.

  • system + developer prompts
  • format enforcement
  • iterative refinement
🛡️

Guardrails & reliability

Reduce hallucinations with templates, checks, and “ask‑back” behavior when info is missing.

  • input validation
  • refusal boundaries
  • safe outputs

Proof (what I built)

Short, punchy, and real. Swap these bullets with your exact examples anytime.

EMUHELPER

Student Q&A assistant

Designed prompt flows that answer EMU student questions with clear, structured responses and “ask‑back” when needed.

prompt templatesintent routingtone control
Portfolio AI

Content + UX workflows

Used different models for drafting, rewriting, and polishing content—with consistency checks to keep outputs clean and on-brand.

multi‑model workflowstyle constraintsiteration loops
Automation

Reusable prompt systems

Built prompt “modules” (requirements → output format → quality checks) reusable across projects.

structured outputsrubricsquick QA
Open Prompt Lab Ask a question

How I work

A simple workflow that keeps AI outputs consistent.

01

Define the output

What should the answer look like? Format, tone, length, and constraints.

02

Pick the model strategy

Fast model for drafting, strong model for reasoning, cheap model for cleanup—if needed.

03

Build guardrails

Templates, refusal rules, ask‑back questions, and “don’t guess” behavior.

04

Evaluate + iterate

Test with edge cases, improve prompts, and measure output quality.

Prompt Lab

Copy a clean prompt pattern. Use it in your projects. Make it yours.

Reusable Prompt Template
[ROLE]
You are a helpful AI assistant focused on accuracy and clarity.

[GOAL]
Answer the user's question with a clear structure and actionable steps.

[CONSTRAINTS]
- If info is missing, ask 1–2 clarifying questions.
- Do not invent facts.
- Keep the answer concise and practical.

[OUTPUT FORMAT]
1) Summary
2) Steps
3) Common pitfalls
4) Next action
Tip: change OUTPUT FORMAT to match your product UI.

Mini checklist

  • Do I want JSON / bullets / sections?
  • What tone? (formal / friendly / futuristic)
  • What should the AI never do?
  • What’s the success metric?

Intro line (for your portfolio)

I design AI workflows that turn messy inputs into clean, reliable outputs.

Use this with me

Want this for your project?

Send me your use case and I’ll suggest the best prompt + model setup.

Best for
websites, student bots, automation, content systems
Deliverables
prompt pack • model routing • evaluation checklist
Open main portfolio