Usage note
This outline, its slide-copy companion, and the workshop pack now form the accepted locked markdown baseline for the practitioner workshop package.
Use this note as the deck map unless a substantive audience or content gap appears.
Deck goal
Give technical practitioners a teachable, discussion-friendly workshop path for using AI as paired engineering in real delivery work.
This deck should help participants answer four questions:
- what AI enablement actually means in day-to-day delivery work
- when to use
learning modeversusdelivery mode - how verification changes by task and artifact
- what good paired-engineering habits look like by role
Recommended deck shape
- Keep the core deck to roughly
10-14content slides. - Keep exercise instructions separate from concept slides where possible.
- Prefer short task examples over abstract AI theory.
- Use the workshop pack as the facilitator layer, not the slide deck itself.
- Make the deck usable for mixed technical audiences without flattening role differences.
Presentation layers
- Outline deck: this note
- Slide-copy companion: Practitioner Workshop Deck Slide Copy - Paired Engineering with AI
- Facilitator and exercise layer: Workshop Pack - Paired Engineering with AI
Use this note as the deck map.
Use the slide-copy companion when the practitioner deck needs fuller on-slide language and presenter notes.
Narrative arc
- AI is already present in technical work, but raw access is not the same as good usage.
- The useful path is paired engineering, not blind delegation.
- The right way to use AI depends on the work, the person, and how easy the result is to verify.
- Good habits can be practiced directly through realistic scenarios.
Slide 1. Title
Headline:
Paired Engineering with AI
Subtitle:
A practical workshop for software delivery teams
Slide goal:
Set the tone for a hands-on session rather than a hype talk.
Slide 2. Why this workshop exists
Headline:
Tool access alone does not teach good AI usage.
Slide goal:
Explain why the session matters and why the team is not being asked to simply “use AI more.”
Speaker points:
- teams are already experimenting
- quality and learning can drift if no one defines good practice
- this workshop is about safer and more useful working habits
Slide 3. The middle path
Headline:
This is not a choice between avoiding AI and handing the work to the model.
Slide goal:
Anchor the workshop in paired engineering as the preferred stance.
Speaker points:
- paired engineering keeps people thinking
- the goal is better understanding, debugging, review, and flow
- fluent output is not the same thing as trustworthy output
Slide 4. The paired-engineering loop
Headline:
Question -> generate or compare -> verify -> revise -> learn
Slide goal:
Give practitioners one simple loop they can remember and reuse.
Speaker points:
- asking the model is only one step
- verification and revision are part of the work
- learning is an intended output, not a side effect
Slide 5. Learning mode versus delivery mode
Headline:
Not every task should use the same AI pattern.
Slide goal:
Show when slower, explanation-first use is better and when faster drafting is acceptable.
Speaker points:
- unfamiliar work should slow down
- bounded, familiar work can accelerate
- the wrong mode creates false confidence
Slide 6. What changes safe usage
Headline:
Good AI usage depends on more than job title.
Slide goal:
Introduce the four practical factors that change safe usage.
Speaker points:
- judgment and verification ability
- task familiarity
- task risk
- verification difficulty
Slide 7. Verification is not one-size-fits-all
Headline:
Code, tests, requirements, architecture, and incident reasoning do not verify the same way.
Slide goal:
Make verification concrete and role-aware.
Speaker points:
- some outputs can be tested quickly
- some outputs sound good but are hard to evaluate
- low-observability work needs stronger caution
Slide 8. Developer example
Headline:
AI can help most when the work is bounded and the feedback loop is real.
Slide goal:
Ground the model in developer work.
Speaker points:
- bounded debugging
- code explanation
- localized unit test drafting
- caution on architecture-heavy or unfamiliar changes
Slide 9. QA, SDET, architecture, and product examples
Headline:
Every role can use AI, but not in the same way.
Slide goal:
Show that adoption must be role-specific.
Speaker points:
- QA or SDET: failure triage and test idea generation
- architects: option comparison and question generation
- product: backlog clarification and ambiguity detection
- each role has its own verification traps
Slide 10. Common anti-patterns
Headline:
Most bad AI usage is easy to recognize once it has a name.
Slide goal:
Help the team spot weak habits early.
Speaker points:
- asking for the full answer before understanding the problem
- trusting fluency as proof
- using AI on hard-to-verify work without stronger review
- copying high-leverage habits without matching oversight ability
Slide 11. Exercise setup
Headline:
We learn good usage by practicing decisions, not just hearing advice.
Slide goal:
Transition into guided exercises.
Speaker points:
- decide mode first
- decide verification path next
- compare choices by role and task
Slide 12. Debrief and team commitments
Headline:
Good enablement changes habits in real work.
Slide goal:
Close with concrete commitments rather than generic encouragement.
Speaker points:
- one workflow to pilot
- one anti-pattern to avoid
- one verification habit to strengthen
Slide 13. Keep practicing after the workshop
Headline:
The worksheet packs are the easiest next step after this session.
Slide goal:
Turn the exercise layer into a concrete follow-up action.
Speaker points:
- start with the pack that matches your level
- use the size and complexity labels to pick a realistic scenario
- if you cannot complete one immediately, review one with a peer or lead
Slide 14. Where to go deeper
Headline:
The workshop is the start, not the full delivery model.
Slide goal:
Point participants to the supporting material.
Supporting notes:
- Workshop Pack - Paired Engineering with AI
- Exercise Worksheet Pack - Paired Engineering with AI
- Practitioner Playbook - Paired Engineering with AI
- Exercise Library - Paired Engineering with AI
- Verification Standards by Artifact and Work Type
- Capability Model - Oversight Readiness x Task Familiarity x Risk