Next
Generation
Development
Teams
the way engineering
teams work.
Review · Test · Debug · Monitor
VP of AI
at Elementor
Eight Parts
Let's Get To Know
How You Work
Scan it on your phone.
It takes about a minute.
Humans No Longer
Write Or Review Code.
That is the destination everyone keeps describing.
Nobody is there yet. This talk is about the road — and about who stays accountable while we walk it.
The
Shift
AI Can Write Code. So What?
Coding faster is useful. But if that is the only thing that changed…
Run Dry
Queue
Surface
Train
…you didn't remove the constraint. You moved it somewhere with no AI pointed at it yet.
What If We Built
The Team Today?
If you were building your engineering team from scratch today, knowing what AI can do — would you design it the same way?
From Assistance
To Delegation
Nobody Opens A Chat
Improve The Loop
trigger
definition
verification
outcome
A better prompt helps you once. A better loop helps the team every day this week.
It Is: Build A More
Capable Engineering Team
AI Is A
Team Sport
Five Engineers.
Five Private Setups.
We optimized the individual, not the team.
Individual Discoveries Become
Team Capabilities
Compound Your Team's Learning
This field changes every week. No individual can keep up with it — a team can.
Slot
Review
Channel
Scan
One engineer discovers. The whole team levels up.
Context Is
Infrastructure
The Model Is Only
One Part Of The System
A better model helps. It is not the entire system.
Stop Teaching AI
From Scratch
Build A Team
AI Repository
The exact structure isn't important. The principle is.
Treat AI Capabilities
Like Code
Skills Are
Reusable Knowledge
— explained again, by hand, every time
Owned by the team.
Now it belongs to the team, not to one person's chat history.
This Is The Whole Thing
--- name: investigate-incident description: Use when an alert fires or a customer reports a production bug. --- 1. Pull the alert window from the dashboard. 2. git log --since on the owning service. 3. Correlate deploys with the error-rate change. 4. Reproduce against the staging snapshot. 5. Write findings before proposing a fix. Never restart the service before capturing logs.
Writing Them Well Is A Skill Itself
Review the pull request carefully and give good feedback. Be thorough and check for bugs.
Use when: a PR touches src/api or src/auth. Read the diff, then the tests, then the callers of every changed function. Block on: missing authz, unparameterised SQL, public API change with no migration. Ignore formatting — the linter owns it. Output: file · line · severity · fix
Commit The Why, Not Just The What
# Checkout v2 — Decisions ## 2026-03-04 · Idempotency keys over DB locks Chose client-supplied idempotency keys. Rejected row-level locks: deadlocks under retry storms. Owner: @payments ## 2026-03-11 · No new payment provider Deferred until Q3 volume numbers land. Owner: @dennis <!-- committed in the same PR as the feature -->
Meet Your
New Team
What Is An Agent?
Not magic. Not just a long prompt.
It can inspect the environment, take actions, observe results and iterate.
Your Digital
Engineering Team
Engineer
The Developer Agent
Give it a goal and an environment it can work in.
The Reviewer Agent
A reviewer that already knows:
Ask The System.
Especially powerful for onboarding and legacy systems.
An Agent Is A File
--- name: reviewer tools: [read, grep, run_tests] context: [architecture.md, conventions.md] --- Block the merge on: - missing authorization on a new route - SQL built from unvalidated request input - public API change with no migration note Never comment on formatting. The linter owns that. Output: file · line · severity · suggested fix
One Reviewer Becomes Four
& Style
That is a line in a config file, not a vendor's pricing tier.
And It Runs In Your CI
name: agent-review on: pull_request jobs: review: strategy: matrix: agent: [syntax, architecture, security, perf] steps: - uses: actions/checkout@v4 - run: | cursor-agent -p "$(cat .agents/reviewer-${{ matrix.agent }}.md)" \ --output-format json > out-${{ matrix.agent }}.json - run: ./scripts/post-findings.sh out-${{ matrix.agent }}.json
Rebuild The
Lifecycle
The Software
Development Lifecycle
Let's Redesign It.
Refinement
The human reviews the result instead of assembling it.
Plan Before You Code
A wrong plan is cheap to fix. A wrong implementation is not.
Implementation
Code Review
Stop Imagining What Changed
A reviewer who can see the change approves it in a minute, not a day.
Give The Agent
Responsibility
The Lifecycle Doesn't
End At Merge
AI becomes part of operations, not just coding.
Autonomy
Without Chaos
Just let the
agent do it
More Autonomy
Requires More
Verification
Not more trust.
Every layer you add is a place the system can catch itself being wrong before a human has to.
The Approver That Doesn't Approve
0 false approvals
mode: advisory # observe → advisory → enforce post_check: true blocks_merge: false # ← the flag that matters record_verdict: true promote_when: agreement_with_human: "> 0.95 over 200 PRs" false_approvals: 0
Earn the merge button with data, not with optimism.
Who Reviews The Reviewer?
The Next
Generation Team
The Old
Development Team
Everything waits for someone's attention.
The Next Generation
Development Team
The human owns
Intent · Architecture
Decisions · Judgment
Accountability
Agents handle
Research · Implementation
Validation
Repetitive work
Your Model Is Not
Your Strategy
You do not need access to every frontier model to build a genuinely capable engineering system.
Don't make it about which model wins. Make it about engineering the system around the model.
Start
Tomorrow
Don't Build
20 Agents
Start with one repeated workflow.
Something your team already does every week.