The
BottleneckMoved.
Platform Engineering
When AI Writes the Code
Guilherme Silva · synvert xgeeks
KCD Porto × DevOpsDays
Writing code by hand
is over.
73%
of developers who use AI coding tools use them daily.
Only 6.6% trust it for important work decisions.
Stack Overflow Developer Survey 2026 · 30,000+ responses
Guilherme
(Gui).
Engineering Manager at synvert xgeeks
Platform, cloud, infrastructure… and now AI, like everyone else.
Interested in AI & robotics
self-rightingSO-101 armsvacuum teardown
What I saw first-hand.
- 01PRs started piling up.
- 02Reviews got slower and shallower.
- 03More bugs reached production.
The volume is real.
+75%
PRs per developer, in one year.
40%+
of pull requests on GitHub start with an agent’s first draft.
DX TrueThroughput, 500+ engineering organizations, Q4 2025 → Q3 2026 · GitHub Octoverse, Oct 2026 · vendor data
The bottleneck moved.
More changes. Same human bandwidth.
“AI increased the capacity to produce change. The next constraint became our ability to verify it.” · Spotify, Sep 2026
AI is load-testing
your SDLC.
More changes get through. More of them break.
DORA ROI report, Apr 2026: AI volume is “overwhelming existing deployment pipelines and manual review gates”
Make developers faster.
Make fast developers safe.
Trust more AI code, with less human review.
“The platform team, which was created specifically to remove bottlenecks, has become one.”
Koray Oksay, CNCF blog, “Guardrails, not gates”, Oct 2026
Enforce what machines can check.
Reserve judgment for intent and risk.
Machines check
- types · lint
- tests
- runtime evidence
Humans decide
- intent
- acceptable risk
- final decisions
Fix the environment, not the agent.
“every mistake and bad pattern you observe from agents, needs to turn into a constraint”
Lauren Tan · engineer at SpaceXAI (xAI) · Oct 2026
01Every failure→a check
02Checks that keep holding→earned trust
03Earned trust→fewer changes need a human
1 contain2 context3 feedback4 review5 release
The verification loop.
1 contain2 context3 feedback4 review5 release
What can the agent reach?
Contain the blast radius.
Built for humansagents run as you, in shared staging
→Built for agentsa fresh box per task; its only way out is a PR
First stepRun each agent task in a fresh sandbox, with no production credentials.
1 contain2 context3 feedback4 review5 release
What does it know?
Context is a platform product.
Built for humanswikis for new hires
→Built for agentscontext shipped with every repo
First stepGive every repo a short AGENTS.md and the tools each task needs.
1 contain2 context3 feedback4 review5 release
How does it learn it's wrong?
Errors written for the agent.
Built for humansCI logs a person reads later
→Built for agentsfix instructions, and a cap on runs
First stepRewrite your five most common CI errors as fix instructions. Cap agent runs at two.
1 contain2 context3 feedback4 review5 release
Who checks it?
Review routed by risk.
Built for humansevery change waits for a person
→Built for agentsrisk decides who reviews
First stepWrite down which changes may take the fast path: small, bounded, with evidence.
1 contain2 context3 feedback4 review5 release
Does it work in production?
Production is the last check.
Built for humansdeploy and hope
→Built for agentssmall rollout, automatic rollback
First stepRelease behind a canary that rolls back on its own.
The bottleneck will move again.
Keep measuring where work waits.
Faster and safer.
CompanyWhat they changedResult
SpotifyStronger review, testing, rollout and rollback8.1k → 17k merged changesno rise in reworkAug 2025 → Aug 2026
CloudflareAI review sorted into three risk tiersfirst review: hours → 4 minrisky changes: 7 review agents, trivial: 248k merge requests, 30 days
AtlassianAI review on every pull requestfirst review: 18 h → 0PR cycle time −45%Jan 2026
MetaTests generated for risky changes before they landserious privacy incidents −20%H1 2026
AnthropicClaude Code teamReview tiered by risk, AI review rounds capped, gradual release2× merged PRs−40% revertsJun → Sep 2026
Company engineering blogs, Jan to Oct 2026
When code becomes cheap,
trust becomes expensive.
Your platform is how
you scale trust.
Thank you · Obrigado
Guilherme Silva · KCD Porto × DevOpsDays