CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

ainativedev/aidevcon-2026-nyc

AI Native DevCon 2026 New York — practical agent skills grounded in conference talks

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

application-template.mdskills/talk-ocytko-scaling-agentic-engineering/references/

Platform and enablement pilot

This is Tessl's recommended application of Ocytko's talk. Choose one user problem and one bounded cohort. Do not copy every tool in Zalando's reported architecture.

User problem and shared capability

Name the users, their actual task, and the friction preventing completion. Record whether the gap is model access, environment configuration, identity, cost visibility, migration effort, or learning time. Describe the smallest shared capability that would help.

Map user, harness, proxy, model, tools, and identity. Separate central metadata from optional local diagnostic captures. State what is recorded, who may inspect it, and how missing harness identification affects conclusions.

Operating controls

Record supported configurations, upgrade responsibility, compatibility checks, caching behavior, credential expiry, and the response when access fails. Use actual observed thresholds; the talk's operational settings are not universal defaults.

For spending, define visibility, warning, cap, exception path, and owner. Pair a warning with an actionable way to improve efficiency. Compare quality and delivery outcomes alongside spending.

Team workflow

If the pilot is a migration, identify the initiating team, representative repository cases, transformation method, generated evidence, and receiving-team acceptance. If it is a hosted agent, identify owner, permissions, caller scope, user consent, memory scope, and sharing scope.

Keep risk scoring separate from correctness. Record the incident evidence behind each signal and the release decisions it informs.

Learning and readiness

Choose a real backlog task and a paired exercise. Define protected learning time, manager ownership, and feedback needed before promoting a lab into repeatable training. Check the repository's observability and rollout capabilities for the intended autonomy level.

Finish with current status, planned extensions, success evidence, failure signal, and next decision. Counts of created agents or generated PRs are activity measures; name the accepted outcome that would justify expanding the pilot.

skills

talk-ocytko-scaling-agentic-engineering

tile.json