AI Native DevCon 2026 New York — practical agent skills grounded in conference talks
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
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.
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.
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.
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.
.tessl-plugin
skills
talk-arcolano-autonomy-and-trust
talk-aroussi-decision-context
talk-bevin-agent-assisted-instrument-design
talk-boeckeler-context-lifecycles
talk-braun-context-graphs
talk-carmont-evolving-agent-harnesses
talk-chanezon-gordon-agent-experience-evaluation
talk-cox-secure-agentic-workflows
talk-cunniffe-reusable-agent-platform
talk-davis-agent-tool-policies
talk-debois-concurrent-delivery
talk-dzialets-team-automation
talk-fahmy-harness-api-design
talk-finster-continuous-delivery
talk-fowler-regenerative-software
talk-gavrilescu-factory-architecture
talk-graciolli-amin-verification-aware-programming
talk-gruenbaum-reverse-graph-engineering
talk-hassan-agentic-engineering
talk-hossain-enterprise-agent-adoption
talk-huntley-patch-ready-factories
talk-jain-verifying-intent
talk-katsioloudes-montei-agentic-lifecycle
talk-knox-harness-engineering
talk-kovac-deterministic-memory
talk-lee-perkins-code-readiness
talk-lorenc-machine-speed-security
talk-lubken-software-of-one
talk-meijer-software-specialization
talk-meppiel-versioned-agent-contracts
talk-moss-concurrent-agent-risk
talk-myers-understanding-agent-generated-code
talk-ocytko-scaling-agentic-engineering
talk-oza-automating-design-quality
talk-panzica-agentic-sdlc
talk-pari-patel-agent-awareness
talk-podjarny-trustworthy-software-factories
talk-poulter-factory-improvement
talk-pratik-patel-refined-rag-data
talk-re-ferre-development-platforms
talk-sadogursky-factory-of-factories
talk-shah-training-agent-skills
talk-sharma-mohapatra-evolving-intent
talk-singhal-operating-agents-at-scale
talk-stack-incident-dossiers
talk-tyler-team-coding-benchmarks
talk-wotherspoon-agent-execution-environments
talk-yegge-ai-powered-factories
talk-zuber-leadership-through-coding