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 worksheet is a recommended application of Zuber's talk, not a mandate to code.
State the company, product or operating decision at stake. Explain why direct participation could reveal evidence that current reports do not provide.
Name the alternative use of the leader's time and why this experiment is worthwhile now. Record the peers or team members whose context should inform that choice.
Choose one real task and include its review, verification and delivery path. Define a bounded time or effort allocation appropriate to the organization.
Clarify who owns the work, how existing commitments are protected and whether the result is a learning prototype or a maintained deliverable.
| Observation | Evidence | Implication | Alternative explanation |
|---|---|---|---|
| Actual friction or result | Trace, task outcome or discussion | Decision it may affect | What remains uncertain |
Track waits and rework as well as generated output. Treat token spend and PR count as prompts for investigation rather than performance rankings.
Ask what people believe they are measured on, where experimentation time comes from and which support would reduce friction. Include both hesitant users and enthusiastic people constrained by current assignments.
Draft one concrete question and state how feedback will be acted on. Avoid equating a different preference with resistance.
Choose one change, its accountable owner and the evidence that would validate it. Separate a prototype's success from customer delivery or broad adoption.
Record what the leader learned, what remains unknown and when the experiment ends or is revisited. If the result is not worth maintaining, state that explicitly without transferring surprise ownership to the team.
Finish with a decision-ready recommendation, not a claim that hands-on activity alone is strategic impact.
.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