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 Dzialets's talk. Use it for one team process whose current automations need coordination.
Name the team, outcome, workflow owner, and recurring task. Describe the common quality bar and existing variation between individual setups. Record reusable environment, instructions, required tools, internal context, and permissions. Identify which local limitation or collaboration problem the shared setup actually solves.
| Stage | Input and state | Output | Verification | Owner or next stage |
|---|
Keep each automation scoped. Identify comments, issue fields, or manual copying currently used to transfer state. Replace hidden dependencies in the design with explicit status and evidence references. Do not claim a stage succeeded simply because it produced text.
State the decisions that need human judgment, including incomplete initial intent and consequential exceptions. Do not require approval at every routine transfer. For a failed stage, specify the current workspace, expected behavior, available evidence, failed check, and resume path a person would receive.
Explain how local intervention retains the team's shared setup. Mark any product handoff capability that still needs verification.
Define actionable notifications and their owner. Separate failure, decision needed, progress, and completion. A shared inbox is a design proposal unless it already exists.
Record estimated cost with its assumptions and observed cost after the run. Set a justified run limit, review date, and condition for disabling a forgotten or unhelpful routine. Those controls are recommendations here, not numerical rules from the talk.
Choose one representative task and a short observation period. Measure accepted outcomes, failed handoffs, intervention burden, quality, and spending. Finish with evidence needed to expand, revise, or stop. Distinguish the team's measured results from the speaker's reported adoption and staffing examples.
.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