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
Adapt this record to one recurring task. It operationalizes Hassan's principles without claiming that the speaker supplied this exact schema.
Task and intended outcome: Current model and workflow: Known failure: Evidence and reproducible example: Temporary workaround: Durable domain requirement: Retest trigger and owner:
Use actual task evidence. Keep a proposed benchmark separate from a result. Record changes to inputs or tools that could make comparisons misleading.
| Step | Input and output | AI may execute | AI may decide | Verification | Escalation authority |
|---|---|---|---|---|---|
Identify where a person contributes judgment and where they merely transport information. Describe how each check is enforced and what a failed check does. Do not add approvals that serve no concrete decision.
Observed failure: Human correction: Likely cause: Reusable guidance or tool change: Scope of that change: Regression example: How the next attempt receives the correction: Evidence of reduced recurrence:
A manual repair is not yet a durable improvement. Mark the improvement unverified until a relevant comparison has run.
Candidate mechanisms: Reasoning needed: Deterministic validation available: Human expertise needed: Unnecessary steps to remove: Total cost per useful result: Error and retry burden:
Choose according to the task, not a preference for using AI everywhere. Include work delegated to people when estimating cost and delay.
Difference between demo and shipping requirements: Human attention required: Learning opportunity retained: Smallest authorized improvement: Owner and observation window: Decision after evaluation:
State remaining unknowns plainly. The record should support a concrete workflow review and later learning, not imply that a diagram or an automated reviewer guarantees quality.
.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