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 suggested application of Re Ferre's talk. Fill it for one team workflow rather than the whole organization at once.
Record the initial signal, triage, design, build, test, release, and observation steps. Identify the owner, input, output, active work time, and waiting time at each step. Mark unmeasured time as unknown. Name the bottleneck that the proposed change will address.
Describe whether work needs to move off a laptop, gain automation, or use an identity distinct from an individual. Explain each choice independently.
For enablement, describe the task-specific environment a new team member needs: relevant skills, context connections, instructions, and a small first success. Record which setup is distributed centrally and which choices still depend on individual knowledge.
For cost control, connect each run to its deliverable and acceptance evidence. Track configuration, spending, failed attempts, and rework where available. A high token bill or low usage count alone does not establish value.
State the required quality bar, candidate model or routing policy, representative evaluation tasks, and an exception condition. Do not copy illustrative costs from the talk. Explain how the team will compare total useful work, including rework, rather than choosing on token price alone.
Write the intended outcome in language that both builder and reviewer can use. List acceptance criteria and supporting evidence. Mark ambiguous product decisions. Define the particular complexity or input gap that requires clarification before implementation.
Choose one recurring task, baseline, proposed change, and observation period. Specify the evidence needed to expand it, revise it, or stop. Keep existing release authority explicit. Finish with a short decision: what the team can implement now, what remains unverified, and the smallest next measurement.
.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