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 Huntley's talk. Fill it for one dependency and one failure. Unknown versions, results, or owners remain unknown.
Describe the affected behavior and the evidence that the dependency participates in it. List direct consumers and transitive consumers separately. Record the version and source actually resolved in each environment, including local modifications. Do not treat a manifest entry as proof that production uses that build.
| Surface | Definition and resolved inputs | Intentional differences | Evidence of parity |
|---|---|---|---|
| Developer machine | |||
| CI | |||
| Agent sandbox | |||
| Production artifact |
Explain where drift can occur. Identify which common definition could produce all four outputs and what remains specific to each environment.
State the chosen option: upstream update, local patch, vendored component, or narrowly scoped replacement. Give the reason and ongoing maintenance owner. Describe the required behavioral change without inventing a runnable Nix command.
List consumers that must be rebuilt, validation inputs, resulting artifact identity, and distribution route. Define one regression check for the defect and one compatibility check for an affected consumer. These check categories are suggestions, not claims that the speaker ran them.
Identify one action the agent should be unable to perform. Record the enforcing mechanism, alternate paths that need inspection, and the test that would demonstrate the restriction. A patched Git binary alone is not evidence that credentials cannot force-push through another route.
State one system invariant suitable for property-based exploration and the counterexample needed to reproduce a failure. Separate unit, architecture, and infrastructure checks.
Record the upstream correction to watch, review date, removal criteria, and rollback condition. Seven days is an anecdotal reminder interval, not an expiry policy. Finish with the evidence needed before adopting or retiring this patch, and keep production access outside the experiment unless separately authorized.
.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