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
Read transcript.md for wording. Promotion cues 228–238 are omitted.
| Time | Cues | Topic |
|---|---|---|
| 00:00–00:52 | 1–13 | Verification defined as mechanical judgment |
| 00:54–03:30 | 14–51 | Low-level safety versus functional correctness |
| 03:33–05:58 | 52–83 | Context contamination and LLM-judge limits |
| 06:00–06:55 | 84–98 | Candidate, verifier and targeted-feedback loop |
| 07:05–08:51 | 100–123 | Assurance spectrum and contract review |
| 08:55–11:18 | 124–161 | Preconditions, postconditions and caller boundaries |
| 11:23–14:11 | 162–202 | Money-splitting failure and repair |
| 14:20–15:59 | 204–227 | Spec checking, review and assurance trade-offs |
| 16:42–19:32 | 239–278 | Functional core and invariant preservation |
| 19:38–20:41 | 279–295 | Commands as data and effect interpreter |
| 20:52–21:51 | 297–315 | Contract authorship and extraction Q&A |
| 21:59–25:41 | 317–367 | Frozen lemmas and justified spec evolution |
| 25:48–27:42 | 368–394 | Takeaways and effects research limits |
The proof is relative to contracts, assumptions and the verified portion. Effects and unverified state constructors remain explicit boundaries. The low/high inequality is verbally inconsistent between cues 127–128 and 145–146. Claims of speed and cost are qualitative; no benchmark is supplied. The joint transcript does not reliably assign every explanation to an individual speaker. The external research contrast is their account, not an independently examined study.
.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