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 exact context. Promotion cues 303–313 are omitted.
| Time | Cues | Topic |
|---|---|---|
| 00:00–03:55 | 1–59 | On-call context gathering and repetitive toil |
| 03:57–07:30 | 60–114 | Connecting tools and adapting workflow to the team |
| 07:40–08:28 | 117–129 | Alert provenance and signature verification |
| 08:33–10:01 | 130–153 | Deduplication, correlation and rule-governed closure |
| 10:04–11:43 | 154–180 | Screening, triage and routing |
| 11:43–14:10 | 181–219 | Certificate example and follow-up investigations |
| 14:16–16:24 | 220–250 | Workflow structure and reported Jev cost improvement |
| 16:29–19:56 | 251–302 | Dossier shape, read-only questions and operator judgment |
| 20:40–23:42 | 314–356 | Corrected agent-decision claim and human expertise |
| 24:25–27:03 | 368–410 | Learning, interviews, postmortems and P2 clarification |
| 27:30–30:38 | 417–468 | Prepared Q&A: evidence, storms, injection, access, cost |
| 31:07–34:12 | 471–519 | Audience answers and wider tooling direction |
The speaker corrects his earlier absolute statement about agents making no decisions: duplicate/previous-incident classification uses an agent. Closure remains described as deterministic business logic. The five-minute path, 91% saving and model-call cost ratio are workload-specific reports, not benchmark guarantees. The certificate example was P2, not a fully expired certificate. The question preceding cues 471 onward is not captured clearly; do not invent its wording.
.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