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
Source: Nicholas Arcolano, Botsitting Doesn't Scale: How to Navigate the Autonomy-Trust Gridlock in Real Engineering Orgs, AI Native DevCon New York 2026. Recording. All anchors refer to original numbered cues in the transcript. Short quotations below preserve the supplied transcription, including spoken wording.
| Topic | Source anchor | Exact short quote | Application and scope |
|---|---|---|---|
| Elevator analogy | 00:01:06–00:03:31, cues 19–59 | “The safeguards was there. The trust was not there.” | The analogy distinguishes safeguards from trust. |
| Reported data | 00:03:36–00:05:17, cues 61–85 | “We collect agent telemetry engineering workflow data” | The findings concern observed telemetry populations. |
| Review bottleneck | 00:05:23–00:07:29, cues 87–118 | “code generation is far outpacing approval and merging.” | Generation and delivery are distinct stages. |
| Attention limits | 00:08:25–00:09:27, cues 131–147 | “watching these agents is expensive.” | Session observations motivate the attention constraint. |
| Review and abandonment | 00:09:31–00:11:54, cues 148–180 | “mostly just being ignored or abandoned.” | Non-merge does not automatically mean quality rejection. |
| Three themes | 00:13:49–00:14:39, cues 209–218 | “defining what done looks like before the” | Move judgment earlier and earn trust by work category. |
| Selection effects | 00:14:43–00:17:26, cues 219–256 | “people are going where the heat” | Higher reversion with human involvement is explained by risk selection. |
| Ticket discipline | 00:17:29–00:18:34, cues 257–273 | “giving a good acceptance criteria” | The source associates scoped work with completion. |
| AI review limits | 00:18:38–00:20:17, cues 274–293 | “it's just adding another voice.” | Adding reviewers did not remove the observed bottleneck. |
| Value leakage Q&A | 00:26:35–00:28:42, cues 367–397 | “other business processes haven't caught up.” | Prioritization can constrain useful delivery. |
| Bounded delegation Q&A | 00:28:49–00:30:39, cues 400–428 | “it's a long road” | The speaker does not recommend automatically merging all work. |
.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