CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

ainativedev/aidevcon-2026-nyc

AI Native DevCon 2026 New York — practical agent skills grounded in conference talks

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

outline.mdskills/talk-arcolano-autonomy-and-trust/references/

Source outline

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.

TopicSource anchorExact short quoteApplication and scope
Elevator analogy00:01:06–00:03:31, cues 19–59“The safeguards was there. The trust was not there.”The analogy distinguishes safeguards from trust.
Reported data00:03:36–00:05:17, cues 61–85“We collect agent telemetry engineering workflow data”The findings concern observed telemetry populations.
Review bottleneck00:05:23–00:07:29, cues 87–118“code generation is far outpacing approval and merging.”Generation and delivery are distinct stages.
Attention limits00:08:25–00:09:27, cues 131–147“watching these agents is expensive.”Session observations motivate the attention constraint.
Review and abandonment00:09:31–00:11:54, cues 148–180“mostly just being ignored or abandoned.”Non-merge does not automatically mean quality rejection.
Three themes00:13:49–00:14:39, cues 209–218“defining what done looks like before the”Move judgment earlier and earn trust by work category.
Selection effects00:14:43–00:17:26, cues 219–256“people are going where the heat”Higher reversion with human involvement is explained by risk selection.
Ticket discipline00:17:29–00:18:34, cues 257–273“giving a good acceptance criteria”The source associates scoped work with completion.
AI review limits00:18:38–00:20:17, cues 274–293“it's just adding another voice.”Adding reviewers did not remove the observed bottleneck.
Value leakage Q&A00:26:35–00:28:42, cues 367–397“other business processes haven't caught up.”Prioritization can constrain useful delivery.
Bounded delegation Q&A00:28:49–00:30:39, cues 400–428“it's a long road”The speaker does not recommend automatically merging all work.

Source limitations

  • Numerical findings are speaker-reported observations from selected populations, not universal facts or a causal trial.
  • The source supplies no full matching methods, confidence intervals, or underlying dataset records.
  • Higher reversion among human-involved changes does not prove review harms quality; the speaker explains risk selection.
  • The elevator analogy does not establish that every software decision should be automated.
  • Promotional interlude cues 181–191 are omitted from the bundled transcript; the remaining cue numbers retain their source positions.
  • This is a spoken transcript; unseen slides, linked repositories, and third-party research were not independently inspected. No outcome beyond the described talk is established.

skills

talk-arcolano-autonomy-and-trust

tile.json