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-cunniffe-reusable-agent-platform/references/

Source outline

Read the corrected transcript for wording and context. Promotion cues 148–158 are omitted from the bundled transcript.

TimeCuesTopic
00:00–02:051–31Internal apps and network-level authentication
02:11–03:5032–59Factory expectations and review bottlenecks
04:08–05:1064–81Delivery, experiments, participation and maintenance
05:13–06:1082–95Development infrastructure versus app platform
06:12–07:2496–115Abstraction economics and dashboard example
07:31–09:26116–147Reuse rationale and large-company examples
10:11–12:22159–188Contribution boundaries and centralized fixes
12:25–14:29189–219Interfaces and API-mandate analogy
14:33–16:13220–246Bad abstractions, missing evals, skills
16:36–18:46250–283Testing, design-system and infrastructure Q&A
18:52–22:38284–343Access, test plans and enforcement Q&A
22:43–28:19344–429Observability ideas, role-selected skills, architecture

Short quotations

  • “what are these agents doing?” — cue 93, 06:03.
  • “bad abstractions are still a lot worse than no abstraction.” — cue 221, 14:38.
  • “we don't have evals for this yet.” — excerpt, cue 225, 14:50.

Evidence limits

The dashboard is a personal example, not a benchmark. Platform benefits are argued, not quantified. Role-selected skills and prompt-to-production trace correlation are ideas, not turnkey capabilities. Audience questions are not speaker claims. Company and product references reflect the speaker's event-time account.

skills

talk-cunniffe-reusable-agent-platform

tile.json