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-finster-continuous-delivery/references/

Source outline

Source: Bryan Finster, Your Software Factory Already Has a Name: Continuous Delivery, 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
Meaning of CD00:00:16–00:01:14, cues 5–18“CD is the entire software development lifecycle”CD concerns idea-to-feedback flow, not only pipelines.
Large-batch risk00:03:20–00:04:09, cues 50–61“smaller haystacks”The speaker connects smaller changes to faster feedback.
Tools versus working practices00:04:15–00:05:42, cues 62–83“What matters is how we work.”A platform did not resolve vague requirements and validation problems.
Acceptance and slicing00:05:47–00:07:03, cues 84–101“testable acceptance criteria.”BDD collaboration supported tests committed with thin changes.
Downstream constraints00:07:09–00:08:39, cues 103–124“all the external roadblocks.”The reported delivery improvements required organizational changes.
Agent planning00:10:03–00:11:51, cues 143–167“I own the guardrails.”Collaborative planning and independent review retain human ownership.
Review ordering00:13:49–00:15:05, cues 197–214“deterministic checks early on.”The described workflow uses deterministic then focused pattern checks.
Improve the controls00:15:48–00:17:25, cues 226–250“The pipeline is never static.”Escaped problems should improve the verification process.
Legacy characterization00:18:28–00:20:07, cues 263–285“you don't want to refactor untested code.”The described sequence establishes and validates tests before refactoring.
Whole lead time00:21:47–00:23:00, cues 308–324“saved 3% of the entire lead.”A personal migration example illustrates downstream delay.
Model and workflow experiments00:25:09–00:27:10, cues 353–382“Find out.”Model choice and TDD comparisons are reported experiments, not universal rules.

Source limitations

  • The Walmart and ACI accounts and delivery figures are reported experience, not independently verified causal estimates or guarantees.
  • The 400-lines-per-hour claim cites unspecified studies; do not treat it as a universal review limit or supply an unseen citation.
  • The Q&A's relative TDD cost and model preferences are contextual experiments. They do not establish that TDD is always worse or that a model is currently best.
  • Do not reconstruct the plugin's GitHub address or executable command semantics from unseen slides. The talk is not a current tool manual.
  • Promotional interlude cues 215–225 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-finster-continuous-delivery

tile.json