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: Baruch Sadogursky, The Software Factory of Factories, 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 |
|---|---|---|---|
| Fictional stakeholders | 00:01:09–00:04:02, cues 19–57 | “As long as Bill as Brent maintains control” | The opening scenario illustrates competing organizational expectations. |
| Approval bottleneck | 00:05:09–00:06:36, cues 72–87 | “what's going on for their needs.” | Stakeholders request different evidence. |
| Signal-based engineering | 00:08:06–00:10:00, cues 104–127 | “he built himself a signal system” | The scenario substitutes decision signals for reading every line. |
| Approval meaning | 00:10:04–00:12:40, cues 128–160 | “what can we demonstrate to the regulators.” | Different roles need different propositions supported. |
| Evidence sources | 00:13:43–00:17:23, cues 175–223 | “None of that is in the repository.” | Many relevant records live outside code. |
| Budget continuation | 00:17:25–00:18:14, cues 224–234 | “my model was off and I need to adjust it.” | Budget exceptions can inform forecasts rather than merely punish. |
| Missing context | 00:18:20–00:19:28, cues 235–249 | “alert when it's not found” | Missing evidence should be visible and addressed. |
| Build versus buy | 00:19:30–00:20:50, cues 250–265 | “huge advantages in not building it.” | The story motivates assessing existing infrastructure. |
| Agent inventory | 00:20:54–00:22:21, cues 266–284 | “agents that have ownership, that have permissions” | Agent governance includes identity and allowed capabilities. |
| Control authority | 00:22:24–00:25:15, cues 285–317 | “authorizing to remove controls by itself” | The factory should not grant itself authority to remove controls. |
| Three takeaways | 00:25:31–00:26:31, cues 320–332 | “Define what approvals means.” | Define the decision, engineer the signal, assess existing providers. |
| Views Q&A | 00:28:09–00:32:02, cues 356–407 | “the answer is both.” | Different roles need different views of connected evidence. |
| Integration Q&A | 00:32:18–00:33:01, cues 411–422 | “The hardest part is being is building the integrations” | Integration remains substantial work. |
The agent-facing transcript omits unrelated promotional offer/sign-up cues 333–351 and 354. Original cue numbers and timestamps for substantive content are unchanged.
.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