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
Use this worksheet for one release or change category. It adapts the talk's scenario to existing organizational authority.
Change or work item: Existing release policy: Stakeholders actually needed: Actions already authorized: Decisions still unresolved:
Do not recreate the fictional organization's full structure if only a few decisions apply.
| Role | Meaning of approval | Evidence source | Scope and freshness | Missing or failed behavior |
|---|---|---|---|---|
| Engineering | ||||
| Security or operations | ||||
| Finance or product | ||||
| Other required owner |
Tie every material signal to the relevant release, service, or work item. Distinguish a negative finding from unavailable evidence. Record conflicting records explicitly.
Policy owner: Who may change controls: Who may grant the relevant exception: Exception scope and expiry: Decision rationale: Evidence retained: How the factory is prevented from expanding its own authority:
Specify the actual existing boundary. Do not add unnecessary approvals or infer that an agent's access to a tool authorizes policy changes.
Delivery unit: Usage attribution: Forecast and basis: Actual spend: Budget boundary: Behavior when exhausted: Remaining work estimate: Authorized continuation path:
Use differences between forecast and actual spending to improve the next estimate. Avoid treating token price alone as a project forecast.
Signals already available: Missing connectors or associations: Permission and freshness gaps: Build effort: Existing-system option: Smallest testable workflow:
For each proposed integration, define the evidence that would demonstrate correct retrieval and access. Keep results unverified until observed.
Supported decisions: Decisions blocked by evidence: Recommended next step: Owner: Verification:
The artifact supports decisions; it does not certify compliance, grant permissions, or release software.
.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