원클릭으로
talk-graziano-spec-driven-development
Spec-Driven Development: From Prompting to Production-Ready Systems
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Spec-Driven Development: From Prompting to Production-Ready Systems
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user asks about Christopher Batey's talk 'Building Product Teams in the Age of AI: What We Had to Relearn Every Quarter' (Latent Space, 2026) — including questions about running AI-assisted product engineering teams, his three pillars (path to production at AI speed, training/evaluating AI-enabled engineers, designing workflow for parallel change), ADR-first workflows with agents, why review becomes the bottleneck, the producer 'black box' (harness/host/model), vanity metrics vs adoption, two-to-four-person sub-streams, one-complex-task-at-a-time, 'you build it, you run it, you drive adoption', or applying his approach to current work.
Answers questions about, retrieves verbatim quotes from, explains concepts from, and summarizes key arguments in Birgitta Böckeler's talk "State of Play: AI Coding Assistants" (AI Native Dev conference, 2026). Use when the user asks about the last 12 months in AI coding assistants, the Opus 4.5 moment, LLM statelessness, context window and attention trade-offs, choosing the right model for a task, the ecosystem around models, or her Thoughtworks/Martin Fowler-site writing on AI-assisted software delivery.
Use when the user asks about Patrick Debois's talk "Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement." — including questions about agent enablement teams, the three pillars (Enablement, Platform, Governance), the Context Development Lifecycle applied to org charts, AI product engineers, agent KPIs like turns-per-task, harnesses and shared context libraries, fixing the system vs. fixing the code, the barrel mental model, continuous learning as the next CI/CD, or how VPs / team leads / platform teams should scale AI coding agents across an org.
Answers questions about Brian Douglas's talk on training AI on your own code. Use when a user asks about Brian Douglas's pipeline for capturing agent sessions, extracting skills from traces, fine-tuning small local models, tapes/steros tooling, SFT vs DPO decisions, or wants to apply his agent telemetry and training data approach to their own work with Claude Code, QLoRA, or parallel agents.
Use when the user asks about Tammuz Dubnov's talk "When Our PM Started Writing Code: What Merge Rate Taught Us About AI Adoption" — including questions about what "AI-native" means, harness engineering, merge rate as an AI-adoption metric, non-technical contributors (PMs, designers) opening pull requests, PR fatigue, the ~74% merge rate / ~84% zero-dev-touch numbers from Autonomy AI, why Uber/Microsoft's AI spend isn't translating to velocity, Shopify as a positive example, Calamarous Coding, feature-flag-driven developer autonomy, or applying his framework to the user's own engineering org.
Use when the user asks about Dave Farley's talk "Vibe Coding — Is this really the best we can do?" — including questions about vibe coding, agentic programming, AI-generated tests, BDD-style executable specifications as prompts, problem-specific DSLs, why natural language is insufficient as a programming language, the three properties of programming languages (formal grammar / unambiguous intent / deterministic execution), the three problems AI programming creates (precise specification, verification, incrementalism), fifth-generation programming, AI as compiler, or applying Farley's continuous-delivery-style approach to working with AI coding agents.
| name | talk-graziano-spec-driven-development |
| description | Spec-Driven Development: From Prompting to Production-Ready Systems |
Alfonso Graziano (AI Tech Lead at Nearform) argues that AI-assisted coding only graduates from prototyping toy to reliable engineering discipline when specifications become first-class artifacts. The talk walks through Spec Kit's four-phase workflow (specify → plan → tasks → implement), the verification loop that replaces line-by-line code review, and field-tested patterns his teams use across dozens of projects — including using a stronger model for the spec and a smaller one for implementation, treating the spec as a contract between human and AI, and running adversarial reviews to catch internal inconsistencies.
outline.md to locate the relevant section, then read that section of transcript.md.transcript.md. Never put quotation marks around paraphrased content.transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.[Spec Kit] style bracketed clarifications.When the user asks "how would Graziano tackle ?" or wants the talk's framework applied to their own situation:
outline.md → "Named frameworks / concepts" to find the relevant framework (Spec Kit four-phase loop, problem-space vs solution-space, adversarial review, model-tier split, etc.).transcript.md for the speaker's exact wording.When the user asks to "audit", "score", "review", "grade", "check", or "gap-analyse" their AI-coding setup against the talk's framework:
outline.md → "Named frameworks / concepts" to locate the four Spec Kit phases (specify, plan, tasks, implement) plus the supporting guardrails (constitution, project context, human-in-the-loop review, adversarial review).transcript.md and quote it verbatim when stating what "good" looks like.When the user asks to draft a spec, plan, tasks file, constitution, or EARS-format requirement:
outline.md and transcript.md.[not from talk — added as a starting placeholder].When the user wants to understand a concept Graziano covered (SDD, constitution, adversarial review, problem-space vs solution-space, vibe coding vs SDD, etc.):
outline.md → "Terminology glossary".transcript.md.For any question about what the speaker said:
outline.md first to find the relevant section(s).transcript.md.When the user's current work touches on AI-assisted coding, prompt engineering, spec writing, AI agent guardrails, or drift between code and intent (even if they haven't asked about this talk):
transcript.md — one quote is usually enough.quotes.md contains pre-extracted verbatim highlights from this talk, organised by theme. When formulating answers, check quotes.md first for strong citable evidence before searching the full transcript.md.