Enter the access password to view the site.
A quick-reference companion to the Tomorrow FDLC. Each activity is keyed to the canvas phase model (Phase 0 Discover through Phase 4 Learn), the G0–G4 gates, the owning role, and an AI mode. Use it to orient on what AI does at each stage and who owns the output. Tool-agnostic by design — for Track A (Copilot/OpenAI) and Track B (Claude Code) specifics see the Cost optimization addendum.
Apply these to any AI-assisted task across any role.
Give the model explicit goals, explicit limitations, clear output expectations, and component or pattern constraints. Constrained prompts produce more consistent, usable output.
Break work into steps — spec interpretation, screen generation, state completion, review — rather than one prompt that tries to do everything at once.
Once usable output exists, prompt to update and refine rather than recreate from scratch. Regeneration wastes context and loses accumulated decisions.
Reference design system components, tokens, pattern names, product terms, and spec sections consistently. The model performs better when it recognises your terminology.
Encode quality through checklists, sections, constraints, and acceptance criteria. Long narrative instructions produce longer, less focused outputs.
Each activity is tagged with one of three modes — the same vocabulary the FDLC canvas uses. The mode tells you who owns the work and where the human judgment sits.
Agent owns the activity. Human reviews and approves output.
Human owns the activity. Agent drafts the first version.
Requires human judgment, accountability, or stakeholder relationship.
Each row maps an activity to its owning role, the gate it serves, the AI mode, and a starter prompt. Phase numbering follows the FDLC canvas; gates follow the workflow walkthrough.
| Activity | Role | Gate | Mode | Starter prompt |
|---|---|---|---|---|
| Customer signal monitoring | PM, CS | continuous | Agent-led | Run a weekly synthesis across support, reviews, and community channels. Output themes, frequency, sentiment, suggested action. |
| VoC and behavioral synthesis | PM | continuous | Agent-led | Synthesise this VoC corpus into themes: frequency, sentiment, representative quote, suggested action. |
| Product and business data analysis | PM | continuous | Agent-led | Here is 3 months of support data. Identify top 5 themes with frequency and severity. |
| Market and competitor analysis | PM | ad-hoc | Agent-led | Analyse [competitor] across UX, pricing, and positioning. Output a structured comparison. |
| Competitor UX review | Design | ad-hoc | Agent-led | Review these screenshots of [competitor]. Identify UX patterns and friction points. |
| Brief candidate authoring | PM | → G0 | Agent-assisted | Draft a brief from this signal: customer problem, scale, hypothesis, downstream costs. |
| Brief dispositioning | PM | G0 | Human-led | Human gate. Agent prepares the briefing pack; PM disposes (advance, return, park with rationale). |
| Activity | Role | Gate | Mode | Starter prompt |
|---|---|---|---|---|
| Problem statement and use cases | PM | G0 → G1 | Agent-assisted | Draft a problem statement from this brief using Jobs-to-be-Done format. |
| Value proposition | PM | G0 → G1 | Agent-assisted | Generate 3 value proposition options for [feature], one per buyer persona. |
| User research synthesis | Design | G0 → G1 | Agent-assisted | Here are N interview transcripts. Extract pain points and unmet needs. Group by theme. |
| Persona alignment | Design | G0 → G1 | Agent-assisted | Update our persona where new research suggests shifts in behaviour or goals. |
| Capacity check and dependency scan | Pod | → G1 | Agent-assisted | Identify dependencies, blockers, and capacity constraints from this brief. Surface from LDG. |
| Feature tier classification Enh / NewCap / NewPar | Pod | → G1 | Agent-assisted | Classify this feature as Enhancement, New Capability, or New Paradigm. Cite the sufficiency criteria. |
| Go / No Go | Pod (Trio) | G1 | Human-led | Human gate. Trio decides in a single short meeting; agent prepares the framing pack. |
| Functional and non-functional requirements | PM | G1 → G2 | Agent-assisted | Generate requirements: As a [role] I need [capability] so that [outcome]. Bind to spec.md §1.x. |
| Acceptance criteria | PM | G1 → G2 | Agent-assisted | Write Given/When/Then AC into spec.md §1.6 including happy path, error states, and edge cases. |
| Success metrics & analytics plan | PM | G1 → G2 | Agent-assisted | Draft spec.md §5.x success metrics and analytics plan tied to the job statement. |
| Variant scope declaration NewCap / NewPar | Design, PM | → G2 | Agent-assisted | Given the tier, declare the variant scope (count + intent) for G3. Log rationale. |
| Architecture engagement check | Engineering, Architecture | → G2 | Human-led | Human gate. Trigger per the architecture engagement policy; log in decision log. |
| Spec authoring (Trio co-author) | Pod | → G2 | Agent-assisted | Draft spec.md sections from the brief, AC list, and analytics plan. Apply the PM spec guide. |
| Spec sufficiency & AC quality check | Pod | → G2 | Agent-led | Check spec.md against P7 sufficiency thresholds and AC quality rules. Output JSON with findings. |
| Trio sign-off (spec approved) | Pod (Trio) | G2 | Human-led | Human gate. PM, Design, Engineering co-sign spec.md. Hard gate that closes Define. |
| Activity | Role | Gate | Mode | Starter prompt |
|---|---|---|---|---|
| User flows | Design | G2 → G3 | Agent-assisted | Draft a user flow for [scenario] covering primary path, alternatives, and error states. Use approved DS components. |
| Variant generation NewCap / NewPar | Design | G2 → G3 | Agent-led | Generate N variants from spec.md within the design constitution and approved DS components. Output variant intent + code per variant. |
| Single-variant prototype Enhancement | Design | G2 → G3 | Agent-assisted | Generate a coded prototype from spec.md against the design constitution. Include all spec states. |
| Accessibility annotations | Design | G2 → G3 | Agent-assisted | Annotate the prototype with focus order, ARIA, keyboard interactions, and contrast notes. |
| Spec-to-prototype reconciliation | Design, Engineering | G2 → G3 | Agent-led | Compare the prototype against spec.md §2.3 / §2.4 / §2.5. Flag deviations and out-of-scope additions. |
| DS compliance check | DS | G2 → G3 | Agent-led | Run DS compliance: token usage, component usage, state coverage. Output severity-classified findings. |
| Architecture evaluation (if triggered) | Engineering, Architecture | G2 → G3 | Agent-assisted | Outline 2 architecture options with trade-offs on scalability and reversibility. Draft ADR candidate. |
| Technical research & R&D spikes | Engineering | G2 → G3 | Agent-assisted | Summarise the current state of [technology] and identify key unknowns to spike on. |
| Engineering spec draft | Engineering | G2 → G3 | Agent-assisted | From G3-approved inputs, draft the engineering spec: data shape, service hooks, contracts. |
| Work item decomposition (units of work) | Engineering | G2 → G3 | Agent-assisted | Break spec.md into units of work completable in 1–3 days. Map each unit to AC items. |
| G3 review brief | Pod | → G3 | Agent-led | Synthesise the feature folder into a G3 review brief: variants, ADRs, DS findings, AC coverage. |
| UX hard gate (G3 sign-off) | Design | G3 | Human-led | Human gate. Design owns the handoff package; UX hard gate runs before QA testing. |
| Code development (per unit of work) | Engineering | G3 → G4 | Agent-assisted | Implement this unit against the engineering companion and constitution. Output code only; verify against AC before marking done. |
| Test plan and script generation | Engineering (QA) | G3 → G4 | Agent-led | Generate a test plan covering unit, integration, and UAT. Map each test to an AC item in spec.md §1.6. |
| Code review and PR descriptions | Engineering | G3 → G4 | Agent-led | Use the agent PR description as default. Engineer edits and confirms — never skip review. |
| Bug triage and root cause | Engineering | G3 → G4 | Agent-assisted | Here is the error log. Identify the most likely root cause and 2 investigation paths. |
| AC clarification and gap detection | Engineering | G3 → G4 | Agent-assisted | Review these AC and identify ambiguities, missing edge cases, or untestable conditions. Log gaps via the spec gap protocol. |
| UAT script generation | PM | G3 → G4 | Agent-assisted | Generate a UAT script with pre-conditions, steps, expected outcomes, and pass/fail criteria. |
| In-product content and microcopy | TC | G3 → G4 | Agent-assisted | Draft UI copy for empty, loading, error, success, confirmation, and tooltip states. |
| Build quality and metrics tracking | Engineering | G3 → G4 | Agent-assisted | Weekly agent-generated quality digest: coverage, failed builds, open defects. |
| Security and compliance review | Architecture | G3 → G4 | Human-led | Human gate. Agent prepares the evidence pack but cannot substitute the review. |
| UX Review Gate | Design | → G4 | Human-led | Human gate (pre-CI/CD). Verifies the build matches design intent; AC re-verified against spec. |
| G4 close-out record | Pod | G4 | Agent-led | Generate G4 close-out: decision log, amendments, ACs verified, cost log, pattern candidates. |
| Activity | Role | Gate | Mode | Starter prompt |
|---|---|---|---|---|
| Release notes drafting | TC | G4 → Launch | Agent-led | Draft customer-facing release notes from these PRs. Tone: clear, benefit-led. |
| Documentation drafting | TC | G4 → Launch | Agent-assisted | Draft customer-facing docs from spec.md and the build artifacts. |
| Launch coordination (GTM) | PMkt | G4 → Launch | Agent-assisted | Generate launch checklist: GTM materials, internal comms, enablement timing. |
| Telemetry & service health setup | Engineering | G4 → Launch | Agent-led | Configure anomaly thresholds from spec.md §5.x success metrics. |
| Rollout configuration | Engineering | G4 → Launch | Agent-led | Generate rollout config from the engineering spec: flags, stages, rollback plan. |
| Final regression sweep | Engineering (QA) | G4 → Launch | Agent-assisted | Run final regression against the test plan; flag deltas vs G4 baseline. |
| Release authorization (Go / No Go) | Pod | Launch | Human-led | Human gate. Agent compiles telemetry, UAT results, and risks into a one-page decision brief. |
| Activity | Role | Gate | Mode | Starter prompt |
|---|---|---|---|---|
| Feature success metric tracking | PM | post-Launch | Agent-led | Here are this week's metrics vs targets in spec.md §5.x. Identify on/off track items and decisions needed. |
| JTBD completion rate analysis | PM | post-Launch | Agent-assisted | Analyse completion rates against the job statement (§1.2) and analytics plan (§5.x). |
| User feedback synthesis | PM, CS | post-Launch | Agent-led | Synthesise post-launch feedback into themes: frequency, sentiment, representative quote, suggested action. |
| Content performance & gap analysis | TC | post-Launch | Agent-led | Here is search and support data. Identify gaps where users search but find no answers. |
| Defect prioritisation | Engineering | post-Launch | Agent-assisted | Triage these bugs by customer impact (H/M/L), reproduction frequency, and fix effort. |
| Pattern candidate identification | Pod, DS | post-Launch | Agent-assisted | From the build, identify reusable patterns to promote to the companion file. |
| Constitution amendment candidates | DS, Architecture | post-Launch | Agent-assisted | Synthesise build close-outs to identify constitution / companion file amendment candidates. |
| Spec gap / drift logging | Engineering | post-Launch | Agent-led | Compile the spec gap log entries from this cycle for the AI FDLC Review. |
| Cost log roll-up (cost-per-outcome) | PM, Del Owner | post-Launch | Agent-assisted | Calculate cycle time, rework rate, and cost-per-outcome from these close-out records. |
| Trio retrospective & amend | Pod (Trio) | post-Launch | Human-led | Human-led. The Trio retrospective produces the next constitution version before the next Define begins. |
| Activity | Role | Cadence | Mode | Starter prompt |
|---|---|---|---|---|
| Spec drift detection | Engineering | G2 → G4 | Agent-led | Compare the build against spec.md AC. Identify deviations, omissions, and out-of-scope additions. |
| Cost log entry | PM | every gate close | Agent-assisted | Generate cost log entry for this gate close: token spend, agent calls, anomalies flagged. |
| Companion file staleness monitor | DS | continuous | Agent-led | Flag companion file sections out of date against current build patterns or DS amendments. |
| Customer signal monitoring | PM, CS | weekly | Agent-led | Run a weekly synthesis across support, reviews, and community channels. |
| Oversight / mode review | Pod, AI FDLC Review | quarterly | Human-led | Review which activities are agent-led, assisted, or human-led. Adjust based on close-out evidence. |
Design-specific expansions of the one-line starters above. For non-design agent types and the canonical six-section prompt template standard (Role / Context / Task / Output Format / Constraints / Stop Condition), see Cost optimization §03. The templates here follow that standard while remaining design-focused.
Create a production-oriented prototype in code using the design system and shared interaction patterns.
[spec] · [domain context] · [relevant patterns] · [approved components list]
Generate 3 distinct UI variants for the same feature. Explore different approaches to hierarchy, flow, and layout without violating the design system.
End with a recommendation and rationale for the best option.
Create a cohesive multi-step flow that supports the user goal from entry to completion.
[changes]
Critical · Major · Minor
[description]
Local only · Team shared · Design system candidate