Skip to content

Partially Verified by AI Team

The Mob Elaboration approach has been trialed in select projects. Multi-level spec management is integrated into existing workflows.

Feature Development Flow

This document describes the complete feature development flow, explaining how AI-DLC (AI-Driven Development Life Cycle) Mob Elaboration integrates into the multi-level spec management system in the Workflow Framework.

Early Convergence Phase

Before entering spec refinement, the Early Convergence Phase must be completed first. This is where humans contribute the most wisdom and work most intensively throughout the entire workflow.

PhaseDescriptionParticipants
Receive IntentReceive requirement intent from business or productPM, Business
Intensive DiscussionComplete all key decision convergence within 2-3 daysAll Stakeholders
Form ProposalProduce a spec-reviewed proposal documentPM, Tech Lead, Design
Produce SpecsGenerate detailed specs via OpenSpecEach Role + AI

Key: Early Convergence

The core of this workflow is the 2-3 days of intensive upfront discussion. All stakeholders who might influence the spec must complete opinion convergence during this phase to avoid late-stage changes causing rework.

Why No AI in Early Convergence?

According to AI-DLC definitions, AI should theoretically be involved in the early convergence phase. However, after actual experimentation, we found that AI produces over-extended specs when context is not sufficiently clear.

Therefore, at this stage we still recommend using human thinking for specifications. This is also where humans contribute the most wisdom and work most intensively throughout the entire workflow.

During this intensive discussion of intent and proposals, everyone becomes a core designer of the product—everyone is closely connected to it.

Relationship with Workflow Framework

AI-DLC Mob Elaboration Flow

PhaseDescriptionOutput
Requirement SeedThrough intensive discussion in mob elaboration meetingRefined preliminary spec
AI ExpansionAI expands the preliminary specStandardized spec document

Early Convergence produces the Preliminary Spec (requirement seed), which is then transformed via AI Expansion into a Standardized Spec Document. After spec review, it becomes the High-Level Spec, then enters the multi-level spec management flow of the Workflow Framework.

Practical Timeline Example

Below is a typical day-by-day timeline for feature development, showing each role's participation at different stages:

Timeline Overview

Day-by-Day Breakdown

DayPhaseActivityParticipantsOutput
Day -5~-1Pre-MeetingPM writes requirement seed, each role prepares materialsPM, RD, UX, ArchitectRequirement seed, prep materials
Day 0-2Mob ElaborationHold Mob Elaboration meeting, intensive discussionPM, RD, UX, ArchitectPreliminary spec (refined requirements)
Day 3AI ExpansionAI expands preliminary spec into standardized documentAI, RDStandardized spec document
Day 4Spec ArchiveReview and archive high-level specPM, RDVersioned high-level spec
Day 5-6Web UX BranchGenerate Web UX spec and wireframesUX, AIWeb UX spec, design tokens
Day 5-6App UX BranchGenerate App UX spec and wireframesUX, AIApp UX spec, design tokens
Day 5-6API BranchGenerate API spec and OpenAPIRD, Architect, AIOpenAPI document
Day 5-6Design BranchGenerate technical design documentArchitect, AIArchitecture decisions, technical design
Day 7-9Web Frontend ImplDevelop based on Web UX + API specsWeb Frontend RD, AIWeb frontend code
Day 7-9App Frontend ImplDevelop based on App UX + API specsApp Frontend RD, AIApp frontend code
Day 7-9Backend ImplDevelop based on API + Design docsBackend RD, AIBackend code
Day 10-11TestingQA executes acceptance testsQA, AITest report
Day 10Code ReviewReview codeRD, TLReview comments, approval
Day 12CompleteMerge to main branch, deployment prepRD, OpsDeployable version

Role Participation Timeline

Key Milestones

MilestoneTimingVerification ItemsOwner
Requirement Seed CompleteDay 0Business context, scope, constraints documentedPM
High-Level Spec ApprovedDay 2All participants reach consensus, edge cases identifiedPM, RD, UX, Architect
Spec Branches CompleteDay 4Web UX/App UX/API/Design specs archivedBranch owners
Development CompleteDay 7Code complete, unit tests passingRD
Acceptance CompleteDay 10QA acceptance passed, Code Review approvedQA, TL

Problems with Traditional SDLC

Sequential Knowledge Transfer

Blind Spots by Role

RoleBlind SpotConsequence
PMTechnical constraints, API limitsUnrealistic requirements
RDUX impact, user journey gapsPoor user experience
UXTechnical feasibility, data availabilityUnimplementable designs
ArchitectBusiness context, priority trade-offsOver-engineered solutions
EveryoneEdge cases, error scenariosProduction bugs

AI-DLC Solution: Mob Elaboration

Core Insight: Requirement quality improves significantly when multiple perspectives challenge assumptions simultaneously. AI adds a tireless participant that surfaces edge cases, checks consistency, and maintains complete documentation in real-time.

Target State

Phase 1: Pre-Meeting Preparation

Requirement Seed

Before the Mob Elaboration meeting, PM prepares a requirement seed document:

markdown
## Requirement Seed: [Feature Name]

### Business Context
- Why now?
- Who requested this?
- What problem does it solve?

### Initial Scope
- Must have: [Core functionality]
- Nice to have: [Bonus features]
- Out of scope: [Explicit exclusions]

### Known Constraints
- Timeline:
- Budget:
- Technical:

### Success Metrics
- [Quantifiable success criteria]

Participant Preparation

RolePre-Meeting Prep
PMPrepare requirement seed, business context
RDFamiliarize with related code, technical constraints
UXPrepare user journeys, competitor references
ArchitectAssess system impact, existing architecture
AI AgentLoad CLAUDE.md, existing specs, API docs

Phase 2: Mob Elaboration Meeting

Meeting Flow

Human Roles in Meeting

The Mob Elaboration meeting is where humans contribute the most wisdom and work most intensively. Each role brings unique perspectives:

RoleResponsibilityContribution
PMBusiness context guardianEnsure requirements align with business goals, clarify priorities
RDTechnical feasibility gatekeeperAssess technical constraints, propose alternatives
UXUser experience advocateEnsure complete user journeys, identify experience pain points
ArchitectSystem integrity guardianAssess architecture impact, ensure consistency

Why Emphasize Human Roles?

During this intensive discussion of intent and proposals, everyone becomes a core designer of the product—everyone is closely connected to it.

AI in this phase only serves as assistance for recording and organizing, not participating in decisions. All key decisions are made by humans.

Phase 3: Spec Branching

After Mob Elaboration produces the high-level spec, it enters the multi-level spec management:

Standard Workflow for Each Branch

Each branch follows the Receive → Combine → Delegate → Review → Refine → Archive pattern:

BranchReceiveCombineDelegate
Web UXHigh-level specWeb design system, brand guideAI generates Web UX spec draft
App UXHigh-level specApp design system, platform guidelinesAI generates App UX spec draft
APIHigh-level specAPI design principlesAI generates OpenAPI draft
DesignHigh-level specArchitecture principles, tech stackAI generates design doc draft
BackendAPI spec + Design docCode standardsAI-assisted implementation
Web FrontendWeb UX spec + API specWeb design system componentsAI-assisted implementation
App FrontendApp UX spec + API specApp design system componentsAI-assisted implementation
QAAll specsTest strategyAI generates test cases

Phase 4: AI-Assisted Implementation

Development Loop

AI Agent Development Assistance

TaskAI Can HelpAI Should Not
Write codeGenerate initial draft from specMake architectural decisions
DebugAnalyze error messages, suggest fixesIgnore root causes
RefactorImprove code structure as directedSignificantly change design
TestGenerate test casesSkip tests and mark complete

Phase 5: Review & Acceptance

Code Review Flow

Review Focus Areas

AspectCheck Items
Spec AlignmentDoes it match the Mob Elaboration spec?
Edge CasesAre edge cases from the spec handled?
CorrectnessIs the logic correct?
SecurityInjection risks? Permission checks complete?

QA Acceptance

Acceptance tests directly derive from Mob Elaboration outputs:

Definition of Done

CategoryCriteria
SpecAll acceptance criteria from Mob Elaboration spec met
CodeMerged to main branch, CI all green
TestingUnit/Integration/E2E tests pass, edge cases covered
ReviewCode Review approved
AcceptanceQA acceptance passed
DocumentationRequired docs updated, archived to version control

Applicability

Full Mob Elaboration for

  • New features with multiple stakeholders
  • Features spanning multiple systems
  • High-risk or high-visibility features
  • Features with unclear requirements

Lightweight Process

For well-defined small features, use:

  • Mini Elaboration: PM + RD + AI (30 minutes)
  • Direct Delegation: PM writes requirement seed, AI generates spec draft, RD reviews

Frequently Asked Questions

Does "2-3 days of intensive discussion" mean everyone is in meetings for 2-3 days straight?

No. "2-3 days" refers to the decision convergence time window, not continuous meeting time. Here's how it actually works:

ActivityTimingFormat
Pre-meeting prepDay -5 ~ -1Async, individual preparation
Mob Elaboration meetingDay 0Sync, 2-4 hours
Async refinementDay 0-2Async, document comments, Slack discussions
Final convergence meetingDay 2Sync, 1-2 hours

Core synchronous time is about 4-6 hours spread across 2-3 days.

What if stakeholders are distributed across different time zones?

Hybrid sync/async mode:

  1. Identify overlap windows: Find 2-3 hour slots where all key participants can join
  2. Async-first discussions: Collect opinions and concerns via documents before the meeting
  3. Recording supplement: Record sync meetings for those who can't attend to watch and provide written feedback
  4. Split meetings: If no overlap exists, consider two separate meetings with PM as the bridge

Key: Ensure every critical decision-maker has an opportunity to express their views before decisions are finalized.

What if a key role (like Legal or Security) can only attend for 2 hours?

Expert time slot planning:

StrategyApproach
Pre-written inputSend focused questionnaire before meeting to collect key constraints and considerations
Dedicated slotReserve 30-60 minutes in the meeting specifically for the key expert
Proxy attendanceDesignate someone familiar with that domain as meeting proxy, confirm with expert afterward
Post-meeting reviewReserve 24-48 hours for expert to review preliminary spec and raise objections

Practical tips:

  • Legal, Security, and other specialized roles typically focus on specific aspects; they don't need full participation
  • Prepare a "summary for experts" document focusing on their areas of concern
  • Clearly communicate what will be decided in the meeting so experts know where their input is needed
How do we handle roles with veto power who "can't participate but have final say"?

Tiered decision authority mechanism:

Concrete approaches:

  1. Pre-meeting alignment: PM conducts 30-minute individual pre-alignment with veto-power roles before Mob Elaboration
  2. Explicit authorization: Obtain "can proceed under X conditions" conditional authorization
  3. Reserve review window: Allow 24-48 hour objection period after spec is produced
  4. Escalation mechanism: If objections come after the review period, they must go through change management

Warning: If a veto-power role can't even arrange 30 minutes for pre-alignment, this is usually an organizational problem, not a process problem. Escalate for coordination.

In reality, it's very hard to get everyone free at the same time. What alternatives exist?

Pragmatic alternative strategies:

SituationAlternative
Only 2-3 people can syncUse mini-elaboration + async review cycles
Core members completely can't syncPure async elaboration (extends to 5-7 days)
Urgent feature can't waitNarrow scope, do MVP version Mob Elaboration first

Async Mob Elaboration flow:

Note: Async mode significantly increases communication costs and convergence time. Recommend using only when necessary, and scheduling a 30-minute sync meeting afterward for final confirmation.

How do we determine which features need full Mob Elaboration vs. simplified processes?

Decision matrix:

CriteriaFull Mob ElaborationMini ElaborationDirect Delegation
Stakeholders≥ 4 people/teams2-3 people1 person (PM can decide)
Cross-system impact≥ 3 systems1-2 systemsSingle system
UncertaintyUnclear requirements, multiple possibilitiesMostly clear, few items to confirmCompletely clear
Risk levelHigh (revenue, security, compliance impact)MediumLow
Estimated effort≥ 2 weeks3-10 days≤ 3 days

Rules of thumb:

  • If you can't explain to RD what needs to be done in 5 minutes, you need at least a mini-elaboration
  • If anyone says "we need to ask XX about this," bring XX in
  • If the answer is "it depends" more than "definitely X," you need more thorough elaboration
Does "avoiding late-stage changes" mean features can never be modified?

No. "Avoiding late-stage changes" refers to within a single feature development cycle—decisions from the convergence meeting should be followed. This doesn't mean features can never evolve.

Correct understanding:

TimingRecommended Approach
Within cycleFollow convergence decisions, avoid mid-cycle overturning
Post-releaseCollect feedback, plan for next cycle
EmergencyFollow emergency change process (see below)

Why stay stable within a cycle?

  • AI has started executing based on specs; mid-cycle changes cause massive rework
  • Team has allocated resources; changes affect other schedules
  • Frequent changes destroy the value of "early convergence"
What if market conditions really change (e.g., competitor releases new feature)?

Ask three questions first:

  1. Urgency: Does this change affect the core value of this release?
  2. Scope impact: Will the adjustment affect more than 30% of planned work?
  3. Time buffer: How much time remains until the planned release?

Decision matrix:

SituationRecommended Approach
Doesn't affect core valueRecord it, include in next cycle
Affects core but small scope (< 30%)Hold mini-elaboration to adjust
Affects core and large scope (≥ 30%)Consider pausing current cycle, re-converge

Practical advice:

Most "market changes" aren't as urgent as they seem. Ask yourself:

"What happens if we respond two weeks later?"

If the answer is "not much impact, really," put it in the next cycle.

What's the process for force majeure like regulatory changes or security vulnerabilities?

Force majeure change process:

Force majeure types and responses:

TypeExampleResponse
Blocking regulationMust comply before GDPR effective datePause feature development, focus on compliance
Security vulnerabilityHigh-severity CVEIndependent emergency fix branch, don't mix with feature development
Third-party API changeVendor deprecates APIAssess impact scope, decide whether to pause or parallel process
Hardware/InfrastructureCloud provider ends supportInclude in tech debt handling, usually doesn't affect feature development

Key principle: Force majeure changes should be tracked independently—don't mix them into the original feature spec.

Is there a "fast track" for emergency changes?

Yes. But conditions must be met and process followed:

Activation conditions (at least one must apply):

  • [ ] Security vulnerability (CVSS ≥ 7.0)
  • [ ] Regulatory compliance deadline
  • [ ] Core functionality completely unusable
  • [ ] Committed customer timeline

Fast track process:

StepTimeDescription
1. Submit emergency requestImmediateExplain situation to PM Lead or Tech Lead
2. Impact assessmentWithin 30 minAssess impact on current development cycle
3. Authorization decisionWithin 1 hourPM Lead + Tech Lead jointly decide whether to activate
4. Mini-elaboration1-2 hoursMinimum necessary personnel for quick convergence
5. ExecutionAs neededMay require pausing or adjusting original schedule
6. Post-mortemAfter completionDocument change reason, impact, learnings

Costs of fast track:

Warning: If fast track usage exceeds once per month, this usually indicates:

  • Early convergence wasn't thorough enough
  • Stakeholders weren't sufficiently included
  • Or the project itself is too high-risk and needs re-evaluation
How do you distinguish "legitimate requirement evolution" from "inappropriate late-stage interference"?

Judgment criteria:

AspectLegitimate EvolutionInappropriate Interference
Information sourceNew data, user feedback, market changes"I just thought of this," "Boss said"
TimingRaised in post-release feedback cycleSuddenly inserted during development
ScopeClear boundaries, can be evaluated independentlyVague, constantly expanding
ProposerParticipant from original convergence meetingPerson who didn't participate in convergence
Decision processWilling to follow formal processWants to bypass process and change directly

Handling approach:

Practical phrasing:

"That's a great idea—let's record it. Since the team has already started executing based on our convergence decisions, I suggest we complete this version first, then evaluate it together in the next cycle after collecting feedback. That way we'll have more complete information to make the decision."

Core principle: Respect work already invested, but don't reject good ideas—put them at the right time for handling.

Will multi-level spec maintenance cost become a new bottleneck?

Reframe multi-level specs: This is tree structure, not document burden.

Core insight:

Traditional ViewCorrect View
7 spec levels = 7x maintenance costTrunk + Branches = Structural investment
Specs are "extra documents"Specs are "skeleton"
Maintaining specs vs writing codeWithout skeleton, leaves won't grow stable

Without API specs, AI-generated frontend and backend code won't automatically align. Without UX specs, AI-generated UI won't match design intent. "Multi-level specs" aren't document burden—they're structural investment for stable AI output.

How many spec documents does a medium-sized feature actually need?

Not every feature needs all 7 layers. The 7 layers represent maximum possible scope:

Feature TypeSpecs Actually NeededLayers
Pure backend APIHigh-level → API → Backend3 layers
Pure frontend adjustmentHigh-level → UX → Frontend3 layers
Full-stack featureHigh-level → UX → API → Frontend + Backend5 layers
Complex cross-platformFull 7 layers7 layers

More importantly: Specs are "generated," not "hand-written"

Traditional: Human writes high-level → Human writes UX → Human writes API → Human writes code
                      ↓                    ↓                 ↓                  ↓
                 (time-consuming)    (time-consuming)  (time-consuming)   (time-consuming)

AI Mode:    Human writes high-level → AI generates UX → AI generates API → AI generates code
                                            ↓                 ↓                  ↓
                                       Human reviews     Human reviews      Human reviews
                                         (fast)           (fast)             (fast)

Maintenance cost isn't "writing 7 documents"—it's "reviewing AI-generated content."

When requirements change, how many specs need synchronous updates?

Principle: Update from the highest affected level, regenerate downward.

Change frequency by layer:

LayerChange FrequencyNotes
Trunk (High-level spec)RarelyBusiness intent is stable once established
Branches (API/UX/Design)OccasionallyMainly adjusted during early development
Leaves (Implementation/Tests)FrequentlyBut regeneration cost is low (AI-generated)

Practical experience: Most changes only affect the "leaves" layer—no need to touch "trunk" and "branches."

Who ensures consistency between specs? Manual or automated?

Hybrid mode: Automated checks + Human judgment

Consistency TypeCheck MethodTools
API spec vs implementationAutomatedOpenAPI validation, CI checks
UX spec vs implementationSemi-automatedVisual regression testing + Design review
Terminology consistency across specsAI-assistedAI comparison + Human confirmation
Business logic consistencyManualSpec review meetings

Responsibility assignment:

Key principles:

  • Automate everything that can be automated (API contract validation)
  • Use AI to flag suspicious areas for what can't be automated
  • Final judgment rests with humans (PM/Tech Lead/UX Lead)
What simplification strategies exist if spec maintenance really becomes a bottleneck?

Diagnosis: First identify where the bottleneck is

SymptomLikely CauseSolution
"Writing specs takes too long"Not leveraging AI generationLet AI generate drafts, humans only review
"Too many specs to track"Over-granular layer divisionMerge related specs, reduce document count
"Specs are often outdated"Unclear update processDefine trigger conditions and owners
"Specs are inconsistent"Lack of automated checksImplement CI validation

Simplification strategies:

  1. Merge layers: Small features can merge UX + Frontend specs, API + Backend specs
  2. Skip non-essential layers: Pure bug fixes can just have high-level description + direct code changes
  3. Progressive refinement: Start with rough specs for rapid development, add detail after stabilization
  4. Spec templates: Build team templates to reduce starting-from-scratch cost each time

Final reminder:

If "writing specs" feels like a burden, it usually means:

  1. Not leveraging AI generation (should be reviewing, not writing)
  2. Or the feature doesn't need this many layers (over-formalization)

The purpose of specs is to make AI output more stable. If specs themselves become the bottleneck, they've lost their purpose. Pragmatically choose spec layers appropriate for the feature's complexity.

Anti-Patterns

1. AI as Decision Maker

Problem: Pushing decisions to AI instead of human judgment.

Correct Approach: AI provides options and surfaces trade-offs. Humans decide.

2. Skipping Mob Elaboration

Problem: Complex features go straight to implementation without multi-perspective refinement.

Correct Approach: Complex features must go through Mob Elaboration to produce high-level spec.

3. Treating Spec as Final

Problem: Treating Mob Elaboration spec as immutable.

Correct Approach: Specs are living documents. Hold mini-elaboration when issues arise.

4. Skipping Spec Branches

Problem: High-level spec jumps directly to implementation without UX/API/Design branches.

Correct Approach: Follow multi-level spec management, each branch produces its spec.

References