Skip to content

Improvement Proposals

This chapter presents actionable proposals derived from the Context Engineering analysis. Each proposal addresses specific challenges identified from cross-team feedback and provides concrete implementation guidance.

Purpose: Transform context engineering insights into implementable improvements that teams can adopt incrementally.

Proposal Framework

All proposals in this chapter follow a consistent structure:

Each proposal includes:

  • Problem Statement - The specific issue identified from team feedback
  • Proposed Solution - Architecture and approach to address the problem
  • Implementation Roadmap - Phased rollout with concrete deliverables
  • Success Metrics - Measurable outcomes to track effectiveness
  • CLAUDE.md Integration - How to document the solution for AI consumption

Proposal Categories

Process Proposals

Establish ongoing practices for maintaining context quality.

ProposalDescriptionStatus
AI-First Decision MakingSystematic framework for evaluating AI as primary executor at every decision pointDocumented
AI-DLC Mob ElaborationAI-augmented development life cycle with collaborative elaboration sessionsDocumented
Continuous Context CleanupFramework for identifying, documenting, and migrating deprecated patternsDocumented
Spec ExtractionReverse-engineer specifications from existing implementations as "existing-fact" contextDocumented

Infrastructure Proposals

Build foundational systems that improve AI code generation accuracy.

ProposalDescriptionStatus
Design SystemUnified design system architecture for cross-platform consistencyDocumented
shadcn/ui FoundationAdopt shadcn/ui as the base for Web design system implementationDocumented
Agent-Friendly Knowledge BaseMigrate from Confluence to Git-based Markdown for AI agent accessDocumented
Global Requirement StoreProduct-oriented centralized requirement repository for cross-platform consistencyDocumented
Tech Radar & RoadmapsInteractive tech radar visualization and roadmap management for technology governanceDocumented
Internal Spec PlatformCentralized specification hosting with date-based versioning and multi-product supportDocumented
Claude Skills AdoptionEncourage teams to create, share, and maintain Claude Code Skills for reusable AI workflowsDocumented

Standards Proposals

Define terminology and documentation patterns for AI comprehension.

ProposalDescriptionStatus
Ubiquitous LanguageCross-team terminology standards and domain glossaryDocumented
Multi-Product Spec ManagementHierarchical specification management for multi-product organizationsDocumented
Frontmatter Spec CoordinationStandardized YAML frontmatter schema for coordinating markdown documents across spec systemsDocumented
CLAUDE.md StandardsTemplates and best practices for AI guidance filesPlanned

Proposal Summaries

AI-DLC Mob Elaboration

Problem: Traditional SDLC approaches fail to leverage AI at critical decision points. Sequential handoffs between PM, RD, UX, and Architect create knowledge silos and miss edge cases that surface late in development.

Solution: Introduce Mob Elaboration sessions where all stakeholders collaborate simultaneously with AI:

  • PM, RD, UX, Architect, and AI participate together
  • AI surfaces edge cases, checks consistency, generates documentation
  • Complete spec produced in single session
  • Real-time synthesis across perspectives

Key Insight: Requirements quality improves dramatically when diverse perspectives challenge assumptions simultaneously. AI adds a tireless participant that can instantly surface gaps and maintain comprehensive documentation.

Read full proposal

Continuous Context Cleanup

Problem: Context pollution accumulates as codebases evolve. Legacy patterns, deprecated frameworks, and inconsistent naming confuse AI code generation.

Solution: A five-phase continuous cycle:

  1. Identify - Detect pollution through AI output review
  2. Document - Update CLAUDE.md with current standards
  3. Mark - Add deprecation markers to legacy code
  4. Migrate - Incrementally move to modern patterns
  5. Verify - Monitor AI accuracy and iterate

Key Insight: Context cleanup should be integrated into the development workflow as an ongoing practice.

Read full proposal

Design System

Problem: Component duplication is one of the most common AI code generation failures. AI creates new UI components instead of reusing existing ones because components are scattered, undocumented, and inconsistently named.

Solution: Establish a unified design system with:

  • Centralized component directory with searchable index
  • Cross-platform component mapping (Web, iOS, Android)
  • Design tokens for consistent styling
  • AI-optimized documentation with hints and usage guidelines

Key Insight: AI cannot "discover" unorganized components. If they aren't in expected locations with clear documentation, they effectively don't exist to AI.

Read full proposal

shadcn/ui Foundation

Problem: Traditional component libraries (Ant Design, Material UI) create challenges for AI:

  • Black-box implementations AI cannot understand
  • Limited customization requiring CSS override hacks
  • Version upgrades that break learned patterns

Solution: Adopt shadcn/ui's "copy-and-own" model:

  • Full code ownership - modify freely without upstream dependencies
  • AI-accessible implementation - code lives in your project
  • Custom registry - share domain components across projects
  • MCP integration - AI-powered component discovery

Key Insight: shadcn/ui transforms UI development from dependency consumption to infrastructure ownership, enabling both human and AI developers to work with fully accessible code.

Read full proposal

Agent-Friendly Knowledge Base

Problem: Traditional knowledge systems (Confluence, SharePoint, Google Docs) are designed for human browsing, not machine consumption:

  • Proprietary formats AI cannot parse
  • No Git integration for version correlation
  • Rich text that breaks AI parsing
  • Permission complexity blocking agent access

Solution: Migrate to Git-based Markdown knowledge system:

  • Plain Markdown with structured frontmatter
  • Version control as source of truth
  • MCP resource provider for AI access
  • Semantic search and relationship graphs

Key Insight: Knowledge systems designed for human browsing actively obstruct AI agents. Making knowledge machine-readable while remaining human-editable enables agent collaboration.

Read full proposal

Global Requirement Store

Problem: Requirements fragmented across platform-specific documents lead to implementation divergence. Each team (Web, iOS, Android, Backend) interprets the same PRD differently, and AI agents only see their platform's interpretation, causing:

  • Inconsistent feature implementations
  • Missing edge cases on some platforms
  • Conflicting API contracts
  • Redundant specification work

Solution: Establish a centralized, product-oriented requirement repository that feeds into existing multi-level spec systems:

  • Product-centric organization (requirements grouped by product, not platform)
  • Single source of truth with platform-specific supplements
  • API-first contracts defined alongside requirements
  • AI-native format with structured frontmatter metadata
  • Version correlation linking requirement changes to implementation PRs
  • Integration with spec systems like OpenSpec (changes -> specs -> archive)

Key Insight: The Global Requirement Store operates at the "What" level - defining product requirements. It feeds into spec systems like OpenSpec that operate at the "How" level - tracking implementation proposals, current state, and history. This multi-level integration provides complete traceability from requirement through proposal to deployed spec.

Read full proposal

Ubiquitous Language

Problem: Terminology fragmentation causes AI code generation failures. When different teams use different terms for the same concept (camera vs device vs channel), AI produces inconsistent code requiring manual correction.

Solution: Establish cross-team terminology standards:

  • Domain glossary with canonical term definitions
  • Legacy term mapping for migration guidance
  • Platform-specific naming conventions
  • Validation tooling for enforcement

Key Insight: AI agents learn from code patterns. If the same concept has multiple names across the codebase, AI will perpetuate that inconsistency. Ubiquitous language is foundational for reliable AI code generation.

Read full proposal

Multi-Product, Multi-Level Spec Management

Problem: Current AI development frameworks assume single product, single team environments. Multi-product organizations face challenges where AI agents lack context about organizational standards, miss product-specific constraints, and cannot detect conflicting specs across product boundaries.

Solution: Establish a hierarchical specification management framework with five levels:

  • Level 0: Organization principles (always applicable)
  • Level 1: Product specs (product-specific constraints)
  • Level 2: Feature specs (what to build)
  • Level 3: Platform specs (how to build per platform)
  • Level 4: Implementation specs (detailed design)

With cross-cutting concerns handled via shared domains, API standards, design systems, and security policies that span all products.

Key Insight: Specifications should cascade from organization-wide principles to product-specific implementations while maintaining traceability. Lower levels inherit from higher levels (not copy), and overrides require explicit documentation with justification. This enables AI agents to navigate the full context hierarchy when generating code.

Read full proposal

Frontmatter-Based Spec Coordination

Problem: Markdown documentation across organizations lacks standardized metadata. Each team invents different frontmatter fields, relationships exist only in prose, and AI agents cannot build document graphs without parsing entire content.

Solution: Establish a standardized YAML frontmatter schema for all specification documents:

  • Required identity fields (id, title, type, status, version, owner)
  • Explicit relationship declarations (inherits, depends_on, related, cross_product_refs)
  • Override tracking with justification requirements
  • AI guidance fields for context prioritization
  • JSON Schema validation in CI pipelines

Key Insight: Markdown frontmatter is the natural coordination layer for specification documents. When standardized, frontmatter becomes a queryable graph of relationships, enabling AI agents to traverse specifications, detect conflicts, and maintain consistency without proprietary tooling.

Read full proposal

Tech Radar & Roadmaps

Problem: Technology decisions scattered across wikis, spreadsheets, and tribal knowledge lead to duplicated evaluation efforts, inconsistent adoption, and poor visibility into the organization's technical direction.

Solution: Build Tech Radar and Roadmap capabilities in the internal developer portal:

  • Interactive radar visualization with Adopt/Trial/Assess/Hold rings
  • Four quadrants: Languages & Frameworks, Tools, Platforms, Techniques
  • Technology proposal and voting workflow
  • Strategic roadmap management with timeline views
  • Historical tracking to compare radar changes over time

Key Insight: A unified Tech Radar provides the single source of truth for "what technologies should we use" and eliminates duplicated technology evaluations across teams.

Read full proposal

Internal Spec Platform

Problem: Organizations managing multiple products face fragmented specification access. Specs are scattered across repositories, have no versioning for audit trails, lack cross-product visibility, and force AI agents to re-fetch and re-parse every session.

Solution: Build a centralized specification platform with date-based versioning:

  • URL structure: https://spec.{company.domain}/{date}/{product-id}/{spec-type}/specs/{spec-id}
  • Multiple spec types: func, ux, api, infra (follows OpenSpec structure)
  • Date versioning over semver (objective, audit-friendly, multi-product sync)
  • Version aliases: /latest, /head, /{date}
  • Respects OpenSpec's flat capability naming convention
  • Git-based resolution (no storage duplication)
  • MCP integration for AI agent access

Key Insight: Date-based versioning fits specification management better than semantic versioning. "Show me 2024-09-15" is objective and auditable, while "which version was live in Q3?" requires interpretation. Same date across products means same snapshot, eliminating version alignment pain.

Read full proposal

Reverse-Engineering Spec Extraction

Problem: Legacy codebases lack structured context. AI agents re-explore the same code every session, wasting context windows. Institutional knowledge is locked in implementations without documentation.

Solution: Reverse-engineer specifications from existing code to create "existing-fact" context:

  • Four-layer extraction methodology (Boundaries, Structure, Behaviors, Edge Cases)
  • Existing-fact specs distinct from forward-looking requirements
  • AI-assisted extraction with human validation
  • Confidence levels indicating trustworthiness
  • 10-20x context compression vs raw code

Key Insight: Specifications extracted from implementations serve as compressed, authoritative context. A well-written spec is 5-20x smaller than the code it describes, dramatically reducing context window usage while preserving essential knowledge.

Read full proposal

Implementation Priority

  1. Start with Continuous Context Cleanup - Establishes the ongoing process
  2. Add Design Tokens - Foundation for consistent styling
  3. Implement shadcn/ui - Modern component architecture
  4. Define Ubiquitous Language - Cross-team terminology alignment

Quick Reference

Which Proposal Addresses Which Problem?

ProblemProposal
Requirements incomplete, edge cases missedAI-DLC Mob Elaboration
Knowledge silos between PM/RD/UX/ArchitectAI-DLC Mob Elaboration
AI creates duplicate componentsDesign System
AI uses deprecated patternsContinuous Context Cleanup
Component library upgrade breaks codeshadcn/ui Foundation
AI hardcodes color valuesDesign System
AI can't access Confluence specsAgent-Friendly Knowledge Base
Requirements scattered in platform-specific docsGlobal Requirement Store
Inconsistent feature implementations across platformsGlobal Requirement Store
Inconsistent naming across teamsUbiquitous Language
AI doesn't know project conventionsCLAUDE.md Standards (planned)
AI lacks org-level contextMulti-Product Spec Management
Specs don't cascade across productsMulti-Product Spec Management
No spec inheritance or override trackingMulti-Product Spec Management
Inconsistent frontmatter across docsFrontmatter Spec Coordination
AI cannot discover document relationshipsFrontmatter Spec Coordination
No validation of document referencesFrontmatter Spec Coordination
Legacy code has no documentationSpec Extraction
AI re-explores same code every sessionSpec Extraction
Context window wasted on raw codeSpec Extraction
Institutional knowledge locked in implementationsSpec Extraction
Specs scattered across repositoriesInternal Spec Platform
No spec versioning for auditsInternal Spec Platform
AI re-fetches specs every sessionInternal Spec Platform
Cross-product specs not discoverableInternal Spec Platform

Team-Specific Entry Points

TeamStart With
All TeamsAI-DLC Mob Elaboration for new features, Continuous Context Cleanup for existing code
Web Frontendshadcn/ui Foundation
Mobile (iOS/Android)Design System - Cross-platform mapping
BackendContinuous Context Cleanup - Pattern documentation

Success Metrics

Track these metrics across all proposals:

MetricTargetHow to Measure
AI first-time accuracy>80%Track prompts requiring re-generation
Component reuse rate>90%Audit AI-generated PRs for new vs existing components
Deprecated code ratio<20%grep -r "@deprecated" vs total files
Design token adoption100%grep for hardcoded color/spacing values
Cross-platform consistencyHighVisual comparison audit

References