I design content systems that scale — structuring, connecting, and engineering documentation so it works for human readers, developer teams, and AI systems alike. 14 years across Actian, Adobe, ABB, and Aristocrat Technologies, spanning DITA migrations, taxonomy design, metadata governance, RAG pipelines, and Model Context Protocol (MCP) servers.
I treat documentation as a product — aligning information architecture, content modeling, analytics, and AI to measurable business outcomes.
Information Architecture — I design the structures that make content findable, reusable, and consistent at scale: taxonomy, metadata schemas, content models, navigation systems, and governance frameworks.
AI-Ready Content Systems — I engineer documentation corpora that LLMs can retrieve and reason over — applying chunking strategy, semantic tagging, and structured authoring principles so content performs in RAG pipelines, not just in browsers.
Docs-as-Code & CI/CD — I build and operate publishing pipelines (Jenkins, GitHub Actions, MkDocs) that treat documentation like software: version-controlled, validated, and automatically deployed.
Analytics-Driven IA — I connect GA4, BigQuery, and content-gap analysis to IA decisions — measuring what users can't find, then restructuring to fix it.
| What I improved | Result |
|---|---|
| Content discoverability | +45% |
| Organic search traffic | +50% |
| Duplicate / redundant content | −35% |
| API self-service success rate | +40% |
| Engineering onboarding time | −70% |
| Documentation build & publish time | −40% |
| Adobe HelpX users supported | 1M+ / quarter |
| Project | What it demonstrates |
|---|---|
| Knowlayer | Live service + writing on making enterprise content AI-ready — including deep-dives on chunking and knowledge graphs |
| knowledge-graphs-for-ia | Turns documentation into a knowledge graph with a working GraphRAG demo — IA modeling made executable |
| docs-style-guard | Automated writing-standards enforcement — turns a style guide into a check that runs on every change |
| docs-mcp | Foundational MCP server — exposes a documentation corpus, GA4 content gaps, and Jenkins CI status to Claude via natural-language tool calls. The base retrieval layer |
| knowflow | Evolution of docs-mcp — adds a RAGAS-style evaluation loop (relevance, faithfulness, recall) so you can measure retrieval quality, not just retrieve it. The full content-intelligence loop |
| information-architecture-playbook | IA principles, governance checklists, maturity model, and content-modeling templates |
Core IA — Taxonomy & ontology design · Metadata standards · Content modeling · Topic-based authoring · DITA · Single-source publishing · Navigation & findability · Governance frameworks
AI & Retrieval — RAG · Vector embeddings · Semantic search · Model Context Protocol (MCP) · Prompt engineering · LLM integration · ChromaDB · pgvector
Developer & API Docs — REST · GraphQL · OpenAPI/Swagger · Postman · Interactive sandboxes · Developer onboarding
Tooling & Engineering — Docs-as-code · Python · TypeScript · Jenkins CI/CD · GitHub Actions · MkDocs · Markdoc · AEM · FrameMaker
Analytics — Google Analytics 4 · BigQuery · Adobe Analytics · Content performance dashboards · SEO
| Role | Company | Period |
|---|---|---|
| Principal Information Architect | Actian | Apr 2024 – Present |
| Information Architect | Adobe | Sep 2021 – Apr 2024 |
| Senior Technical Writer / Information Architect | ABB | Aug 2018 – Sep 2021 |
| Senior Technical Writer | Aristocrat Technologies | Jun 2012 – Jul 2018 |
🎓 B.Tech, Aeronautical Engineering — R. V. College of Engineering, Bangalore
📜 Prompt Engineering: How to Talk to the AIs (2025) · UX Foundations: Information Architecture · Jenkins Essential Training · The Web Developer Bootcamp
Portfolio · LinkedIn · IA Playbook · pandey.bipin2@gmail.com