Guides
Guides to decision records & chat-history extraction
Practical references for the two moments every senior engineer hits: before the stale-docs problem (when you're adopting an ADR template) and after (when the reasoning is buried in six months of AI chats).
ADR templates
- ADR template in Markdown — copy-paste ready
- The Nygard ADR template (2026 edition)
- ADR template for GitHub repos
- The ADR GitHub Action — a CI pipeline for architecture decision records
- ADR review checklist — what to look for before merging an architecture decision record
- ADR numbering scheme — padding, gaps, and collision recovery
- ADR status template — format, fields, and the lifecycle beyond Accepted
- ADR storage format comparison — Markdown vs AsciiDoc vs Notion vs Confluence vs SharePoint
- Log4Brains ADR — generate an architecture decision record website from your codebase
- ADR tooling comparison — adr-tools vs Log4Brains vs adr-log vs hand-rolled
- TOGAF ADR template — mapping decision records to Phase H and the Architecture Repository
- Architecture Board charter template — scope, cadence, decision rights, and the Governance Log boundary
- ADR template for Confluence
- ADR template for Notion
- ADR template in Linear — Documents, custom properties, and the graduated handoff
- ADR template for Jira — custom fields, Confluence integration, and the graduated handoff
- ADR template for Azure DevOps — Repos, Wiki, and Work Items
- arc42 architecture decision record template
- ISO 25010 quality attributes in ADRs — tagging decisions for architecture governance
- ADR change management template — linking ADRs to ITIL and CAB approvals
- ADR template in Miro — whiteboard sessions and the diagram handoff
- Mermaid diagrams in ADRs — sequence diagrams, C4 models, and flowcharts in Markdown
- MADR (Markdown ADR) template explained
- GitHub Discussions as an RFC surface — proposal-to-ADR workflow
- VS Code ADR template — extensions, snippets, and workspace setup
- JetBrains ADR template — Live Templates, File Templates, and IntelliJ ADR workflow
- ADR template for Microsoft Teams — Loop, Planner, and channel-based review
- Engineering principles template — ADR vs principle, the promotion path, and the standing-rule repository
Examples & practice
- Architecture decision record example: Postgres vs MongoDB
- Architecture decision record template
- How to document architecture decisions (without your team revolting)
- When to write an ADR (and when you shouldn't)
- How to update an ADR (without breaking the audit trail)
- ADR supersession pattern — when to supersede, when to annotate, and how to stay bidirectional
- ADR adoption guide — how to introduce architecture decision records to a resistant team
- ADR lightweight template — LADR, Y-Statements, and the minimum viable format
- ADR vs Design Decision Record: what's the difference?
- ADR vs RFC — when to use each and how they work together
- The RFC-to-ADR process — lifecycle stages, review ceremony, and section mapping
- ADR from meeting minutes — capturing synchronous decisions as architecture records
- Retrospective ADR template — writing decision records for pre-adoption architecture choices
- When to retire an ADR — deprecation, supersession, and the never-delete rule
- ADR template for squad-sized teams — scaling the practice from 3 to 50+ engineers
- Decision log template (free, copy-paste)
- ADR vs decision register — scope, mutability, and when you need both
- ADR template in Obsidian — Dataview queries, auto-numbering, and the supersession Canvas
- Architecture decision record best practices — what actually works after year one
- ADR directory structure in a monorepo — per-service vs central, numbering, and CI
- ADR decision authority matrix — who writes, reviews, and approves
- ADR governance patterns — async teams, decision authority, and the RFC announcement loop
Chat-history extraction
- How to export your ChatGPT history (2026 guide)
- How to export your Claude conversations
- Gemini conversation export — how to get your Google Gemini chats out (2026)
- ChatGPT conversations.json format — field reference
- Claude conversation export format — field reference
- How to search your ChatGPT history (the four levels)
- How to search your Claude conversations (the four levels)
- ChatGPT export not working? Eight failure modes and how to recover
- Claude export not working? Eight failure modes and how to recover
- Claude Team workspace export — admin DSAR path, member scope, and Project isolation
- ChatGPT Team export — differences from Plus, workspace admin flow, and the Compliance API
- ChatGPT Memory export — where your memories live in the data download (2026)
- ChatGPT Custom GPTs export — conversations vs configurations, what's included and what's not
- Perplexity conversation export — how to save your AI research history (2026)
- Gemini Workspace export — Google Vault, admin console, and enterprise data portability (2026)
- Uploaded files in ChatGPT exports — what's included, what's missing, and how to recover them
- ChatGPT shared links — what persists, what expires, and how to archive conversations (2026)
- ChatGPT web search in conversations.json — tether content types, what's stored, and how to extract citations (2026)
- Can you export OpenAI Playground conversations? No — and here's why
- Can you export Claude API conversations? No — and here's why
- How to convert your ChatGPT export to Markdown
- How to convert your Claude export to Markdown
- How to export your Claude Artifacts (and why they're the decision layer)
- How to export a Claude Project (system prompt, knowledge base, all conversations)
- ChatGPT Projects export — custom instructions, files, and conversation routing
- How to extract decisions from your ChatGPT chats
- How to extract decisions from your Claude conversations
- ChatGPT voice mode in the data export — transcripts, what's missing, and how to process them
- Perplexity Spaces export — what team workspace data is recoverable (2026)
- Microsoft Copilot export — how to retrieve conversation history (2026)
- GitHub Copilot Chat export — why there isn't one, and where your history actually lives
- Perplexity API vs product — what's stored, what's stateless, and what you can export
- Gemini Deep Research export — reports, citations, and what appears in Google Takeout
- ChatGPT image generation in the data export — DALL-E prompts, CDN URLs, and what expires
- Cursor AI chat export — what's stored, what's lost, and how to capture decisions
- ChatGPT Canvas export — what's in your ZIP and how to extract documents
- Google NotebookLM export — what you can save and what you can't
- Windsurf AI chat export — what Codeium stores, what's lost, and how to capture decisions
- Zed AI chat export — what Zed stores, what's lost, and how to capture decisions
- Claude Projects memory and Knowledge Base export — what survives and how to back up before deleting
- Perplexity Deep Research export — saving reports before they disappear (2026)
- Microsoft 365 Copilot export — Purview eDiscovery, interaction logs, and data retention (2026)
- Slack decision threads — capturing architecture decisions from Slack channels (2026)
- Notion AI export — what's saved, what's lost, and how to archive AI-assisted content
- Claude Desktop export — local storage, session architecture, and data portability
- Gemini Advanced export — Google One subscription, Gems, and what changes vs standard Gemini
- Grok conversation export — xAI chat history, data portability, and export options (2026)
- ADR template for Backstage — TechDocs integration, MADR format, and catalog annotations
- Amazon Q Developer export — chat history, session storage, and architecture decision capture (2026)
- ChatGPT o1 and o3 export — what appears in conversations.json and what's hidden
Try the product
WhyChose extracts decisions from your ChatGPT/Claude exports and emits ADR-shaped records. Run the open-source extractor locally, or join the waitlist for the hosted product with team sharing and Notion/Linear export.