Observed Signal · Jun 26, 2026 · How-to Guide · Source: UX Collective · Impact: 2/5 · Sentiment: Positive
Use identity files to stop re-explaining Claude
The author describes a practical workflow to give Claude a persistent, workspace-level identity so it remembers who you are across sessions. By creating four markdown "identity files" (about-me.md, principles.md, anti-patterns.md, voice-samples.md) that Claude reads before every response, the system reduces repeated explanations and improves collaboration. The identity files are authored from existing materials, consolidated over time by Claude, and updated via periodic scans so corrections and patterns are incorporated automatically. The playbook and example files are shared in a Google Drive folder; the approach is positioned as a quick (an afternoon) setup that compounds into noticeably better multi-session behavior.
Practical, reproducible workflow that improves multi-session LLM collaboration and memory; useful to teams adopting conversational AI but not industry-shifting.
Track claude.ai Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Author switched from ChatGPT to Claude and experienced repeated re-explaining across sessions.
- Claude, as used in the author’s workflow, starts each session from zero and does not carry memory between chats.
- The author created a workspace-level identity layer composed of four markdown files: about-me.md, principles.md, anti-patterns.md, and voice-samples.md, which Claude reads before every response.
- The identity files are synthesized from existing materials, can be created with a ~30–45 minute interactive session, and are consolidated/updated over time by Claude plus a weekly scan.
- The author published a Cowork identity layer setup playbook and scrubbed example files in a Google Drive folder.
Connected Companies & Entities
4 Entities mapped“Every session, Claude starts from zero. It doesn’t carry memory between chats....”
“They live at the workspace level, not inside any project, which means they follow you everywhere: into every project, every Figma session, e...”
“Get Sean Filiatrault’s stories in your inbox. Join Medium for free to get updates from this writer....”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Tool and Workflow to Prevent Claude Context Pollution
The author describes encountering "context pollution" when using Claude with a single repository of evergreen notes that caused unrelated session context to leak into conversations. To solve this, they use Claude Code's --system-prompt-file option and a small TypeScript CLI (ctx / npx @nbaglivo/ctx) that reads markdown files with YAML frontmatter tags, merges selected files plus global notes into a temporary .claude-context.md system prompt, and passes it to Claude. The generated file is ephemeral and gitignored. The workflow includes a feedback loop where Claude helps update source context files, and the author notes token-count/cost tradeoffs when including large system prompts.
Claude's Hidden Features Transform Workflows
This article surveys lesser-known capabilities of Claude beyond simple chat: a very large context window for uploading long documents and codebases; 'Artifacts' that produce interactive outputs (dashboards, mini web apps, diagrams); persistent 'Projects' workspaces that keep context, files, and custom instructions; a Model Context Protocol (MCP) that allows Claude to interact with external tools, APIs, databases and local systems; and Connectors that link Claude to platforms like GitHub, Google Drive and Slack. The author highlights Claude's strengths in long-form reasoning and more natural writing, arguing these combined features shift Claude from a transient chatbot toward a collaborative workspace and productivity layer.
How to Build High-Performing Claude Projects
A Dev.to how-to post describes a tested 6-part blueprint for configuring Claude Projects so they act like ‘‘customized AI employees’’ rather than labeled chat windows. The author reports three weeks of experimentation and presents six mandatory components (Identity, Rules, Process, Output Format, Knowledge Files, Onboarding Message), a recommended set of five focused projects (content, research, communication, strategy, code), and a reusable system-prompt template. The guide emphasizes uploading persistent knowledge files (style guide and audience profile required), stricter rules/processes to avoid vague prompts, and a short onboarding message to activate context. The author claims the setup takes about 45 minutes and can reduce editing time by ~90%, freeing an estimated six workweeks per year.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.