Files

david.delagneau 1ad707373a Add daily logs and templates for project fidelity

- Created daily log entries for May 13, 14, 18, 19, 20, and 21, capturing work done, findings, and next steps.
- Established a daily logs index for easy navigation of daily notes.
- Developed templates for daily logs, decisions, meeting notes, people, systems, and work items to standardize documentation.
- Introduced base files for filtering and displaying various types of project knowledge, including daily notes, decisions, people, systems, work items, and workstreams.
- Added maps for current work, fidelity apps, and fidelity domain to enhance project navigation and context.

2026-05-21 12:28:07 -06:00

2.0 KiB

Raw Blame History

Security And Privacy

AI Workspace is designed for local-first, auditable context management. Treat it as a companion workspace that may contain sensitive project metadata and communication evidence.

Rules

Do not commit secrets, tokens, cookies, API keys, headers, or session IDs.
Keep connector credentials in ignored .env files.
Keep raw evidence outside canonical project memory until curated.
Keep MCP read-only unless a write tool has explicit safety rules.
Treat generated indexes as local artifacts because they may contain snippets from project notes.
Prefer local services for corporate or confidential projects.

Ignored Local State

Examples of local-only data:

.aiw/runtime/
.aiw/indexes/
workspaces/*/inbox/mattermost-mirror/
scripts/*/.env

Cloud Memory Systems

Tools such as mem9 or managed vector stores can be useful, but they introduce a data boundary.

Before enabling them for a project, decide:

what data may be stored;
whether cloud storage is allowed;
whether self-hosting is required;
who can inspect/delete memories;
what happens when cloud memory conflicts with Markdown.

Default recommendation:

Use cloud memory only for non-sensitive preferences unless a project policy approves broader use.

MCP Safety

MCP clients may let models invoke tools automatically. For that reason, workspace MCP tools should stay read-only by default and return bounded, source-attributed context.

If future MCP write tools are added, require:

explicit user intent;
narrow target paths;
clear diffs or summaries;
no secret exposure;
easy audit through git.

Before sharing or open-sourcing a reusable version:

Remove or isolate project-specific profile data.
Confirm ignored inbox/runtime files are not tracked.
Replace real profile examples with sanitized examples.
Keep reusable architecture docs in docs/ and core/.
Keep confidential project knowledge in private profile/workspace data.

2.0 KiB Raw Blame History