Shared literature, research code and experiments

1. Shared literature and private research

2. Connect an idea to a code workspace

3. Inspection coverage and change watching

4. Compare alternatives and generate implementation or ablation code

5. CPU checks and actual experiments differ

6. Run ablations locally or in your cloud environment

7. Approve changes and create a draft PR

8. Continue through strategy, daily reviews and ChatGPT

9. From an idea to code, downloads and publication

10. Multiple workspaces and input help

11. Editing ideas, attachments and when commits happen

Repository consultation, isolated checks and integration

Detailed filters and research notifications

Analysis continuity and ChatGPT

Synchronizing external discussion and code results

Start repository consultation

4. Continue across AI surfaces

1. Use ▾ beside the send button in either a new or follow-up request to choose: Answer in this work, Continue in AI chat, or Continue in ChatGPT.
2. Selecting a destination runs no AI. Answer in this work sends the request. Continue in AI chat prepares your final question, selected evidence and files in the consultation panel; review and send there to start.
3. Continue in ChatGPT prepares handoff text. Copy it into ChatGPT with LUNA connected. Copying alone neither transfers nor saves anything externally.
4. Reuse the same work and conversation for the same purpose. New work is created on actual send; switching a prepared request’s destination must not run it twice.
5. Only delivered and saved content and files are preserved. Check the receipt’s work ID, files and download links. Choosing a destination does not broaden private conversation access or sharing.

7. Core materials and AI drafts

1. Search and pin important sources in Materials & results. Pinning and unpinning do not copy, delete or change source access.
2. Private pins enter only your own AI context; team sources still require current source permissions. Attach relevant evidence and choose Ask AI to save a request on the same work.
3. Choose Save note to preserve a private memo without AI; it does not replace the current result. Waiting, running and failure reflect actual request state; saved stages remain preserved.
4. AI requests follow administrator policy and personal limits. Reading, saving notes and pinning make no new generation call.
5. Pins and AI drafts are not factual verification or researcher approval.

10. Find earlier analyses and results

1. Existing goals, code, reports and discussions retain their original IDs and permissions while being linked into one work list. Open work or search Materials & results for originals and downloads.
2. The current revision and latest saved checkpoint represent a conversation; earlier versions remain in detailed history. Distinct reports are not merged by matching titles.
3. If evidence is inaccessible, the owner may see only a preserved-result notice. Restore current connection and permissions before opening content or downloads.
4. Never infer or claim to have read blocked content. A classification-only change with identical content, version, connection and current access does not require regenerating saved results.

11. One work list and research map

1. Choose List or Research map in Research work. Selecting work opens the right panel. Use ↗ or Ctrl/⌘-click to open the same work on its own page with a stable URL. The default map groups results inside their owning work; Expand outputs reveals exact report and code-result cards.
2. Renaming work changes its display name without rewriting source titles, content, versions or evidence, or duplicating work. Distinct works are never merged by title.
3. Solid workflow/derivation links and dashed reference/validation links are both visible by default. Multiple origins, references and sections retain their exact report IDs and versions even when output cards are folded.
4. Counts distinguish the works, outputs and materials currently shown, not the total saved collection. Use the next work range or a focused neighborhood to navigate.
5. Renaming or reordering the list does not reposition the same works and relationships. Goal settings, literature, strategy analysis and specialized code tools remain available from that work’s settings or detail screen.
6. Source changes require deliberate evidence review and refresh. Disconnecting does not delete the source or earlier history.
7. Maps, search and opening a work URL call no AI and create no work or conversation. The panel and separate page use the same work, current permissions, conversation, results, files and history.
8. While drafting, use ↗ to open a new tab. Unsent text and selected files remain in the original tab. Open in research space returns to that work. Use the original tab to resume its search, map position and draft.

12. Trash and a new research cycle

1. Review the target and effects before moving work or a space to Trash. Saved conversations, outputs, attachments and external originals remain preserved.
2. A new cycle archives earlier work while retaining materials and members. Restore from Trash or previous cycles without automatically restoring work individually trashed earlier.
3. Related local pending or running requests stop, but a call already sent to an external provider cannot be guaranteed recalled. Restoration itself queues no AI.
4. Original automation policies remain preserved, so an enabled policy may execute at its next scheduled time after restoration.

13. Navigate quickly and inspect history

1. Switch between List and Map and sort by recent activity, creation, execution state, attention or title. Changing work loads its detail in place and retains the draft question for each work.
2. Open Records and filter All, Conversation, Results and versions, Executions or Links. An answer and its result are grouped.
3. A conversation started from an earlier report or selected passage retains its original thread. Load earlier records on demand.
4. No execution requested, generating and needs attention describe execution separately from saved outputs. Downloads require actually preserved files.

14. Save naturally from a conversation

1. Ask the AI consultation or ChatGPT: “Save this conversation and its results to the current research work.” LUNA prioritizes an explicit work, the bound conversation and a previous save receipt. Choose by title when several targets match, or preserve privately in the personal inbox before selecting a destination.
2. New work requires an explicit request; retrying the same request does not duplicate it. Review the destination, content and files before saving.
3. The personal inbox supports downloads and linking to existing work. Saving text makes no additional platform model call.
4. Files can be uploaded in resumable chunks up to 8 MB per bundle; larger materials may be saved as accessible source references. A source link is not a preserved binary copy.
5. Check the completed save receipt: uploading means only received parts are preserved. External messages and files that were never delivered are not automatically collected.
6. Team sharing and external publication retain separate scope reviews.

15. Full-width map and images

1. The map uses the full work area. Derivation and dependency relations guide its left-to-right layout, including independent work and loops.
2. Select a node for detail and return to the same map position. More offers PNG, JPEG and SVG exports of the currently loaded range, not a claim to cover every record.
3. No AI call is made.

16. Attach files and use code results

1. Use Add materials for files, images and platform evidence; paste links into your question. Upload up to 50 files totaling 100 MB through resumable chunks.
2. Originals are preserved while AI excerpts are prepared in the background. Preparation is not a full read of every original; extraction failures and text or image limits are shown separately.
3. Actually completed ChatGPT file transfers can be attached with the same permission checks. Missing code output has no download; execution history shows the failure.
4. Import preserved text code or a validated ZIP as a code changeset and inspect each diff. ZIPs are never executed or automatically installed.
5. Review repository, branch, baseline commit and changes before approving GitHub publication. Reconcile uncertain responses to avoid duplicate posts.

17. Keep existing work in My saved items

1. Star existing work, conversations or results to keep a shortcut in My saved items. This differs from a preserved copy of delivered conversation content and files.
2. Shortcuts reopen the same work and version; source permission revocation blocks content access. Web, AI consultation and ChatGPT use the same bookmarks and save receipts.

18. One library and pinned materials

1. Use All, Favorites and Saved conversations and files in one personal library. Old favorite URLs and folders remain valid.
2. Unstarring does not delete preserved originals. Materials and results initially shows pinned items; search includes all accessible materials.
3. Toggle the same pin to unpin and clear search to return to pins. Pinning does not expand source permissions.

19. Private work and team discussion

1. Click Only me on a work item to manage sharing. Review the exact body and selected files before sharing.
2. Earlier private discussions and personal memory are not shared automatically. Continue in team view to accumulate attributed discussion under the same canonical research work.
3. Sharing withdrawal, membership and source access are rechecked; private originals remain preserved. ChatGPT uses the same work ID and current permissions and reflects only delivered content.

20. Add schedules and export maps

1. Use Add to choose an event, GitHub task or report request and then create or link existing. Creation opens the standard form with optional AI drafting.
2. Linking does not duplicate the original or create an external item. Select one image format before downloading a map.
3. Dashed reference and validation relations identify evidence or verification links, separately from derivation order.

24. Refine a request through conversation

1. Write a few sentences in New research or Continue this work, then select sources and files in Add materials. Put links in the text. Both composers use the same refinement, attachment and destination controls.
2. Refine request opens a conversation on the right. It checks the current request, work and selected evidence, suggests a research kind and identifies missing conditions. It reuses known conditions and asks one or two important questions at a time.
3. A choice fills the reply box. Add or edit details, then choose Send reply. You may leave a condition undecided or ask for a recommendation. Repository candidates are authorized connection metadata, not proof of write permission or server availability.
4. Preview the prepared request and conditions, distinguishing your input, existing evidence, AI suggestions and unknowns. The composer changes only when you choose Apply to request. Undo restores your earlier input.
5. Applying does not execute research. Edit the result if needed, choose this work, AI consultation or ChatGPT from the destination menu, then send. You may also skip refinement and send directly.
6. Closing and reopening preserves the saved conversation. On mobile, closing returns to the original composer. An older response never automatically overwrites text you changed.
7. Starting refinement and sending each additional reply request one personal AI attempt each. Page reads, saved conversation reads and applying use no AI. Closing the panel does not cancel an already accepted AI job.
8. Administrator policy, remaining allowance, provider and time limits apply. Failures retain input and conversation without automatic paid retries. Up to 50 files totaling 100 MB are supported; uploading is distinct from analyzing all original content.
9. Selecting a saved suggestion only fills the request and evidence; Save memo stores a record without AI. Team requests use only currently authorized shared evidence.

25. Continue request drafts and results in ChatGPT

1. You can hand off a rough request without finishing refinement on the website. Choose Continue in ChatGPT from the destination menu for either a new request or a follow-up.
2. The handoff includes the latest composer text, selected sources, prepared attachments and existing work, conversation and result versions. An applied refinement also carries the same request session and accepted revision. Preparing and copying the handoff calls no AI, creates no work and transfers nothing externally.
3. Paste the text into ChatGPT with LUNA connected and check that the host exposes the needed tools. Ask: “First clarify the request by asking for missing conditions; proceed after we settle it.”
4. Preserve the same request session, work and evidence versions when saving a request refined in ChatGPT. Saving externally prepared requests and results does not rerun platform AI. Draft storage, applying a request and executing research remain separate actions.
5. Ask: “Save the discussion delivered so far and the generated files to this work, then show download links.” The platform preserves only conversation content and files actually delivered through its tools, not the entire external chat automatically.
6. A filename or temporary link is not proof of preservation. Check the receipt destination, file list, downloads and readiness. Use web upload if the host cannot deliver files.
7. Confirm a destination for new work and retain the existing work, conversation and exact result version for follow-ups. Continue through the stable work link; include the exact result or version link when reviewing a specific output. Opening a link does not save drafts, external conversations or files. Private conversations and evidence do not become team-shared automatically. Publication and paid GPU execution have separate scopes.

33. Automatic recommendations and usage

1. Open space settings in Research team to turn automatic research recommendations on or off. Existing and new spaces default to on, preparing suggestions from existing reports and consultations.
2. Opening pages, reading suggestions, searching and sorting make no new AI call. Relevant saved results refresh recommendations in the background; the first view shows saved suggestions.
3. Additional automatic AI enrichment defaults to zero attempts. Set a daily cap if needed; the space owner’s allowance and administrator policy also apply. Changing settings never resets consumed usage.
4. Turning off stops subsequent automatic recommendation generation while preserving existing suggestions and history. Pending work rechecks the setting and permissions immediately before execution.
5. Private consultation or source recommendations are not automatically shared with other members. Changed or revoked evidence requires revalidation. Preparing a suggestion does not execute research, prove success or constitute human review.

34. Compact cards and work search

1. Open titles in the Projects and Research spaces sections of a grant or project. The directory uses the same cards without repeating a parent already shown.
2. Work and result counts use currently accessible entries. A work’s conversation, report and execution history are not counted as separate work. A + marks a bounded count.
3. Choose List or Map and type to search Research work. Search waits for composition to finish; Enter searches immediately. Use the compact sort menu for recent activity, creation, status and other criteria.
4. Searching and changing views preserve the draft and selected work. Renaming work or adjusting map relations retains the same work ID and history.

35. Research kinds, requests and results

1. A research kind describes the activity: planning, literature review, model design, experiment design, code implementation, training, validation, reproducibility, analysis, discussion, writing, reporting or scheduling. Reports, code files and literature tables are result formats.
2. AI proposes a kind during refinement. Direct requests receive an initial classification; use Change research kind in the work menu to correct it. Manual choices are never overwritten automatically.
3. Every work uses Request, Results and Continue this work, in that order. Expand long requests and open or download results. Find initial requests, conversation, execution and earlier versions in History under the work menu.
4. Changing kind preserves sources, results and permissions; it does not authorize server execution or GitHub writes. Distinguish a training plan from actual training and a validation plan from completed validation.

36. Continue earlier goals and literature

1. Earlier paper-goal settings and discovered literature can be organized as a separate preparation work. Read its research objective and conditions as the request, and open the literature bundle as its result.
2. The literature result includes search and observation history, selection state and sources. Open or download it, distinguishing reorganized existing records from new AI analysis.
3. Earlier strategy and detailed-report IDs, conversations, reports, citations and downloads remain intact. Linking preparation as the logical starting point never invents historical runs or conversations.
4. Earlier settings and literature URLs lead to the preparation work. Its automatic execution settings retain the earlier policy; reorganization does not resume stopped AI or incur additional AI charges.
5. Renaming work never creates another map node for the same work. Work and result artifacts remain distinct; expand result versions when needed.