Threads¶
A thread contains a research question, context, decisions, plans, experiments, reports, and follow-up messages. Folders organize threads without changing their contents.
Thread boundaries¶
A thread can contain multiple plans and experiments. Other threads remain separate unless they are attached as context.
What a thread contains¶
A thread can contain:
- the original question and follow-up messages
- files, repositories, papers, datasets, models, and earlier work attached as context
- questions from Silico and the answers you provided
- plan drafts and revisions
- experiments and their current state
- reports, including diagrams and interactive views
- a codebase shared by experiments in the thread
- interpretation, competing explanations, and follow-up ideas
Context stays with the message that introduced it.
Context stays explicit across threads¶
Experiments in the same thread can build on that thread's earlier work. Other threads remain separate unless you attach one of them, or one of their reports, to the message that needs it.
Attached cross-thread context is read-only. Work in the new thread does not modify the source.
Threads, plans, and experiments¶
| Purpose | |
|---|---|
| Thread | Preserves the research question, reasoning, decisions, and continuity between pieces of work. |
| Plan | Describes proposed work before it runs, including the goal, inputs, method, controls, and expected output. |
| Experiment | Preserves the execution record and evidence after a plan launches. |
| Reports | Communicates durable outputs from that work. |
Launching an approved plan creates an experiment. Its reports return to the thread, where you can interpret the result and decide what question should come next.
Summary and Timeline¶
The thread has two views:
- Summary shows the current synthesis, active work, and recent reports.
- Timeline shows plans, experiments, decisions, and reports in order.
Open Summary for the current synthesis and Timeline for the chronological record.
The thread codebase¶
A thread codebase is shared across related experiments. Each experiment works on an isolated branch, and code can be merged back into the thread codebase.
When exploratory runs have copied and modified the same model, loader, or evaluation module, ask Silico to consolidate the relevant experiment EIDs. Silico inventories the overlap, creates a maintenance Task that extracts a tested shared API into the thread codebase, and keeps the old experiment directories as provenance. Merge that Task before starting runs that should import the shared module.
Use the code icon to browse files and history or download an archive. Ask Silico to push reusable code to GitHub as a draft pull request.
Continue, fork, or start a new thread¶
Continue to retain the existing thread context.
Use Fork to branch from a specific completed response. The fork is independent and excludes later source turns.
Start a new thread without existing thread history. Attach earlier work when the new thread requires it.
Sharing and continuation¶
Copy the thread link to share the full, read-only research record.
Continuing creates your own thread with the source attached as context. It does not grant private credentials or compute access.
See Start a thread for the practical workflow and Share reports for access boundaries.