Shrink the always-on prompt
Keep only universal behavior, privacy, and approval invariants. Move integration, meeting, document, routine, and tool procedures behind existing on-demand mechanisms. Target: no more than 4,000 tokens.
Make every model prompt a small, request-specific projection. Keep the full capability surface, but reveal tools, procedures, and state only when the turn needs them.
Treat model context as a disposable view of durable system state, not as the system of record.
The direction matches current guidance from Anthropic and OpenAI: keep a small stable core, defer large tool catalogs, and retrieve detail just in time.
Keep only universal behavior, privacy, and approval invariants. Move integration, meeting, document, routine, and tool procedures behind existing on-demand mechanisms. Target: no more than 4,000 tokens.
Start normal turns with at most ten universal tools. Load integrations, meetings, communications, files, documents, web, sandbox, workflows, and Mac context only when relevant. Visibility changes; backend authorization does not.
Provide one ephemeral block per turn: current time, a compact Work Index of up to 30 open tasks, and meeting, approval, or view state when relevant. Fetch detailed Task Briefs only for a specific task.
Compact around 20,000 tokens, preserving unresolved requests, corrections, decisions, durable references, and a recent raw tail. Remove stale state, reloadable guidance, reasoning, and historical artifacts.
| Turn | Include up front | Retrieve if needed |
|---|---|---|
| Main answer | Core, recent chat, time, compact Work Index | Task Brief or memory file |
| Integration action | Core plus integration group | Operation schema, guidance, relevant memory |
| Task continuation | Core, Task Brief, pending input, recent task tail | Provider or meeting evidence |
| Meeting question | Core, recent chat, meeting identity | Transcript passages and related tasks |
| Approval response | Exact action, decision, authorization evidence | Live provider preview |
| Proactive run | Trigger evidence and task or routine state | Relevant memory and provider reads |
Make turn state ephemeral, remove Task Brief summaries and historical artifacts, and lower the compaction threshold.
Default rare tool groups to inactive while preserving the shared authorization surface.
Add component budgets to tests and use Context Token Attribution telemetry to catch regressions.
Release internally, then to 10%, then 100%. Compare token use, no-tool latency, tool-group misses, compaction, status accuracy, and approval regressions.
Main and Task share one capability surface. Raw chats, traces, Task Briefs, approvals, and User Files remain durable outside the prompt. Writes and approvals stay fail-closed.
Capability does not imply visibility on every call. A compact full Work Index replaces durable turn-by-turn deltas. Model context becomes disposable and never acts as a second durable store.