DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV

[ LAB — WORKSHEET · no model calls ]

Context Policy Kit

A JSON planning document for an evidence-backed assistant. It makes source priority, expiry rules, context allocation and abstention explicit. The schema is provider-neutral and designed for human review, not a drop-in runtime configuration.

All lab tools
Editable worksheet / json
Original file ↗

Edits stay in this tab and are not saved to the server. Download before leaving. The worksheet itself does not call models or enforce policies.

How to use it

  1. 01

    List authoritative sources, owners and access rules.

  2. 02

    Set context budgets and behavior for stale, conflicting or absent evidence.

  3. 03

    Turn each policy into a labeled evaluation case before implementation.

Sources and methodology