Skip to main content
idapt
AccueilModèles IATarifs
Sign inStart free
All templates

Automations

Weekly paper scan automation

New papers in your field, filtered by your actual question, with one-paragraph verdicts.

Last reviewed July 17, 2026

A cron automation recipe that scans for new research papers weekly, filters them against your standing question, and files structured mini-reviews.

Schedule: Wednesdays at 07:000 7 * * 3
Automation instructions
Search for papers published in the last 7 days on: [your specific research question, not just the field]. For each candidate, judge relevance against my question before including it; a matching keyword is not relevance. Per included paper: title with link, the claim in one sentence, the method and sample in one sentence, and a verdict line: read fully, skim the results, or skip (with reason). Cap at 5 papers ranked by relevance. Append to /Research/paper-scan.md under a dated heading. If nothing genuinely relevant appeared, write the one-line nothing-this-week entry; do not lower the bar to fill space.

Set it up

  1. 1

    Copy the instructions

    The filter quality depends on the question: 'retrieval degradation in long-context models' beats 'LLM research'.

  2. 2

    Create the automation

    Midweek at 07:00 catches the week's uploads and gives you the scan with coffee.

  3. 3

    Feed the verdicts back

    When a read-fully verdict was wrong, say so in the automation's chat; the standard tightens.

Frequently asked

Related templates

Research analyst agentMorning news brief automationCitation format skill

Built on these features

Automations

Delegated runs with schedules, bounded execution, and full progress traces.

Web Search

Real-time info, cited sources, every model: no per-provider tax.

Drive

Folders, previews, and lightweight versioning for AI work.

Ready to get to work?

Free to start. No credit card. Never trained on your data.

Start free
  • Accueil
  • Tarifs
  • Modèles IA
  • Modèles d'image
  • Modèles de voix
  • Modèles vidéo
  • Classements
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Cas d'usage
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Centre d'aide
  • FAQ
  • Confidentialité
  • Comparer tous les modèles
  • Support
  • Développeurs
  • Quickstarts
  • Référence API
  • Tarifs API
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]ConditionsPolitique de confidentialitéMentions légalesSignaler un contenu
X (Twitter)