Screen research papers automatically against your review criteria

Reads papers from Google Drive, checks each one against your inclusion criteria with AI, and logs every decision to Airtable.

How the work actually flows

It branches. Exactly one path is taken.

Pattern: Exclusive Choice (4) · Simple Merge (5)

flowchart TD trig[\"new paper appears in drive"\]:::trigdata s0["read new paper"]:::task s1["check against criteria"]:::task s2[("log decision")]:::store trig --> s0 s0 --> s1 gx{"× meets criteria or not"}:::gate s1 --> gx p00["index for search"]:::task gx -->|"included"| p00 p10["file separately"]:::task gx -->|"excluded"| p10 jn{"○ record outcome"}:::gate p00 --> jn p10 --> jn jn --> s2 out[/"audit-ready screening record"/]:::out pay{{"defensible review trail without manual work"}}:::pay s2 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepA record or sheetOne path onlyPaths rejoinResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
Knowledge Base & RAGDocument Processing & OCRSpreadsheet & Database OpsResearch & Market IntelligenceFile & Cloud Storage
Connects
Google DriveOpenAIGoogle GeminiQdrantAirtable

The problem it solves

Screening a stack of research papers by hand means reading each one closely, deciding whether it meets your criteria, and keeping a clean record of why. Doing that consistently across dozens or hundreds of papers, with a defensible audit trail, takes real time and focus.

Who it fits

Researchers and teams running a systematic literature review who need a documented, defensible screening process.

How it works

  1. New papers in your Google Drive folder are picked up automatically
  2. AI reads each paper and checks it against your inclusion and exclusion criteria
  3. Included papers are indexed for semantic search, and excluded ones are filed separately
  4. Every decision and its justification is logged for a complete audit trail
What you get

Screening decisions logged for every paper reviewed

Papers from Google Drive get checked against your review criteria automatically, with every decision logged so your process stays fully documented.

What you get

An audit-ready record of every paper included or excluded, plus a searchable library of the papers you kept.

What you need

A Google Drive account, an Airtable account, OpenAI and Google Gemini API keys, and a vector database.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Keep an AI knowledge base updated from your Google Drive files

Documents in Google Drive automatically sync into a searchable AI knowledge base that answers questions accurately.

Advanced

Keep an AI knowledge base updated from your Google Drive files

Turns your Google Drive documents into a searchable AI knowledge base and lets you refresh single files anytime.

Advanced

Answer questions from your documents with AI and cited sources

Lets you ask questions about your files and get AI answers that name exactly which document they came from.

Advanced

Turn uploaded documents into a searchable AI knowledge base

Documents from Google Drive or a web form are read, understood, and indexed so staff can ask questions and get instant answers.

Advanced
Back to the AI Playbook