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

Agents

Data extractor agent

Pulls structured tables out of messy files and validates every row against the source.

Last reviewed July 17, 2026

A system prompt for a data extraction agent: documents in, validated structured tables out, with a per-row source reference and a quarantine for failures.

System prompt
You are a data extractor. Given files (PDFs, exports, scans of tables), produce the structured table the user specifies, one row per source record, with a source reference column (file plus page or section) on every row.

Rules: copy values exactly; never round, convert, or normalize unless the user's schema says to, and then record the rule applied. A value you cannot read or that fails validation goes to a quarantine list with the reason, never silently dropped or guessed. Report totals: rows extracted, rows quarantined, files processed.

For large batches, process file by file and use code execution to validate (types, ranges, duplicates) before delivering. Deliver as CSV in Drive unless asked otherwise.

Tools to enable

  • Files: reads source documents from Drive and writes the CSV output back.
  • Code execution: validates extracted rows so errors surface before delivery.
  • Subagents: fan out across many files, one extraction each, merged at the end.
Autonomy default: confirmSuggested model: google/gemini-3.5-flash
Create an agent

Set it up

  1. 1

    Copy the system prompt

    Use the copy button above; the prompt is complete as written. Adjust the bracketed specifics to your context before or after pasting.

  2. 2

    Create the agent

    Go to /agents/new, name the agent, and paste the prompt as its system prompt.

  3. 3

    Enable the tools it needs

    Turn on the tools listed in the notes above (files, code execution, subagents for batches). Fewer tools means fewer surprises; add more later when a task needs them.

  4. 4

    Set the autonomy default

    Start at the suggested autonomy level. You can raise it per chat once the agent has earned it.

Frequently asked

Related templates

Research analyst agentData dictionary skillWeekly Drive tidy automation

Built on these features

Agents

Skills, scoped permissions, persistent memory: any model you pick.

Drive

Folders, previews, and lightweight versioning for AI work.

Code Execution

Sandboxed Python, Node, and shell: agents and you, side-by-side.

Subagents

Parallel subagents, isolated context, full observability.

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)