Zapier’s Sidekick shifts AI approvals from tools to protected resources
Zapier’s Sidekick AI workspace has refined how it handles user approvals for automated actions. Early versions asked for permission on a per-tool basis, but this led to confusion and inconsistencies. The team now ties rules directly to specific resources—like files, apps, or folders—so users can set broad protections (e.g., “never change anything in this folder”) that apply across all actions…
Key points
- Sidekick now links permissions to resources (files, apps, folders) instead of tools, letting users set rules like *‘never edit this doc’*
- Approval requests appear in a fixed panel, not chat, with clear scopes and readable labels to avoid confusion
- Auto mode uses an AI reviewer for uncovered actions, while YOLO mode skips approvals unless blocked by user rules
How much should an AI decide without asking you first?
Zapier Blog · 6 November 2026
Loading the full article…
This text was published by Zapier Blog and written by Jay Ayinla. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Perplexity launches Teammates agents for Perplexity Max users · 3 src
- OpenAI, Meta and xAI launch AI agents for long-term task delegation · 8 src
- Study finds AI agents waste 18% of tokens on unnecessary tasks · 1 src
- Amazon Quick defines four agentic primitives based on When, What, Who, and How · 1 src
- AWS shows how to govern AI agent access with Okta and Bedrock AgentCore Gateway · 1 src
Comments
via GitHub Discussions