Instead of creating a bespoke memory or messaging protocol for agent-to-agent communication, Notion leverages its core primitives. Agents compose by writing to and reading from shared Notion pages and databases, creating a decoupled, human-editable, and transparent system for coordination.

When a key software tool like Gong lacked a direct data feed, a workaround was created by identifying URL patterns. A scraping tool was used to grab a unique Call ID, which was then appended to a base URL to access and scrape the full transcript, unblocking a complex automation workflow.

If a tool, like the meeting-note app Granola, lacks an official MCP for integration, you can write a simple script for your AI agent to execute. The script can fetch data and save it as local files, effectively making any external data source part of the agent's accessible context.

By running locally on a user's machine, AI agents can interact with services like Gmail or WhatsApp without needing official, often restrictive, API access. This approach works around the corporate "red tape" that stifles innovation and effectively liberates user data from platform control.

Creating integrations for native desktop applications can be difficult. A powerful workaround is to use the web-based version of the app, like Slack in Chrome. This allows you to build custom Chrome extensions that can read content, trigger actions, and automate workflows.

The hype around AI agents needing local file system access may be misplaced for the average consumer. Most critical personal data—photos, emails, messages—is already mirrored in the cloud and accessible via APIs. The real challenge and opportunity lie in securing cloud service integrations, not local device access.

By running AI models directly on the user's device, the app can generate replies and analyze messages without sending sensitive personal data to the cloud, addressing major privacy concerns.

Many apps, like WhatsApp, encrypt message content but still collect revealing metadata (contacts, communication patterns). Signal's President Meredith Whittaker contrasts this with their comprehensive encryption, which protects this metadata, offering true privacy rather than just the appearance of it.

With no default data-sharing protocols, police agencies resort to primitive methods. The first step up from nothing is emailing PDF bulletins. More advanced groups create private Slack or WhatsApp channels for real-time collaboration, despite the data retention and security risks of using consumer tech.