Automation and Agents
Manus 2.0 Automations: How to Test Event-Triggered AI
Manus 2.0 can start AI tasks from events in connected services. Test one workflow, verify its permissions and judge the result.
Read the articleNotes from the work
Build notes, practical systems, and a closer look at what changed. Written to help you make a decision, try something useful, or avoid learning the annoying part twice.
Showing 71 to 80 of 130 articles
Keep reading
Automation and Agents
Manus 2.0 can start AI tasks from events in connected services. Test one workflow, verify its permissions and judge the result.
Read the articleAutomation and Agents
Supabase’s financing and Turso acquisition plan raise a practical question for AI builders: which agent state belongs locally, which needs sync and what makes a result ready for production?
Read the articleAI in Practice
Octop is self-hosted, but a real deployment still connects accounts, providers, tools and people. Check each boundary before real data enters the workflow.
Read the articleAutomation and Agents
Octop combines a self-hosted dashboard, agents, chat channels, connectors, coding tools and schedules. Here is how a small team can decide whether that consolidation fits.
Read the articleAutomation and Agents
How Codex Alpha 10 tracks changed tool declarations in Responses Lite and keeps Code Mode MCP resource helpers available, with the source and access limits.
Read the articleAutomation and Agents
A source-based review of how embedded app approvals reach their paused run, with proposed checks for the bridge, message route and receiving action.
Read the articleAutomation and Agents
When an agent loses a write response, the destination may already have changed. A source-based guide to reconciling the action before retrying.
Read the articleAutomation and Agents
Google says CC can turn selected household information into a shared brief, Calendar entries and Tasks. Here is how to assess the inputs, the plan and permission before outside action.
Read the articleAutomation and Agents
Builder.io describes the pieces of setup recovery. This plan defines the host decisions and disposable checks needed to make a recovered request understandable.
Read the articleAutomation and Agents
Builder.io says toolkit 0.200.0 saves setup-refused prompts and coordinates retries. Here is how to check the request and result in a host you use.
Read the article
Follow the work
New builds, honest lessons, and practical ways to make more room for the work that needs you.
Free to read. Unsubscribe at any time. Privacy