Skip to content
BotClawAgent ObserverTracking personal agents: progress and limits
2026.10.02
FROM QUESTION TO RESULT

Workflows you can verify

Start with a concrete task. Each guide includes inputs, steps, success criteria, failure handling and evidence boundaries.

The RSS Node example has recorded execution evidence. The other procedures are based on official documentation and have not been run in the named agents.

  1. 01
    OpenClaw · Node execution recorded

    Build a repeatable RSS digest with source links

    A runnable Node example fetches feeds, removes duplicate URLs and remembers seen items. Live inputs produced 35 unique entries; an unchanged replay produced zero new entries. Agent scheduling remains untested.

  2. 02
    Hermes · Documentation-based procedure

    Verify the first Hermes conversation before connecting apps

    A small acceptance procedure separates installation, provider connectivity, tool execution and session persistence. Use harmless local input before adding messaging or schedules.

  3. 03
    Hermes · Documentation-based procedure

    Check that a memory update changes the next session

    A two-session test verifies persistence, correction and retrieval with a harmless fictional preference. A verbal promise to remember does not count as a saved memory.

  4. 04
    Hermes · Documentation-based procedure

    Inspect a skill before installing and testing it

    Review files, commands, permissions and outbound destinations before adding a skill. Keep a reversible install record and verify removal in a new session.

  5. 05
    OpenClaw · Documentation-based procedure

    Validate one scheduled task before making it recurring

    Check timezone, execution logs, destination and cleanup with a single harmless event. The current OpenClaw docs use automations; cron remains an alias.

  6. 06
    Hermes · Documentation-based procedure

    Connect one messaging channel with an explicit allowlist

    Verify sender access, conversation routing and actual reply delivery separately. Start with a private test chat; gateway registration alone is not a successful integration.

  7. 07
    Hermes · Documentation-based procedure

    Build a permission boundary that can be tested

    Separate model instructions, tool approvals and operating-system access. Use an allowed read and a denied write to test the effective boundary.

  8. 08
    OpenClaw · Documentation-based procedure

    Verify a backup by restoring into a separate directory

    Inventory and verify an OpenClaw archive, then restore into a test target. Keep credentials private; an archive existing on disk is not a recovery test.

  9. 09
    OpenClaw · Documentation-based procedure

    Check an upgrade against a recorded baseline

    Record the actual CLI and gateway versions, preserve recovery data, and recheck chat, tools, memory, messaging and schedules after upgrading.

  10. 10
    Hermes · Documentation-based procedure

    Compare OpenClaw and Hermes with the same task

    Use a controlled task and record evidence, completion time, failures and observed cost. Choose for your deployment and workflow constraints rather than a general score.