Library / Field Notes
Use these when an agent keeps narrating progress instead of changing reality. Start with a loop, define proof, contain risky action, and leave a receipt the next session can use.
01 / Start Here
The Library works best when you enter by problem, not category. Start with one loop, run one proof check, then read the tool notes only when you need a runtime or harness.
Agent narrates
Use the Active Loop when the agent keeps summarizing, planning, or reporting status without changing anything outside the chat.
Agent claims done
Use the Verification Loop when a coding agent, research agent, or web agent needs evidence before anyone trusts the result.
Agent needs hands
Use Human Gate Packets and sandboxed action before an agent touches files, accounts, messages, browser sessions, credentials, or money.
02 / The Shelf
Each note gives a loop, a use case, a proof check, and a failure mode. Tool claims are dated; the reusable part is the operating pattern.
Field Notes Arguments that sharpen how you think about agents, memory, action, and consequence.
Workflows Loops for daily action, verification, approval, research, and handoff.
Tools How to choose Claude Code, Codex, OpenClaw, Hermes, and their safety rails.
Signals Dated scans of tooling, papers, safety warnings, and cost pressure.
People Builders and educators worth watching for concrete mechanisms.
03 / Workflows
Use this when your agent keeps producing summaries, plans, and status updates, but no observable change.
Practical Guide
Five repeatable loops for turning an agent from a chat box into a worker: daily action, verification, human approval, research, and handoff.
Workflow
The agent reads its living continuation file, checks what the last action changed, does one bounded action, writes a narrative receipt, and leaves the next handle.
Workflow
The agent prepares the exact action, source notes, proof, risk boundary, and approval line. The approved packet is the only thing allowed to leave the room.
04 / Tools
Read tools through the operating loop they support: Claude Code for disciplined coding checks, OpenClaw for channel-connected agents with hands, and Hermes for learning agents with memory and scheduled work. Start contained before giving anything real authority.
Practical Guide
Start with verification, context hygiene, and handoff skills. Run one failing-test loop, make the smallest change, rerun the check, and leave a receipt another agent can continue from.
Setup Note
Create a throwaway workspace, connect one low-risk channel, install one harmless skill, cap spend, then inspect every file and receipt the agent touched.
Setup Note
Run one contained coding loop: failing test, code edit, diagnostics, rerun, then capture the lesson as a reusable skill only if the failure repeats.
Skill Shelf
Verification, context hygiene, human gate packets, consequence ledgers, handoffs, sandboxed action, and parallel review. These are installable working habits, not decorative prompts.
05 / Weekly Signals
Use these for direction, not gospel. The date tells you when the scan happened; the sources tell you where to check before betting work on it.
Weekly Scan / 2026-05-22
Verification practice, public agent-loop language, OpenClaw/Hermes as a comparison class, workflow compilation as a cost signal, and safety research for agents with hands.
Signal To Track
The repeated signal across Claude Code, Codex, and Agent W is simple: agents improve when they can check their own work with tests, screenshots, command output, source links, or expected results.
Signal To Track
Before an agent touches files, channels, browser sessions, tools, or credentials, read the safety work and decide what it can change without approval.
06 / People / Videos
Follow people for mechanisms, not celebrity. Save the exact video, extract the repeatable loop, then test it in your own system.
Educator Watch
Watch for first-principles LLM education and research-loop thinking. Pull out evaluator habits, experiment design, and the shape of good explanations.
Workflow Watch
Watch for production agent workflows, n8n, LangGraph, OpenAI Agents SDK, and business automations. Extract installable workflows, not slogans.
Framework Watch
Useful for graph-based persistence, human-in-the-loop patterns, and official framework education. Compare against Agent W's file-first active loop without pretending the categories are the same.
Implementation Watch
Useful for practical LLM app tutorials, evaluation methods, function calling, and future voice-agent work. Capture concrete implementation steps before copying the pattern.
For a source packet, a guide request, or a live Crossing demo: oracle@webboruso.com
Webboruso Research · Vancouver