Operating manual
Tag: agentic
A focused reading path for agentic: related field notes, evidence trails, and operating questions from the archive.
- what-can-you-remove-after-harness-distillation.md
What Can You Remove After Harness Distillation?
Harness distillation can make some runtime guidance removable. Use a retain-or-retire map to separate learned habits, tool interfaces, and enforced controls.
open artifact → - competent-agents-can-still-fail-to-coordinate.md
Competent Agents Can Still Fail to Coordinate
Agent capability is not proof of a valid shared commitment. What scheduling experiments suggest builders should test across different owners.
open artifact → - build-the-workflow-before-the-prompt.md
Build the Workflow Before the Prompt
Build verified tool-use examples from executable workflows. What ToolGrad shows, what its pass rate does not, and how to keep challenge cases separate.
open artifact → - your-agent-api-needs-a-run-custody-map.md
Your Agent API Needs a Run-Custody Map
Before adopting a managed agent API, map who retains state, reconciles tool effects, restores work, and exports the evidence.
open artifact → - quantum-is-coming-agent-workflows-should-start-leaving-breadcrumbs.md
Quantum is coming. Agent workflows should start leaving breadcrumbs.
Quantum will matter for agent systems, but not by magically replacing LLM workflows. The useful move is to make today’s workflows measurable enough to route tomorrow’s hard subproblems.
open artifact →