Tag
26entries across current project state and published notes.
Published and in active use
A working family of sprint, queue, dispatch, knowledge, audit, and cockpit tools is becoming one served composition layer without giving up explicit state ownership or machine-local execution.
exploration / current / model evaluation
A small isolated-completion pilot asked whether a model can report influences on its own output. External-reconstruction controls qualitatively reproduced the effects, so the useful residue was operational, not introspective.
exploration / current / agent workflow
Direct agent operation removes a universal deployment handoff, so authority, evidence, and reconciliation must bind to each consequential action instead of to its location.
guiding / current / software assurance
A maintained reading map in two tiers -- established sources for intent, assurance arguments, verification, authority, provenance, runtime evidence, and resilience, then a short dated watch list for the composition question that is still open.
exploration / current / agent workflow
Chronology is one projection of this site's notes, not the structure underneath them. The corpus is the artifact of record; pages, feeds, and prompts built from it are derived realizations that should stay regenerable rather than independently maintained.
exploration / current / software assurance
The assurance questions behind my recent agent-workflow notes are established engineering problems. The useful work is learning their vocabulary and testing their methods at small scale.
guiding / current / agent workflow
A note explains what survived editing. An explorePrompt is a separate, deliberately post-hoc artifact that explains where the investigation should continue -- for a reader, their agent, or a later version of me.
exploration / current / agent workflow
Working model: a production-critical agent pipeline becomes an institutional capability only when a second person can reconstruct, operate, change, and recover it from recorded substrate and evidence.
exploration / current / software assurance
AI generation creates more disposable realizations, but an artifact becomes derived only when assurance can move from its exact implementation to a durable generation and verification contract.
exploration / current / organizational systems
Working model: agent-readiness depends less on whether work is digital than on whether intent, action, consequence, and correction remain joinable while the work is happening.
exploration / current / agent architecture
A model can be replaced only when the application retains authority, canonical state, evidence, verification, and recovery outside the model's control.
exploration / superseded / agent workflow
Agents can bypass the physical handoff between execution and runtime, so authorization, evidence, and reconciliation have to attach to each consequential action instead.
prospective / superseded / agent infrastructure
A devbox can bind identity, tools, network reach, and session evidence, but it should remain a replaceable access cell rather than becoming the organizational authority.
exploration / superseded / organizational systems
Routine junior work once paid for useful production and professional formation at the same time; agent automation separates those goods and leaves succession needing an explicit operating model.
exploration / current / agent workflow
AI makes synthesis cheap enough that the prose has little scarcity. The human remainder is the changed judgment and an attributable position that can age badly in public.
exploration / current / open source
AI weakens the old correlation between producing a plausible patch and understanding a project, so OSS contribution shifts toward evidence, verification, standing, and durable ownership.
exploration / current / organizational systems
Professions remain human-anchored where productive context, social standing, or institutional authority must stay bound to a person, even as most surrounding execution becomes agent-operated.
exploration / superseded / agent workflow
sprintctl and actionq enforce useful execution discipline, but five current invariants rely on one operator remaining the only source of identity, authority, and audit judgment.
exploration / current / agent workflow
Work-management systems can delegate and coding agents can execute, but authority, attempts, evidence, and acceptance still have no obvious neutral owner between them.
exploration / current / agent workflow
Coding agents now shape my project structures, notes, prose, and tolerance for complexity. I shape them in return, mostly by deciding what survives.
guiding / current / agent workflow
New agents carry more work from intent to evidence, but that changes rather than removes the supervision problem. The next prompt reveals whether the result needs repair or is ready to extend.
guiding / current / agent workflow
The sprint database held 831 work items and seven doc refs, six of them the same document. The reference command existed the whole time. The missing piece was never a tool — it was placement on the path the agent actually walks.
guiding / current / agent workflow
actionq-dispatcher runs agent work as subprocesses inside a per-invocation coordinator. The rejected alternative was a long-running agent service, and the rejection is most of the design.
guiding / current / agent workflow
Conversational refinement produces the feeling of having thought clearly, which is not the same thing as having thought clearly. The fix was not discipline. It was writing the stop rule into the counterpart.
guiding / current / agent workflow
Sprint work is split into plan, build, and review dispatches, and the orchestrating session is structurally barred from editing deliverables. The bar is the point.
archival / superseded / agent workflow
The useful workflow layer for solo agent work is not a giant orchestration stack. It is a local-first system that remembers claims, checkpoints, routing choices, and promotion boundaries without pretending one operator needs a whole platform team.