Notes
These notes begin with work I expect to encounter again: a migration that failed in an unexpected place, a rule that keeps an agent inside its permissions, a design choice worth testing, or a question that is not settled yet.
Some are instructions I use now. Some connect several sources or projects. Some are explorations, and some preserve the exact sequence of an incident. The labels under each note tell you which kind you are reading, how firmly I hold it, and whether it is still current.
Exploration note · Prospective claim · Current · Software assurance
A wrapper-derived effect-intent projection should let an application session correlate instability during the next Talos control-plane upgrade; if it still escalates without correlation, the hypothesis fails.
Synthesis note · Exploratory claim · Current · Organizational systems
An EventStormingAlberto Brandolini's workshop method for modeling a domain on colored sticky notes -- commands, domain events, actors, views, and hotspots -- normally run with a room of stakeholders around a paper timeline. pass run solo, over agent session logs instead of a stakeholder workshop, still produced six ranked findings. The notation survived; the workshop did not; the value was in clustering the absences.
Synthesis note · Exploratory claim · Current · Organizational systems
A solo operator's tooling keeps adopting controls that look stolen from an organization. The controls are not for headcount; they are for coordination between actors who share neither memory nor judgment, which describes one operator across time as much as it describes a team.
Exploration note · Current · Agent workflow
A prior "human perpendicular to the loop" claim only describes one interface. The fuller model is two coupled loops at different speeds, with a settlement boundary -- not an empirical/normative split -- deciding when the slow loop must be consulted.
Exploration note · Current · Agent workflow
The next-prompt heuristic measures what became visible at the human interface. A merged PR later filed as architecture, and a self-report that turned out to be reconstructable rather than introspective, both passed that test and still needed a different check further down.
Synthesis note · Exploratory claim · Current · Model evaluation
RAG, vector search, graph engines, and generic evaluation tooling are moving into managed platforms. The durable work is defining which evidence may count, what failure means, and when an agentic system is acceptable to ship.
Synthesis note · Exploratory claim · Current · Agent infrastructure
The queue chassis behind ActionQThe PostgreSQL-backed queue that owns actions, sessions, claims, and outcomes. is now commodity, split across a Postgres-native library, a durable-workflow runtime, an execution control plane, and an automation platform. How much of ActionQ survives once that chassis is removed is the open spike.
Synthesis note · Exploratory claim · Current · Agent infrastructure
OutctlA tool that captures a command's full output outside the agent's context and returns a bounded projection the agent can query later for the omitted evidence. began as an answer to tool results flooding model context. Programmatic tool calling now moves that work into the harness, invalidating the original product boundary while leaving a narrower durable-evidence question open.
Synthesis note · Exploratory claim · Current · Agent infrastructure
Production access exposes the limits of prompt-only agent design. A useful operational run binds a general harness to domain context, scoped authority, evidence, and completion rules.
Exploration note · Current · Agent workflow
An agent asks for a design decision mid-implementation, the operator answers at pull-request depth, and the answer gets filed as architecture. The fix is not a better escalation prompt but keeping three separate reviews from borrowing each other's authority.
Project history · Archival claim · Disproven · Model evaluation
OutctlA tool that captures a command's full output outside the agent's context and returns a bounded projection the agent can query later for the omitted evidence. cut model-visible Kubernetes output by about 84%, while pair-level cost and diagnostic quality remained unresolved. The useful result was a four-part evaluation model: mechanism, quality, economics, and authority.
Synthesis note · Guiding claim · Current · Architecture practice
A reference architecture is a set of ideas to test, not a target to copy. It can suggest capabilities, controls, and common failure modes; local strategy and evidence decide which parts survive.
Operating note · Guiding claim · Current · Homelab operations
A live migration needs more than a target diagram. Before changing the first node, name the temporary configurations, the checks between them, who controls each handoff, and the point after which rollback stops being cheap.
Exploration note · Current · Organizational systems
Senior analysts rarely start with complete information or a blank strategic canvas. Their job is to produce a recommendation that holds together when other people challenge it; AI can help maintain that reasoning without making the decision.
Project history · Guiding claim · Current · GitOps operations
Two upgrade failures came from persistent node-local state outside Git: malformed UEFI NVRAM and an iSCSI record that poisoned shared parsing. The fix was bounded exceptions, preflight checks, controlled migration and verification.
Operating note · Guiding claim · Current · Agent workflow
A multi-repository project folder may assemble member worktrees, shared guidance and project context, but it must not acquire ownership of Git, backlog, execution or deployment state merely because every tool can see it.
Project history · Guiding claim · Current · Release engineering
A release candidate passed every gate and failed on contact with production six minutes later. The gates proved compatibility with the target database state; nothing had proved the transition from the state actually running.
Project history · Guiding claim · Current · Creative tooling
A 48-second generated loop stays out of Git, and ~21 MiB of tracked source, manifests and receipts identify ~2.2 GiB of untracked media and verify any retained or reconstructed copy. That buys identity, not availability or reproducibility — the gates taught the rest.
Exploration note · 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.
Synthesis note · Exploratory claim · 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.
Synthesis note · Guiding claim · Current · Software assurance
A reading map for building AI systems that can show what they were asked to do, what they did, why a result should be trusted, and how failures are contained. It starts with established assurance practice and ends with a dated watch list of open work.
Synthesis note · Exploratory claim · 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 note · Current · Career
Senior specs in Finnish regulated reporting bundle proxies for someone else's apprenticeship system; the newest slice, auditable AI automation, has no such system yet, so the working hypothesis is to form it in place rather than wait for it to appear in a listing.
Synthesis note · Exploratory claim · 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.
Exploration note · Superseded · Career
Four plausible sources for the eventual cohort of auditable AI-automation specialists in regulated reporting, recorded now so the guess is falsifiable against later hiring patterns.
Operating note · Guiding claim · 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.
Synthesis note · Exploratory claim · Current · Software assurance
Continuing assurance can move away from an exact generated output only when retained inputs and independent checks can produce another acceptable result; retention remains a separate decision.
Exploration note · 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.
Synthesis note · Exploratory claim · Current · Organizational systems
Agent-ready work keeps the reason, permission, attempted action, observed result, and correction connected while the work happens instead of reconstructing them later.
Exploration note · Current · Energy systems
An operating sketch for a boutique Finnish mill-site retreat where the river sets the scale of the baths, restaurant, lodging, and renewal reserve.
Synthesis note · Exploratory claim · Current · Agent architecture
A durable agent application keeps permissions, records, checks, and recovery outside the model, so changing models does not also replace the system's memory or rules.
Exploration note · 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.
Exploration note · Prospective claim · 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.
Project history · Exploratory claim · 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 note · 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 note · 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 note · Current · Organizational systems
Agents may perform most of a professional workflow while a named person still supplies local judgment, trusted relationships, or accountable approval.
Project history · Exploratory claim · Superseded · Agent workflow
sprintctlThe CLI and schema that own sprint work, dependencies, claims, and handoffs. and actionqThe PostgreSQL-backed queue that owns actions, sessions, claims, and outcomes. enforce useful execution discipline, but five current invariants rely on one operator remaining the only source of identity, authority, and audit judgment.
Exploration note · 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 note · 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.
Operating note · Guiding claim · Superseded · 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.
Operating note · Guiding claim · 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.
Exploration note · Current · Energy systems
A business plan for battery-swap delivered energy that works in one narrow niche and matters most for what it implies about EVs, home batteries, and off-grid design.
Operating note · Guiding claim · Current · Software architecture
homelab-analyticsThe household data and decision platform that owns long-lived semantics, scenarios, policies, and approvals. enforces its layer boundaries with pytest. A documented architecture is a request; a tested one is a constraint.
Project history · Guiding claim · Current · Cluster operations
Migrating a Talos cluster from a legacy subnet to its own VLAN while it kept serving. The design was mostly an ordering problem, plus one bootstrap loop: the network controller lives inside the network it manages.
Exploration note · Prospective claim · Current · Hardware contracts
Cassettes, diskettes, and cartridges as physical handles for digital media. The rule that makes the whole family of projects work: the tag points, it never hosts.
Operating note · Guiding claim · Current · Agent workflow
actionq-dispatcherThe one-action coordinator that creates a bounded workspace, invokes a worker, and records the result. 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.
Operating note · Guiding claim · 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.
Operating note · Guiding claim · 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.
Exploration note · Prospective claim · Current · Data architecture
A reference design for audit-native systems where code, layout, control decisions, and data are all log artifacts.
Operating note · Guiding claim · Current · Data architecture
A pipeline rule: land raw, split deterministically, enrich point-in-time, then shape for consumers.
Project history · Archival claim · 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.
Project history · Archival claim · Archived · GitOps operations
A live rollback fixed a crashlooping workload, but the more interesting part was needing to suspend reconciliation long enough for the fix to become the desired state instead of a temporary lie.
Project history · Archival claim · Archived · Contract governance
Backend-owned contracts only become useful release artifacts once the compatibility tooling is conservative enough to complain about real breakage instead of politely missing it.
Project history · Archival claim · Archived · Authentication architecture
Homelab analytics had enough auth surface to accidentally grow a second identity product. The useful decision was to keep identity proof upstream, keep authorization local, and demote local login to a narrow break-glass path.