These are pieces of Skeen's own practice. Each note covers the problem, the approach, the stack,
and the outcome we can state without inventing numbers or naming clients.
Layered agents, human approval
Specialist agents draft and classify. A coordinator keeps a review queue. A person approves anything external.
Problem
An unattended send is hard to undo: the wrong recipient, a commitment nobody read, a message that cannot be unsent. The delay of a review is smaller than that failure.
Approach
Specialists do bounded work—research, classification, drafts. A coordinator routes that work onto a queue a person can see. External actions wait. The layers exist so a draft cannot become a send by itself.
Outcome
This is the operating shape. We do not publish volume or time-saved figures.
Text version: specialist agents do bounded work, a coordinator places it on a review queue, a person
approves, and only then does an external action go out.
Public-sector procurement and RFP signals are collected, scored, deduped, and placed where a person already reviews work.
Problem
Notices arrive from many public places, in different shapes, often more than once. Reading them raw is where a duplicate gets chased and a real fit gets skipped.
Approach
Ingest from more than one public source, score, dedupe, and import into the system of record a person already uses. A periodic digest shows what changed. Anything that would leave the practice still waits for approval. We do not list the sources here.
Outcome
Review happens on a queue, not in a pile of tabs. Counts are not published.
Agents can query a private corpus. The corpus stays on systems we operate, and a person decides what leaves.
Problem
Drafts and research are more useful when they can see the actual documents. Copying that corpus to a public model is a leak you cannot take back.
Approach
The documents stay on systems we operate, separate from this public site. Agents may query and draft against them. A person decides what is sent or filed onward. Separation is the control: the marketing host should not be where the corpus lives.
Outcome
Lookup is possible without handing the corpus to a public model. Document counts are not published.
Text version: private documents stay on systems we operate. Specialist agents may query them and
draft. A person decides what leaves. The corpus is not copied to a public model.
When an agent needs operational data, it uses a narrow path. Long-lived credentials are not copied into each agent.
Problem
A credential pasted into every client fails all at once. One copy leaks, and every copy is exposed.
Approach
One path, least privilege, strong authentication, and a person in front of anything that writes or sends. We do not publish which systems are connected or how the lock is built. The public site is not that path.
Outcome
The pattern is narrow access. The inventory is not on this site.
A static site. A pull request is previewed and reviewed before merge updates production.
Problem
Editing the live site in place means the mistake is already public. A copy step onto a server is easy to skip and hard to review.
Approach
Astro builds the site. Every pull request runs a type check and the production build, then opens a preview. A person reviews. Merge to main updates https://ai.skeen.biz. Secrets stay out of the repository, because a secret in git is a secret in history.
Outcome
Production moves when main moves, after a preview. We do not publish performance or uptime numbers.
Hands-on database and enterprise asset management work. The person who designs the change can also support it.
Problem
Asset-heavy operations depend on Oracle data and an EAM system of record. A change that only exists in a design note fails the first time something breaks and the author is gone.
Approach
Delivery is hands-on: PL/SQL packages, procedures, tuning, and migrations; DBA practice (backup and recovery, patching, monitoring, hardening); Oracle Fusion finance and SCM support, reporting, and data conversion; enterprise asset management with the Oracle data and integration work beside it. Notes are written with the change so the next person can operate it. Open-source Oracle PL/SQL toolkit: object types/UDTs, finance functions, ETL, migration, data quality, dev tooling; utPLSQL-tested with CI.
Outcome
Client names, system identifiers, and measured results are not published here. Those details belong in a conversation, under the terms of the engagement.