The Agency
Skills, playbooks, and field notes · Athan Dial
The portfolio side covers the decisions. This side covers the workflows themselves — what I reach for, what I changed last week, what failed enough times that I wrote the recovery down.
AI shows up everywhere in real work: pipelines, research, code, project ops. The case studies on my portfolio cover the decisions. The pages here cover the workflows themselves — what to install, what to run, what to do when it breaks. Most of these started as a problem I hit twice and decided not to hit a third time.
What you’ll find
Latest
Latest Dispatch
AI research that actually cites sources
A fake citation in a product brief forced the switch: parallel pulls from PubMed, preprints, and trials, then tables with DOIs I can open before I repeat a number.
Latest Playbook
Build an ingest pipeline
Helps you run ingest → stage → process → publish across Slack, Confluence, bookmarks, and video—deduped knowledge atoms, provenance, one orchestration command.
Playbooks
View all 12 →Playbook
Code
Jira and Confluence from Claude Code
Helps you move Jira state and Confluence pages from the terminal—JQL previews, acli transitions, version-fetched REST updates—when the web UI is too many clicks away.
Playbook
Code
Query your data warehouse with Athena
Helps you answer lakehouse questions with Athena by matching intent to tables, fetching schemas on demand, then running SQL without memorizing the whole catalog.
Playbook
Code
Read replica forensics from Claude Code
Helps you slice operational Postgres via a read replica—staleness, soft deletes, join paths—with saved SQL, logged commands, and CSVs while the admin UI is still loading.
Playbook
Desktop
A daily workflow with Claude Desktop
Helps you run a full workday in Claude Desktop: overnight brief, mail triage, meeting prep, Cowork passes on what's on screen, evening carry-over—connectors carry the context.
Playbook
Code
Build your first Claude Code skill
Helps you freeze a repeated workaround as SKILL.md: specific trigger, runnable procedure, verification, and the failure modes you already paid for.
More dispatches
View all →Dispatch
Code
Autonomous agents need a foreman
I learned the hard way that one-shot multi-phase Claude Code returns fast code and expensive cleanup; discuss → plan → execute → verify with atomic commits is what made autonomy survivable for me.
Dispatch
Desktop
Cowork changed how I think about AI
I stopped paying the preamble tax once Claude sat beside the doc or thread—short questions, faster triage; I still reach for Claude Code for files, commands, and APIs.
Dispatch
Code
Delegation is the real skill
I filed a vague `/codex-task` on a Friday and spent Monday unwinding five conflicting guesses; the real bottleneck is always the same—context, legible scope, and explicit format—so a new teammate could ship without guessing.
Dispatch
Code
Memory across sessions
I stopped burning every session opener on the same policy paragraph once `/remember`, `/reflect`, and the knowledge hub gave me one collaborator that already held decisions, guardrails, and corrections.
Dispatch
Desktop
Read-only automation is a feature
I keep automations in draft: Claude proposes, I send—parallel drafts for speed, human gate for tail risk after a near-miss taught me the cost of auto-send.
Dispatch
Code
Skills encode what you learned the hard way
Every skill I write holds the constraint I burned time discovering — the CLI flag that silently fails, the join pattern that actually works, the config the docs forgot to mention.