Work | Blueism
Home Work About us
Get started Contact

Info@blueism-studio.com — Online worldwide · HQ in Tetouan, Morocco

{{ title }}

{{ eyebrow }}

{{ line.text }}

{{ m.label }}

{{ m.value }}

The brief

{{ briefHead }}

{{ briefBody }}

{{ wideAlt }} {{ wideAlt }}

Approach

{{ a.n }}

{{ a.title }}

{{ a.body }}

{{ e.n }}{{ e.alt }}
{{ e.alt }}

Plates

Drag sideways to turn the page

{{ e.alt }}
{{ e.n }}{{ e.alt }}
{{ g.alt }}
{{ g.alt }}
{{ g.alt }}

01 — Selection

The shape of standing work

Before building anything we sorted the week on two axes: how often it recurs, and how much judgement it takes. Only one quadrant is worth an agent.

Agent territory

Weekly · needs a decision

Standing orders

Recurs on a clock, requires an opinion, has a rule you could write down if pressed.

Rare · high stakes

Keep it human

The judgement is the value. Do not delegate it.

Weekly · mechanical

Already solved

A plain script does this. No model required.

Rare · mechanical

Leave it alone

Too infrequent to earn the build cost.

02 — Architecture

How it is wired

One n8n workflow per agent. Every one of them runs the same five-stage spine, so a new agent is a configuration rather than a project.

01 Trigger

Wake up

Cron — Mon 06:00. Gmail watcher. Inbound webhook.

02 Gather

Assemble context

Airtable records, Postgres history, Drive and mail threads.

03 Reason

Form an opinion

Claude, given the rubric and prior decisions. Returns a reason and a score.

04 Gate

Act or ask

Confidence at or above threshold acts. Anything below escalates.

05 Act

Do the thing

Write to Airtable, draft in Gmail, call an internal API.

Fallback

A Slack thread to a named human, with the reasoning attached.

Run ledger

Every run writes input, reasoning, decision, confidence and outcome to Postgres. Nothing an agent did is unexplainable after the fact.

03 — The roster

The agents, one by one

Each one is narrow on purpose: a single decision, a single rubric, a single person it can interrupt.

Agent 01

The Reconciler

Reads the week’s movements against what was expected and reports only the differences that need an opinion.

Airtable → Postgres → Slack

Agent 02

The Triage Clerk

Sorts the inbound queue by what a message is actually about, not by what its subject line claims.

Gmail → Claude → Airtable

Agent 03

The Follow-up

Notices what has gone quiet, drafts the nudge in the right register, and leaves it for a human to send.

Postgres → Claude → Gmail draft

Agent 04

The Registrar

Keeps the record straight: fills the gaps it can prove, flags the contradictions, and never invents a value.

Webhook → Claude → Postgres

04 — Method

Judgement, encoded

An agent allowed to decide needs three things a script does not: a rubric, a memory, and a way of saying it is not sure.

The rubric

The policy the team already had in their heads, written out as ordered rules. Most of the project was this conversation.

The memory

Prior decisions are retrieved and passed in, so this week is judged the way last week was.

The gate

Low confidence is a valid answer. It routes to a person instead of guessing.

Rubric — extract

DECIDE: route | hold | escalate
IF variance > tolerance AND no matching note → hold
IF counterparty unseen in 90 days → escalate
ELSE route — and state the reason you routed it

#standing-orders

Mon 06:04

RC

The Reconciler APP

Holding 1 item from this week’s run. Variance is above tolerance and I cannot find a note that explains it.

confidence 0.41 · rule 2 of 6

Counterparty last seen 114 days ago. Comparable items in the last quarter were held, not routed.

Approve hold Route anyway Add a rule

05 — Outcome

The week still contains the same work. It no longer waits for a person to start it.

Monday begins finished

The recurring run completes before the first person logs in. What is waiting is a short list of held items, not a full queue.

Exceptions became the job

People spend their attention on the items the agents could not settle — which is the part that needed a person all along.

The record stopped drifting

Because every decision is logged with its reasoning, the history is now answerable. Disagreements are settled by reading, not remembering.

Grading

Drag across the image

Ungraded frame
Graded frame
Ungraded Graded

Delivered

  • {{ d.label }}
{{ s.display }}

{{ s.label }}

Next project {{ nextTitle }} {{ nextBlurb }}