/neuronio ›› transmission 04 ›› process

Five phases
from signal to silence.

We're allergic to discovery decks and 12-week scoping exercises. Below is the actual rhythm of an engagement, start to handoff.

01 / probe

Listen

One-hour call. We listen for the seam — the place where humans are doing pattern-matching at scale. We say "no" if there isn't one.

▣ 1 day
02 / sketch

Specify

72 hours later: a written agent specification. Inputs, outputs, tools, eval criteria, failure modes, escalation paths. No mockups.

▣ 3 days
03 / probe

Prototype

Two engineers, two weeks. We build a working agent against real data, with the eval suite, and a candid memo on what we learned.

▣ 2 weeks
04 / build

Harden

Production deployment, observability, runbooks, on-call rotation, and a 30-day shadow period before traffic flips over.

▣ 6–12 weeks
05 / steward

Tend

Ongoing: drift monitoring, model migrations, prompt regressions. We hand off the keys when you ask, not before.

▣ ongoing

A working system. Source. Eval. Runbook.

  • Source code in your repo, your CI, your cloud. We don't gate on a SaaS.
  • An eval suite that runs on every commit and gates the deploy.
  • A 12-page runbook covering every observed failure mode.
  • Two of your engineers trained to operate and extend it.
  • Optional ongoing stewardship — you own the system either way.
engagement.tail active
D-0   signal   channel opened
D-1   discovery call · 60min
D-4   spec delivered · 8 pages
D-7   kickoff · 2 engineers assigned
D-14  prototype · running on real data
D-21  memo · candid go/no-go
D-28  harden phase begins
D-60  shadow traffic · 100%
D-90  cutover · agent online
D-120 steward handoff
// 02 principles

How we actually work.

/ rule 01

Eval first, prompt second.

We write the eval before we write the prompt. If we can't measure good, we can't ship good.

/ rule 02

Boring before clever.

If a SQL query, a regex, or a Zapier zap will do the job, that's what we ship. The agent shows up where reasoning is required.

/ rule 03

No mystery boxes.

Every decision the agent makes is logged with the prompt, the model, the inputs, and the rationale. Your auditor will love us.

D-0 starts the moment you open the channel.

Open a Channel