Approach

Six phases. Every project, every time.

How an engagement actually runs, by week. Calendar is published before the contract. There are no “TBD” phases, no discovery that bills for ten weeks, no surprise change orders in week four.

A typical six-week Agent Build
Phase
Wk 1
Wk 2
Wk 3
Wk 4
Wk 5
Wk 6
Assess
Shape
Build
Harden
Pilot
Adopt
Kickoff MondayCalendar set in writingHandoff & 30-day support
Phase 01 / Week 1

Assess

On site with the team. Watch the work. Decide what is worth building.

We do not start in a workshop. We start at a desk, on a couch, on a job site, watching the actual person do the actual task. Half the projects we kill at this stage. The other half come out with a sharper scope than the client walked in with.

What you give us
  • Two hours with leadership
  • Access to one team for shadowing
  • Sample documents or call recordings (anonymized fine)
What you get back
  • A scored opportunity list
  • A written 90-day plan
  • An honest go / no-go recommendation
Phase 02 / Week 2

Shape

Write the evals before the agent. Define what right looks like.

We pull 100 to 300 real historical examples and label them. This is the unglamorous week that decides whether the project succeeds. Without an eval set, you do not have a project, you have a vibe.

If you can’t describe success on a spreadsheet, you can’t build for it. Week 2 is the spreadsheet week.
Phase 03 / Weeks 3–4

Build

First working pass. Crude but end-to-end.

By the end of week three you have a working agent on a staging URL. It is not polished. It is end-to-end, and we can run it against the evals and see exactly where it fails. That failure list is the build plan for week four.

What ships in this phase
  • The agent itself, wired to your stack
  • An eval dashboard, updated nightly
  • A short Loom walking through it
Phase 04 / Week 4

Harden

Tool calls, retries, cost ceilings, observability.

Most agency projects quietly stop at the “works on a happy path” phase. Week four is the part nobody photographs: rate limits, fallback prompts, partial-failure handling, audit logs, daily cost ceilings, alerting when the model drifts. This is what makes the system survive contact with a real Tuesday afternoon.

Phase 05 / Week 5

Pilot

Live with two or three real people. Measure friction.

We pick two or three actual end users (not managers) and put the system in front of them for a week. We watch what they do, where they go around it, where they distrust it. The thing we ship in week 6 is shaped by what week 5 tells us, not by what looked good on the demo.

Phase 06 / Week 6 + 30 days

Adopt

Handoff, training, 30 days of running support.

We write a runbook your team can actually read. We train a named owner. We sit in your Slack for 30 days, on the house, watching the metrics and patching the small things that surface in real use. Then we get out of the way. The point of the engagement is that you do not need us afterwards.

Working principles

How we operate, regardless of the project.

Five rules that have not changed since the practice opened.

01

Evals before code.

If we can’t measure right, we don’t build right. Every engagement opens with a labelled dataset.
02

Ship to one user first.

No rollout without a single named pilot user who can break it for us.
03

Default to your stack.

We use what your team already runs. We’ll add one new tool at most, and only if the payoff is obvious.
04

Show your data, never train on it.

We sign DPAs. We use enterprise endpoints. Your data does not leave Canadian or US regions without your written ok.
05

The off-ramp is a deliverable.

Every project ends with a handoff doc so you could replace us with another vendor on a Monday morning.
Ready to start

A calendar before a contract.

We write the calendar before we sign. If the dates don’t work for either of us, that conversation happens before any money moves.

Book an intro See pricing