HomeKiran Machha/fde-playbook
Forward Deployment Playbook

A Day in the Forward Deployed AI Engineer Life

How I operate inside customer engineering teams, security reviews, and production clusters to deliver working AI systems.

A deployment day, hour by hour

08:30

On site before the team. Read yesterday's run log and the overnight errors — I want to know what broke before anyone tells me.

Check
09:00

Stand with the operators. Watch the actual workflow being done, not the version in the process document. Note every exception they handle by hand.

Observe
10:30

Whiteboard with whoever owns the data. Where does this field come from, who is allowed to see it, and what happens today when it is missing?

Model
11:30

Build. Wire the tool, extend the agent, fix the retrieval that returned the wrong policy version this morning.

Build
14:00

Run it against real cases from their own data. Add the ones that fail to the eval set so the same mistake cannot come back quietly.

Evaluate
16:00

Show the operator, not the sponsor. Sit next to them while they use it and write down every hesitation — that is the real backlog.

Show
17:30

Rebuild what they hesitated over. Small, same-day changes are what earn the right to keep coming back.

Iterate
18:30

Write it down. What changed, what it cost, what is still open — a short note the sponsor can read in a minute and the next engineer can read in ten.

Record

Operating Rules I Work By

Ship something every day

A working ugly thing today beats a beautiful design next week. Momentum is what keeps an engagement alive.

Show the operator first

The person doing the work knows things no engineer will. If it does not survive their desk, it will not survive the rollout.

Escalate rather than guess

Below the confidence threshold, the system asks a human. In a regulated estate a wrong answer costs more than a slow one.

Leave evidence

Every run logs its prompts, tools, results and errors. If an auditor cannot replay it, it is not finished.

Build to hand over

The engagement ends with their team running it — documented, tested and owned by someone who is not me.

Discover, Prototype, Show & Iterate

Monday

On site. Back-to-back stakeholder interviews. Understand the workflow and who owns each step of it.

Discover
Tuesday

Whiteboard the domain. Sketch the object model. Identify the datasets the system actually needs.

Model
Wednesday

Pair with their data engineer to pull the first export. Stand up the pipeline and the retrieval layer.

Plumb
Thursday

Build the first working version of the operator's app and put it in front of them the same afternoon.

Prototype
Friday

They disliked the layout. Rebuild it, then show the sponsor something that runs end to end before the week closes.

Iterate
Cadence:DiscoverPrototypeShowIterate

Seven Concrete Tangibles Produced

01A problem statement the customer signs off on.
02A domain model — objects, links and actions — of their business.
03Data integrations from their source systems.
04Operational applications that their people use daily.
05A deployment in their production environment, on their infrastructure.
06An evaluation set and the runbook to keep quality honest.
07A trained customer team that can run it without me.