SERVICE · 02
Custom AI builds.
You have a specific problem an LLM should solve. I scope it, design it, and ship working software to your repo — 2 to 6 weeks from brief to live in production, depending on scope. Not a demo. A system, with evals.
- price
- from $25k
- build time
- 2–6 weeks
- output
- live in your repo
- handoff
- + 30 days of me
- cap
- 1 build at a time
WHAT YOU GET
Six things. Every build.
A scoped system spec
Day one. A document that names exactly what we are building, what we are not, and the eval that proves it works.
Working software in your repo
On your stack — Postgres, TypeScript, Python, your existing infra. Reviewable PRs, not zip files. No Lambda graveyard.
Eval suite and monitoring
Every prompt has an eval. Every eval has an alert. You catch model drift before your users do.
Versioned prompts and ops docs
Prompt history under source control, a runbook for the first 90 days, and a one-pager your team can extend from on day 31.
30-day live partnership
I stay on after ship. Bug triage, prompt tweaks, the first real eval failures — then I hand off cleanly.
A second opinion before we start
If the plan is wrong, I will say so on the call. I do not do month-two pivots.
ESTIMATOR · UPDATES LIVE
Price your build in 6 taps.
A price range, a timeline, and a starting point we can both work from. The binding quote arrives 48 hours after our call.
What kind of build?
Scope of the system
Integrations needed
OPTIONALExpected request volume
Timeline
Add-ons
OPTIONALFAQ
Direct answers.
What can't you build? +
Anything that needs a model I cannot access. Anything that requires fine-tuning on more than 100k examples — I will refer you to someone who specialises in that. And anything where the right answer is "just write a regex".
Why two weeks? Most agencies say three months. +
Most agencies bill an account manager, a designer, and a project plan template. I bill a brief and a stack of agents. I scope tight — if the system genuinely needs three months, I will say so on the call and recommend someone else.
What stack do you use? +
Your stack. I build in TypeScript or Python on Postgres, pgvector, and your existing infra. No new SaaS to subscribe to. No Lambda graveyard to inherit.
What happens after the 30 days? +
Three options: clean hand-off; monthly retainer for tweaks and evals; or roll into another sprint. About 60% of clients pick the retainer.