Josiah Bujanda / AI Product Manager

Four years owning 0-to-1 AI products. Ten years leading high-stakes commercial work.

I own two products end to end. Stem is a local-first AI agent with real users, an eval ledger, and a shipped roadmap, and I write the Playbook from its logs. The bid-review desk surfaced $221,915.70 in missed margin and estimating errors across $3,442,234.02 of live commercial bids, every finding linked to source evidence and held for human approval before it reached a customer. Before either, ten years leading high-stakes commercial developments where a missed milestone carried liquidated damages, which is where the habit of grading work before it ships comes from.

Stem The Playbook The review desk

0-to-1 Product Development · Product Strategy · Agentic AI · Evaluation · High-Stakes Execution

The Work

Two products.

01 / Production AI

Stem

A local-first AI orchestration harness I designed and run daily: a chat interface, an eval ledger that grades every output, a retrieval vault, a voice loop, and a constitution that lets it improve itself. The requirements, the evals, and the iteration loop are mine.

See the product page

02 / Shipped Product

10 iOS apps

Mostly AUv3 audio instruments, built with AI assistance and mined into a seven-phase build pipeline I now teach from. Perihelion is in App Store review right now.

See the build log

What I Bring

Six things I do on a product team.

Each one links to the artifact that proves it, or tells you it's on the way.

01 / Context and system design

Give the model the right context

I write the context a model needs before I ask it for anything, the same discipline that turns a vague RFI into a decision someone can actually act on.

What the Model Sees

02 / Evals and quality gates

Grade the output before it ships

Every output Stem produces gets graded against a ledger before it ships, the same instinct that made me itemize $221,915.70 in the review desk before it ever reached a client.

Own the Definition of Good

03 / Model selection in production

Route by cost and consequence

Different tasks earn different models. I route by cost, latency, and what a wrong answer would actually cost the person waiting on it.

The 300 Second Write

04 / Agent orchestration

Know when to fan out

I know when to fan a task out across cheap agents and when to keep it on one thread, because the wrong call burns tokens and still hands back the wrong answer.

Three Scouts in 47 Milliseconds

05 / Domain operations

Read the drawing, find the leak

Ten years leading delivery on commercial developments where a missed milestone carried liquidated damages taught me where the money leaks on a job and who has to be in the room when it does. That judgment is the whole reason the review desk works.

Read the review desk The record

06 / Shipping

Ship it, then ship the next one

Ten user-facing iOS products, primarily creative audio tools, and Perihelion, a standalone and plugin synthesizer taken through App Store submission.

See the build log