Josh SolisJS Book an intro callBook a call

AI consulting: LLM evals, agents and computer vision

You get a working AI system and the tests that prove it. Fixed scope, a demo each week, and a hand-over your team can run.

I speak both sides. Years of sales and client work taught me to scope like a consultant. I build like an engineer.

I reply within two working days. NDA on request.

Dallas-Fort Worth · Oklahoma City · Remote and on site · 30-minute intro call

Four ways to start

Each offer has a fixed scope and a clear result. You get a quote after the intro call.

  • AI Feature Audit

    3 days
    For
    Teams with an AI feature that feels unreliable.
    You get
    A written review of the feature, its data and its tests, and a fix plan in priority order.

    See the proof: Harness Engineering

  • LLM & Agent Eval Harness Setup

    2-3 weeks
    For
    Teams that ship LLM or AI agent changes without proof.
    You get
    An eval corpus, a scoring function, a CI gate with JSON verdicts, and a runbook.

    See the proof: Harness Engineering

    More detail: LLM evaluation consulting

  • Computer Vision / AI Agent Prototype

    3-4 weeks
    For
    Teams that want to test an AI idea on their own data.
    You get
    A working demo with metrics and a clear go / no-go note.

    See the proof: Blueprint VisionCollectible ID

    More detail: AI agent developmentComputer vision consulting

  • AI Dev Workflow Setup

    1-2 weeks
    For
    Small dev teams that want to use AI coding agents safely.
    You get
    Agent rules files, a worktree workflow, a verify command, and session hand-off tools.

    See the proof: Agent Systems

    More detail: AI agent development

Services in detail

Each page answers common questions and links to the work that proves it.

LLM eval harness and AI agent evaluation consulting
I am an AI engineer and consultant. I set up LLM eval harnesses and AI agent evaluations for teams that ship AI changes without proof. Each change gets a verdict before it merges.
AI agent development consulting
I am an AI engineer and consultant. I build AI agent systems that run with small, revocable authority, and the evals that check them. I also set up AI coding agent workflows for small dev teams.
Computer vision consulting
I am an AI engineer and consultant. I build computer vision systems: object detection on drawings and documents, OCR, and near-duplicate image identification. I grade each model inside the product, not only on the training metric.

Four steps

  1. 1

    Intro call

    30 minutes. You tell me the problem. I ask about data, users and limits.

  2. 2

    Written scope and quote

    You get a short scope: what I build, what you get, the timeline and the price.

  3. 3

    Build with weekly demos

    I build in small steps. Each week you see a working demo.

  4. 4

    Hand-over

    You get the code, the tests and a runbook. Your team can run it without me.

Based in Dallas-Fort Worth. Clients in DFW and Oklahoma City.

I am an AI engineer and consultant based in the Dallas-Fort Worth area. I work with clients in Dallas-Fort Worth and Oklahoma City, and I can meet teams there in person.

I work remotely with teams anywhere, and I travel to work on site when it helps. Each week you see a working demo, so distance does not slow the work.

Most work is LLM evals and AI agent evaluation, AI agent systems, computer vision and construction takeoff tools.

Tell me what you are building.

30 minutes. Tell me what you are building. I reply within two working days. Client details can stay private under a mutual NDA.