Seattle Tech Week · July 27–31, 2026

Bring one workflow.
Leave with it running.

I'm Paul, founder of Nicia. If we talked at Tech Week — or you took a card and we never got the chance — this is what I'd rather do than send you a deck. Bring one thing you do by hand, or one thing your AI only does on your laptop, and we rebuild it on the call as a governed agent your whole team can run.

Book a 30-min teardown

In person around Seattle or remote · Or email paul@nicia.ai

your laptop, today
~/work $ claude /weekly-account-review
reading 14 accounts…
drafting summaries…
done in 6m 12s
⚠ runs only on your machine
⚠ nobody else can trigger it
⚠ no record of whether it was any good
30 minutes
nicia — Account Review AgentLive
Pulled 14 accounts
1.4s
Applied your review rubric
0.6s
Drafting summaries
running
Human approval gate
queued
Runs on
Schedule
Budget
$5 / run
Scored
Every run
What actually happens

Thirty minutes, three things.

This is a working session, not a demo. I share my screen, you share the workflow, and we ship something real before the call ends.

  1. 010–5 min

    Pick the one thing

    The report you rebuild every Monday. The research pass before every call. The review nobody has time to do twice. We pick whichever one costs you the most time and has the clearest definition of done.

  2. 025–20 min

    We build it live

    Your prompt, script, or Claude Code skill goes in as-is. We wrap it with the parts that make it safe to hand to other people: a budget, a data policy, an approval gate, and a written definition of what a good result looks like.

  3. 0320–30 min

    Run it, score it, keep it

    We run it on real inputs, score the output against that definition, and look at what the evaluation says to change. You leave with the agent in your own workspace — schedulable, shareable, and yours.

What you walk out with

Four things, not a follow-up email.

An agent that runs without you

It lives in your workspace, not on my laptop. Put it on a schedule, trigger it from an event, or hand the link to a teammate who has never seen a terminal.

A written definition of done

The rubric we write together becomes a reusable success contract. Every future run gets scored against it, so quality is a number you can watch instead of a feeling.

Guardrails you can show your boss

Budget cap per run, a policy for what data it may touch, an approval gate before anything irreversible, and an audit trail of every action and why.

The first improvement, already proposed

The evaluation doesn't just say pass or fail — it says what to change. You'll see the first proposed patch to the prompt or the rubric, with the evidence behind it, before we hang up.

Fit check

Is this actually worth your time?

I'd rather you skip the call than sit through one that wasn't for you. Here's the honest read.

Book it if

  • You already have prompts, scripts, or Claude Code skills that genuinely work for you
  • Other people keep asking you to run them, and that doesn't scale
  • You lead a team where several people do the same work slightly differently
  • Someone will ask about budget, data access, or an audit trail before this touches production
  • You've handed a workflow to a teammate before and watched it not survive the trip

Skip it if

  • You want an overview of what AI agents are — I'd be wasting your time
  • You're shopping for a chatbot over your docs
  • You want me to invent the workflow for you — bring one you already do by hand
  • You need paperwork before a working session (email me and we'll start there instead)
  • You want to argue about AGI timelines — genuinely fun, wrong call, buy me a beer instead

Not sure which column you're in? Send me the workflow in two sentences: paul@nicia.ai

Who you're meeting
Paul Dlug
Founder, Nicia AI

I live in Bend, Oregon. Seattle is the city I keep coming back to — close enough to drive, far enough that I still notice how good the coffee is. Fair warning: I'm from a town where strangers make eye contact and start conversations. I'm told that isn't how it's done up here. I'm going to do it anyway.

You get me for the whole 30 minutes — no SDR, no handoff, no "let me loop in a solutions engineer." I'm the one who writes the code, so if the thing you need doesn't exist yet, you'll get a straight answer about that too.

Home base
  1. Bend, OR
    where the laptop lives
  2. Seattle, WA
    home away from home

~330 miles · about six hours · one podcast about databases

What we're building

Models are good enough. The missing piece is the operating layer between "works for me" and "works for the team": shared state, policy, evidence, and improvement that a human signs off on.

Nicia Platform
Runs your agents for the team — budgets, policy, approvals, audit, and evaluation-driven improvement you approve before it ships.
TypeGraph
The typed knowledge graph underneath, so agents read structure instead of guessing from a pile of text.
Corpus
Versioned context your non-engineers can actually edit, served to agents over MCP.
House rules

Coffee's on me

Anywhere except the original Starbucks. That's a forty-minute line for a cup you can get, better and sitting down, two blocks up the hill.

Weather is not a problem

If it's raining, nothing about this changes. If the mountain is out, the whole city goes outside and we get the place to ourselves.

One thing I won't build

Your agent is not writing LinkedIn posts. It could. The technology is right there. Please don't make me part of that.

The workflow you're thinking of right now
should be running without you.

Grab whatever slot suits you. I'm around Seattle this week and on a calendar the rest of the time.

Book my teardown

No charge, no deck, no follow-up sequence.

Calendar full or you'd rather write first? paul@nicia.ai

Live agent teardown
30 min with the founder · no pitch
Book