Brain 2 · 2026-04-20 · 3:00 PM CT

Atlas Mynd × Rent Responsibly / DoubleCheck Verified

Working session. DoubleCheck-first Phase 1 scope, live demo, and a written boundary before we hang up.

Dave Krauss Patrick Arata Will Lucas Justin Rodermond
Today's flow · 6 stops
  1. 1
    Pivot ack
    DoubleCheck-first. Confirm.
  2. 2
    What we heard
    4/14 in your own words.
  3. 3
    What we've built
    Briefs, intel pack, stack.
  4. 4
    Live demos
    Slack bot + Claude Code.
  5. 5
    Phase 1 scope
    The boundary, in writing.
  6. 6
    Next steps
    Who owns what, by when.
Section 01

The pivot,
acknowledged

"Let's start with DoubleCheck Verified first — smaller deployment, lower risk, cleaner way to get set up before touching the RR team."
— Dave, via text, 2026-04-20

What this changes. Pat is the primary champion and daily operator for Phase 1. Dave stays exec sponsor, part-time. Alexa is out of scope until Phase 2 — when a win story exists to hand her. The $3M DoubleCheck raise makes the budget path cleaner too.

Our honest read

DoubleCheck-first is actually stronger positioning. A 1.5-FTE team with a technical-fluent lead and a clear workflow surface (inspections) is a cleaner place to prove the pattern than a 10-person service org with an AI skeptic at the COO seat. We'd rather earn RR via a DoubleCheck win story than cold-pitch Alexa.

How this got into the brain: Dave's text on the morning of this call. Pre-call brief was rewritten to reflect it. See the artifacts ↓

Section 02

What we heard
on 4/14

Fully transparent — these are the moments we wrote down as the ones that changed how we're going into today. In your words, not ours. Verbatim from the call.

Our north star now
"Why didn't you start here, Will?"
Dave, on seeing the brain-generated prep doc.
The commitment
"Let's assume we're going to be early adopter, like a pilot slash design partner."
Dave.
The stakeholder map in one sentence
"Pat is going to be your CTO, for lack of a better term. I will be the 'let's go right now, what could go wrong' — and Alexa will be 'everything could go wrong.'"
Dave.
The economic anchor
"Get rid of it. Get rid of it. Get rid of it."
Dave, on Quorum ($16K/yr) — a Phase 2 signal.
The bar for Phase 1
"Show me, don't tell me."
Dave. Architecture diagrams were rejected; the live bot was requested.
The framing we're designing against
"This sounds like the Jetsons, but we don't have flying cars right now because it just, like, defied gravity. We're going to need some level of show me, don't tell me — not signing up for a 12-month relationship."
Dave. The bar for Phase 1 is incremental, reversible proof — not a big promise.
What landed
  • Live Slack bot demo
  • The brain-generated prep doc
  • "Everything is yours" transferability
  • Triple hybrid retrieval (the CA jurisdiction example)
  • Tweet curator (Dave immediately wired it to his own workflow)
What didn't
  • Architecture diagrams ("why didn't you start here")
  • Leaderboard / gamification — Pat: "not going to fly with us right now"
  • Full STR regulatory database (market too small, ~5 orgs)
  • Agentic workflows (sandbox not ready; we said so)
What we still need to prove
  • Phase 1 is reversible — you keep everything if it doesn't land
  • Pat can maintain it without writing code
  • A result Alexa can't pick apart (Phase 2 gate)
  • Scope discipline — under-commit, over-deliver
Section 03

What we've built
since 4/14

Two stacks worth seeing. The first is what we made for you. The second is what we've made for ourselves using the same system — because we wouldn't sell you something we aren't running on.

3a

Built for Rent Responsibly / DoubleCheck

Pre-call brief · 2026-04-20
Today's briefing on you

Generated by /pre-call-brief. Caught the DoubleCheck pivot (after Will patched the texts in manually). Sent to our inbox.

📧 Will to open live in Gmail
Internal debrief · 4/14
Every quote you just saw

Generated by /post-call-debrief. 5 quotable moments, stakeholder map, assessment, red flags — fully transparent.

✍ See Section 02 above
Follow-up email · draft
What we would have sent

Drafted retrospectively. "Show don't tell" + start-small framing. Sits in Will's Gmail drafts, unsent — today's call is the better version.

📧 Will to open live in Gmail drafts
Intelligence Brief · Live site
Your market, your bottleneck, your first win

Five parallel research deliverables + exec brief. ~10 minutes of agent work. Deployed to Cloudflare. Dave can use it in raise conversations or a Phase 2 Alexa pitch.

→ Walkthrough in Section 04
Integration scoping · Justin
Your 12-tool stack, tiered

Pat's tool list, mapped against MCP availability. Five tools ready on Claude Team today; four thin wrappers; one unknown (Comparent — Pat, what is this?).

→ See Section 08
Stakeholder briefs
Alexa Nota · Jake

Enriched automatically when the debrief ran. Alexa: journalism background, just handed off the 6-year RR newsletter — bandwidth signal. Jake: Pat's ex-NoiseAware shadow reviewer.

🗂 Referenced inline; not surfaced externally
STR regulatory change brief · 4/20
The Quorum-replacement prototype

Weekly change digest — 5 enacted (Phoenix ADU, Decatur AL, Ocean City MD, Riverside CA, Columbia Falls MT), 3 in-committee, 2 platform updates (Airbnb ToS, VRBO fees). Manual v0.1; shows the shape.

📜 Phase 2 demo material — not pitched today
3b

Built for Atlas Mynd — because we run ourselves on the same stack

Dave, you said you want Rent Responsibly to be one of the best AI users in the world. Here's what that looks like for us.

Atlas Mynd Brand Book
↗ atlas-mynd-brand-book.pages.dev
Interactive brand specification

Color palette, typography, mark system (the asymmetric constellation at the top of this page). Auto-deployed. Same pattern we'd ship for RR's brand system if that's ever in scope.

Atlas Mynd Dashboard
↗ dashboard.atlasmynd.ai
Justin's observability layer

The operational view into the brain — updates, activity, skill usage. Prototype of the "visible brain" every client deployment gets on top of the chat surface.

The Atlas Mynd brain
live · Claude Code + Slack
The substrate everything else is on

Every artifact you've seen was generated from this. Will's going to load it live in Section 07 and you'll see every open founder decision we're running against today.

The live Slack bot
live · Atlas Mynd workspace
What your team would use daily

Five real queries queued for Section 06. Dave, you saw this on 4/14 — Pat, this is the primary surface Phase 1 delivers. Everything else is scaffolding.

We wouldn't sell you something we're not running on ourselves. Everything above is in production for Atlas Mynd today.

Section 04

Intelligence
Brief

A design-partner briefing pack, not a cold pitch. Five research deliverables + executive brief. ~10 minutes of agent work, drawing from the Atlas Mynd brain plus public sources.

Open the Intelligence Brief
01 · Competitive Position

The 18–24 month first-mover window in the alliance layer. AI adoption in your direct competitive space is structurally zero.

02 · Workflow Capacity

~142 hrs/week of AI-assistable work across your team. ~3.5 added FTE of capacity without hiring.

03 · Regulatory Advantage

3,500–5,000 active local STR regimes. Your interpretation moat — the hard 90% that Quorum/FiscalNote don't touch.

04 · Talent Pressure

Why augmentation — not hiring — makes the 50-association vision arithmetic instead of aspirational.

05 · Thirty-Day Win

The DoubleCheck Inspection Knowledge Brain — Slack bot + Pat's folders. ~15 hrs/month returned; break-even on pricing by design. The Phase 1 return isn't economic. It's the pattern proof that justifies Phase 2.

Numbers are estimates with conservative bands — flagged as such throughout the brief.

Section 05

The skills
behind all this

Each skill is a markdown prompt — version-controlled, transferable, inspectable. Three of ours produced everything you've seen today.

/pre-call-brief
Today's briefing

Pulls from brain + web search + SEC EDGAR + LinkedIn. Caught that Dave's surname has two s's. Missed the DoubleCheck pivot because SMS isn't in the brain yet — Will patched it manually.

Lesson captured → skill roadmap updated.
/post-call-debrief
The 4/14 debrief

Processed the 4/14 transcript into a debrief, a follow-up draft, and enriched stakeholder pages (Alexa Nota, Jake). Auto-researches every new name mentioned.

Feeds back into pre-call accuracy loop.
/prospect-intel
The Intelligence Brief

Spawned five parallel research agents, composed the executive brief, deployed it to Cloudflare Pages with the --publish flag. ~10 minutes start to finish.

Also supports password-gating (disabled here by choice).

When you take over the brain, these skills come with it. Fork, edit, and make them yours.

Section 06

Live demo
· Slack bot

Five real queries Will will ask, live, on screen-share. If one falls flat, that's real data — we flag and fix.

Action: Will tabs to Slack. Expand any query below for why-this-one rationale.

What's Patrick Arata's background?
Tests structured retrieval across the client page + stakeholder brief. Should surface: NoiseAware → Frontdesk (SVP Real Estate, 10K rentals + 40K hotel rooms) → RR/DoubleCheck Sept 2025. Non-programmer who ships with Claude + Railway.
Summarize DoubleCheck Verified's business model — what's the $2.50/transaction play?
Cross-source synthesis. Proves the brain knows the strategic context Pat and Dave live in — inspection platform + exchange rights + the wedge economics if Vrbo/Airbnb adopt the standard.
What did Dave say about Quorum on the April 14 call?
Transcript retrieval with verbatim quote. Should return "get rid of it, get rid of it, get rid of it" and cite the 4/14 transcript. Demonstrates the brain doesn't just paraphrase — it can recall precisely.
What's the biggest risk in the DoubleCheck Phase 1 pilot?
Reasoning over our own debrief. Should surface Pat's predecessor scar tissue and the "under-scope every commitment" rule we wrote for ourselves. The brain pushing back on its own overreach.
List every open founder decision in the Atlas Mynd brain right now.
Meta-query. Shows the discussion queue — the brain is the operational backbone of the company, not a content vault. This is what Dave's CEO brain would look like when he checks it on Monday morning.
Section 07

Live demo
· Claude Code

Two prompts. The first is how Will starts every Monday. The second is a test of whether the brain can push back on its own people when they're over-committing.

1
Will types…
> load the brain
What happens

Claude Code follows the brain's startup protocol: reads the company CLAUDE.md, loads firm/memory.md and firm/decisions/pending.md, asks "Who's working today — Will or Justin?", then prints every open founder decision, grouped by type.

Why this is worth a minute: the brain is a working artifact, not a demo. This is Will's Monday morning — 20+ open decisions, visible on screen, ready for action.

2
Then Will asks…
> Given Pat's predecessor scar and Dave's "show me, don't tell me" bar, write the narrowest possible Phase 1 DoubleCheck scope — one Slack channel, the Drive folders, the people, and a 30-day success metric. Push back where I'm over-committing.
Why this one

First-principles reasoning over the brain's content plus our writing-style rules for external deliverables. Pat and Dave watch the brain help us under-commit to them — exactly the posture they told us they want.

Live theater — if the model misfires on screen, we'll walk through it together. That's also transparent.

Section 08

The integration
map

Justin's scoping of Pat's 12-tool list, reshaped for DoubleCheck-first Phase 1.

Tier 1 · Ready today
Official MCPs on Claude Team
  • HubSpot
  • Stripe
  • Airtable
  • Fireflies
  • Google Drive
  • Slack
Plug-and-play once you're on Claude Team.
Tier 2 · ~3–4 days custom
Thin MCP wrappers we'd build
  • Hivebrite · plan-tier risk
  • AirDNA
  • Wheelhouse
  • Zoom · likely redundant with Fireflies
Each API exists; we just wrap it.
Tier 3 · Needs clarification
One unknown
  • "Comparent" — Pat, what is this?
Not on the public tool landscape under that name — we want to make sure we scope it right.
Phase 1 · DoubleCheck MVP
Slack (1 channel) + Drive (3–5 folders Pat picks) + DoubleCheck-specific Airtable bases + Fireflies for DoubleCheck meetings

Everything else in the 12-tool stack stays out of scope for Phase 1 — we'd rather fully resolve a narrow surface than half-wire everything.

Honest flag: Hivebrite plan tier is the single biggest technical risk for Phase 2 — API access is gated. Pat, can you confirm the plan tier before we promise a timeline?

Section 09

Phase 1
scope · today

The most important block on this page. We leave the call with this boundary in writing, or we've fallen short of what we came here to do.

The boundary
Deployment posture (repeat for comfort)

Sub-account in your name, fully transferable, no SaaS lock-in. If the pilot doesn't earn Alexa's confidence, you keep the brain and we walk away. That's the whole "everything is yours" principle in one line.

Three deliverables we promise for the 30-day pilot (conservative on purpose)
01

Slack bot live against the scoped corpus. Working, observable, in Pat's hands.

02

A short retrospective in Pat's voice — the artifact Dave can hand Alexa when Phase 2 comes up.

03

A written Phase 2 scope doc naming exact folders + workflows + guardrails for the RR extension.

Section 10

What happens
after this call

Predictable cadence. Small weekly check-ins. A retrospective that earns Phase 2 — or doesn't.

Today
Written Phase 1 scope Pat signs off on — Slack channel, Drive folders, bot access list, 30-day window, Phase 2 trigger.
This week
Atlas Mynd stands up the narrow MVP — Slack bot wired to the scoped corpus. Sub-account provisioned in your name.
Weekly
15-minute check-in — Pat reports what's working / not. We iterate. No slide decks.
Week 4
Retrospective + Phase 2 scope doc — two artifacts teed up for the Alexa conversation (or the "we walk away" conversation — both are honest outcomes).
Phase 2
Conditional on Pat's retrospective + Dave's green light. RR extension scope, Quorum replacement test, alliance-management overlay — all sit behind that gate.
Will owns
  • Phase 1 scope doc (today)
  • Dave relationship cadence
  • Phase 2 trigger language
Justin owns
  • Sub-account + MVP stand-up
  • Bot wiring this week
  • Integration build-outs
Pat owns
  • Slack channel + Drive folder picks
  • Part-timer names for bot access
  • "Comparent" clarification
  • Hivebrite plan-tier confirm
Dave owns
  • Exec sponsor cover
  • Phase 2 trigger sign-off
  • Timing of Alexa loop-in