Huddle · living roadmap

The upgrade roadmap

Saturday, August 1, 2026 · waiting on Tim's v0.2 read

The running list of what the engine still needs, in priority order. We keep appending to this as feedback comes in. The rule from Friday holds: nothing below Tier 1 matters until the output is worth paying for.

Shipped in v0.2 (Fri): per-user isolation, onboarding-first, sales-site/app split, copy-paste fix, admin panel, $1 test signup. Sent to Tim & Melissa to test.
Tier 1 — Prove it works (the gate)
1

Content / output quality the whole ballgame

the #1 upgrade

Tim's verdict is still “generic.” The engine reads the page and applies templates; it has to produce genuinely site-specific, insightful work. Better generators, richer use of onboarding signal, real drafting where it counts — until this lands, it is a recommender, not a department. Plan (7/31): engine researches the real site + competitors and generates grounded content it's a recommender, not a department.mdash; no-LLM first (within the no-API rule); revisit a metered content-LLM only if still needed after Tim reads it. Focused build next session.

2

Connect real customer sites (the write path)

makes “approve” real off-clone

Approving a fix only ships live on our clones today. A real customer needs a connection — CMS credentials, a snippet/plugin, or a publish integration — before “approve” can touch their site. Tim named this: it's the difference between a tool and staff.

3

Connect the real polymagnet.com & measure impact

the proof

Run it on the real site and track actual traffic/rankings over time — the evidence that the value is real, not theoretical.

Tier 2 — Finish the architecture
4

Propagate the sales/app split to the other 17 engines

only the flagship has it

Each branded domain gets its own marketing page + auth-aware root.

5

Real marketing-page content

placeholders now

Real screenshots, a demo video, honest proof — replace the placeholder testimonial/video blocks on the splash.

6

Onboarding depth that changes the output

the “real hour”

Example customers, competitors, article ideas that measurably drive the work — not decoration.

7

Operating dashboard

metrics over time

Week/month/quarter movement, pending vs in-process vs done, and a clean way to feed the engine more info.

Tier 3 — Run it as a real business
8

Harden the account app for outside customers

before opening signups

Email verification, CSRF tokens, login/reset rate-limiting. (Fine for you two now.)

9

Admin panel depth

operate it

Cancellations, refunds, per-user activity, Stripe reconciliation on top of the accounts/payments view.

10

Billing lifecycle

real revenue

Dunning, failed-payment handling, plan changes/upgrades, receipts.

Tier 4 — Scale & polish (later)
11

Shipped-items ledger UX

thousands over years

Filtering, pagination, search — Tim flagged the list will get unwieldy.

12

Cross-domain SSO

one login everywhere

Same accounts today, but login is per-domain.

13

Reporting / email digests

the cadence users pick

Scheduled reports at the frequency chosen in Operations.

14

Second backup leg — Synology

needs DSM access

Lifelog is on B2 daily; add the NAS leg once SSH/rsync + a backup user are set up.

📌 Living list. We keep appending here as Tim's feedback and new needs come in. Add new items at the bottom of their tier; promote/demote across tiers as priorities shift.

Waiting on