// verdict #14 · 28 May 2026 · 14:33 UTC

google.omni.com/

PASS

three or more voices said no. release without guilt.

submitted by Rob · BLKOUT · model anthropic/claude-sonnet-4 · against wishlist of 2026-04-27T11:18:37z · visit the tool → · back to history

// the four voices, in parallel

What the Council said

// 01 · critic

Baldwin

pass

technical risk, lock-in, sequencing — the master's tools.

**FETCH FAILED — CANNOT EVALUATE** The page at https://google.omni.com/ could not be reached (422 Unprocessable Entity error). I cannot evaluate a tool without knowing what it actually does, what data it collects, how it operates, or what dependencies it creates. This is precisely the kind of situation where rushed adoption creates problems later. Without being able to examine: - The actual functionality and scope - Data collection and privacy practices - Pricing model and vendor lock-in risks - Technical requirements and operational overhead - Whether it violates any Year One guardrails ...there's no responsible way to recommend adoption. **SPECIFIC CONCERNS:** The URL pattern `google.omni.com` suggests this might be a Google product or service, which immediately raises questions about: - **Data sovereignty** — Google's business model is built on data extraction - **Vendor lock-in** — Google has a history of discontinuing services users depend on - **Surveillance mechanics** — Any Google tool needs extra scrutiny against BLKOUT's values But without being able to see what this actually is, I can't assess whether those concerns apply or whether it might somehow align with the wishlist priorities. **THE PRINCIPLE:** BLKOUT is building foundational infrastructure with a small team. Every tool adoption should be deliberate, not speculative. The **"Infrastructure before application"** guardrail means getting the basics right before adding complexity. Come back when the page is accessible and the tool can be properly evaluated against BLKOUT's actual needs and constraints. **RECOMMENDATION: PASS**

// 02 · ethicist

Murray

hold

values, sovereignty, community benefit.

I cannot evaluate this tool because the page fetch failed with a 422 error — the URL https://google.omni.com/ was not accessible through the content reader. Without being able to examine the actual tool, its functionality, data handling practices, or terms of service, I cannot make a responsible assessment against BLKOUT's values framework or determine how it maps to the wishlist items. This is particularly important given BLKOUT's commitment to data sovereignty and anti-surveillance principles. Any tool evaluation requires understanding: - What data it collects and how it's processed - Whether members retain control over their information - If it introduces surveillance mechanics disguised as features - How it aligns with the community benefit mission - Whether it supports or undermines transparency principles The URL structure suggests this might be a Google product, but I won't speculate based on the domain name alone. Google's track record on data sovereignty and surveillance capitalism would raise immediate red flags if confirmed, but that assessment requires seeing the actual tool and its implementation. To properly evaluate this resource, we would need: 1. A working link to the tool's documentation 2. Clear description of its functionality and data practices 3. Terms of service and privacy policy review 4. Understanding of how it would integrate with BLKOUT's existing CRM schema and member-controlled data principles RECOMMENDATION: HOLD

// 03 · builder

Rustin

pass

vibe-codeability, stack fit, lift — what'll actually ship.

I cannot evaluate this tool because **the page fetch failed completely**. The URL `https://google.omni.com/` returned a 422 Unprocessable Entity error, which means either: 1. The URL doesn't exist or isn't publicly accessible 2. The domain is misconfigured 3. There's a typo in the URL provided Without being able to read the actual page content, I have zero information about what this tool does, how it works, its technical requirements, pricing, or whether it even exists. I won't guess based on the domain name or make assumptions. **VIBE-CODEABILITY**: Unknown — can't assess documentation or DX **STACK COMPATIBILITY**: Unknown — can't assess infrastructure needs **SPEED OF DEPLOYMENT**: Unknown — can't assess onboarding **LIFT ASSESSMENT**: Unknown — can't classify effort level **MAINTAINABILITY**: Unknown — can't assess operational overhead **INTEGRATION POTENTIAL**: Unknown — can't assess API or connection methods **GUARDRAIL CHECK**: Can't verify against any guardrails without knowing what it does For a proper evaluation, I'd need either: - A working URL to the actual tool - Direct paste of the page content - Clear description of what the tool is supposed to do This isn't about being cautious — it's about having literally zero data to work with. A builder's job is to assess real tools, not phantom ones. RECOMMENDATION: PASS

// 04 · inclusion

Rivera

pass

reach, the under-served, who's on the street.

**FETCH FAILED — CANNOT EVALUATE** I cannot reach the page at https://google.omni.com/ — the fetch returned a 422 error, meaning the URL is either invalid or the content is not accessible through standard web scraping methods. Without being able to see what this tool actually is or does, I cannot evaluate it against inclusion criteria or BLKOUT's guardrails. I will not guess based on the URL structure or make assumptions about Google products. **What I need to proceed:** - Working URL to the actual tool - Clear description of what the tool does - How BLKOUT would use it - What problem it's meant to solve **Why this matters for inclusion analysis:** I can't assess accessibility floors, privacy architecture, or reach implications for a tool I can't examine. The most excluded communities are often the ones most harmed by tools that get adopted without proper scrutiny — I won't rubber-stamp something sight unseen. **For the submitter:** Please verify the URL and resubmit with accessible content, or provide a working alternative link to the tool you want evaluated. RECOMMENDATION: PASS

// context at time of judgement

The Wishlist, as it was then +

this is the document the council was asked to hold this tool against. click to expand.

BLKOUT Digital Strategy — Living Document

This document is the authoritative context for the Dreamcatcher Council. It combines BLKOUT's Year One guardrails with the fifteen-item wish list. The Council reads this fresh on every evaluation — edits here immediately reshape every future verdict.

Last revised April 2026. For board and community input.

Year One Guardrails

Rules that hold while foundational infrastructure is being built. Harder than tier priorities — these do not negotiate.

— No n8n. All automations use node-cron or Supabase triggers. n8n was tried and removed; the operational cost of a workflow engine outweighed the benefit for a small team.

— Schema ownership. The CRM's 001_crm_complete_schema.sql is authoritative. Any new tool that touches member data reads from CRM tables — it does not maintain a separate schema.

— Pre-order model, not always-on store. The BLKOUT shop is a waiting-list / pre-order surface with CBS tiers (free / £3 per month / £10 per month). Tools that assume always-on e-commerce are a category mismatch.

— Stripe pre-flight. Stripe routes stay disabled until credentials are confirmed in Coolify. Test mode only — no tool that requires live payment provisioning on adoption.

— CRM mock data stays until migrations verified. Nothing removes CRM mock data until the equivalent migration has been confirmed via supabase-query.mjs. Tools that auto-migrate are held until verification is possible.

— RSVP and Stripe are already built. Frontend and backend exist in the platform. Tools that duplicate these are a category mismatch — the gap is credentials and tables, not code.

— Infrastructure before application. Debug infrastructure (CPU, disk, running services, Docker images) before application code. Tools that add operational complexity must justify themselves against this order.

Wish List — fifteen capabilities

Prioritised by potential impact and capacity to instigate change. First draft March 2026, living document since.

Tiers: do now (accessible) — plan and build (moderate lift) — develop with intent (significant undertaking)

Categories: infrastructure — member experience — co-production

Tier 1 — do now

High impact, low barrier — no dependency blockers.

— AI policy, à la New Public infrastructure accessible Unlocks the integrity of everything beneath it. Determines what BLKOUT will and won't do with AI, and why. Data sovereignty and privacy follow from this document, not the other way around. Mainly a thinking and writing exercise — the hardest part is the thinking.

— CRM — values-embedded member system member experience accessible Already in active use. Develop with transparency and member control principles baked in before habits calcify around the wrong defaults. Needs connecting to member pages, AIvor, and the directory as those mature.

— Leania.ai — AI ops audit infrastructure accessible Quick diagnostic of workflows, tools and bottlenecks. Keep / kill / replace / automate recommendations. Low cost, high information value. Caveat: recommendations will skew commercial — use the diagnostic layer, not the prescription.

— Tech stability and system resilience infrastructure moderate lift Without this, everything built on the infrastructure will fail. The VPS, Coolify, and all modules need to be reliable and recoverable before more is added. Foundational before ambitious.

Tier 2 — plan and build

High impact, requires resourcing, people or sequencing.

— Bookkeeping, financial regulations and fundraising infrastructure moderate lift CBS obligation, funder pipeline active. Needs the right person as much as the right tool — the Treasurer role is load-bearing. Required before significant grant income flows through the organisation.

— Compliance infrastructure — demonstration not monitoring infrastructure moderate lift Mission risk if left too long. Evidence of governance, financial stewardship, and community benefit must be buildable in real time, not reconstructed after challenge. Systems need building before they are needed.

— Regular events calendar and Brunch 2030 member experience moderate lift Visible, reliable rhythm signals organisational health. Monthly social, film screening at The Arzner, community organisers gathering, seasonal specials, Berto Pasuka day. Key venue relationships held — Stanley Arts, The Arzner. Delegate the programming.

— Non-intrusive lead generation member experience moderate lift Community-appropriate discovery. Transparent about the win on all sides. Values-consistent methodology — games welcome if honest, surveillance mechanics excluded. The question is whether the constraint is capacity, visibility, or trust, because each has a different solution.

— Live directory of Black queer civil society co-production moderate lift Co-production and community research — built by the community, kept live by the community. Feeds CRM, AIvor, lead generation, and network mapping simultaneously. The gaps in the directory are as revealing as what is in it.

— Partner tool and project management dashboard infrastructure moderate lift Operational capacity for transparent relationships with organisations of all sizes. Sits on stable infrastructure. Enables partnerships to be held without depending on founder memory.

— Network mapping — loneliness co-production moderate lift How loneliness manifests for Black queer men — which responses are proximate, which require greater effort. Research question still needs articulating before design. Board community lead to own this. Brunch network exercise as potential methodology.

Tier 3 — develop with intent

Transformative — significant undertaking, dependencies to resolve first.

— Unique member pages — member-controlled data as feature member experience significant Members see exactly what BLKOUT holds about them, can edit or delete any of it, and are equipped to ask the same of others. Policy as education. Significant data architecture. Needs CRM foundation first. The feature that most visibly demonstrates the values.

— Next-level AIvor — orchestration on member need member experience significant From broadcaster to responder — receiving member need signals and acting on them, with care and ethical guardrails. The line between care and surveillance must be designed in from the start. Depends on knowing what members actually need. Network mapping and directory must precede.

— Co-designed member consultation with iterative learning loop co-production significant Design the consultation process in consultation. Radical transparency, shared results, member agency in decisions that follow insight. Includes autoresearch-style closed feedback cycle with co-designed metrics. Never a failure, always a lesson — at organisational scale. The most ambitious item on the list and the one that could make every other item more effective.

— Youth leadership intervention co-production significant Form and content both need co-producing — this cannot be designed for young people, only with them. Requires funding. Can begin relationship-building and scoping conversations now, against the backdrop of Black youth unemployment returning to 1981 levels.

— Enterprise and wealth — pop-up / shebeen / art model co-production significant Still forming. The relationship between enterprise, workplaces, community and intergenerational wealth remains to be discovered. An inquiry that in its form embodies potential elements of the final proposal — collaborative, cultural, accessible, profitable, sociable. Trust for London proposal as the discovery vehicle.

BLKOUT Creative Ltd — Community Benefit Society Living document — edited in situ via the Dreamcatcher editor

---Podcast hosting — added April 2026, surfaced via Commons page build

What we want: A hosted podcast platform with a brand-themeable embeddable player (we'll skin to obsidian/gold), an RSS feed for distribution to Spotify/Apple Podcasts, and basic listener analytics. Should integrate with the Commons + Critical Frequency pages without a generic Drive iframe.

Why now: We're starting to publish AI-generated audio (NotebookLM Deep Dives, future episodes from the Compass material). Drive embed is the current workaround — generic player, no podcast-app distribution, no analytics, asset lives in personal Drive.

Constraints / what we won't: Free tier or low monthly cost (BLKOUT is small); no extractive licensing on community audio; option to self-host or export RSS to migrate (no lock-in); accessible player UI; no Spotify exclusivity.

On the radar for Council review when surfaced: Castopod (open source, self-hostable on Coolify — natural fit), Transistor (paid, neutral, RSS-first), Buzzsprout, Spotify for Podcasters / Anchor (free + reach but sovereignty concerns).