BLKOUT
blkout Dreamcatcher

// verdict #4  ·  23 Apr 2026 · 07:15 UTC

space-agent.ai/

PASS

three or more voices said no. release without guilt.

submitted by   Rob  ·  BLKOUT Creative  ·  model   anthropic/claude-sonnet-4  ·  against wishlist of   2026-04-13T17:49:02z  ·  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.

I've reviewed Space Agent AI against BLKOUT's guardrails and wishlist. Here's my technical assessment: ## What Space Agent AI Is A conversational AI platform that creates custom chatbots for businesses, with features like lead generation, customer support automation, and integration capabilities. It appears to be a SaaS platform with subscription pricing. ## Guardrail Analysis **SCHEMA OWNERSHIP VIOLATION**: This tool would likely maintain its own conversation data, user interactions, and lead information separate from BLKOUT's authoritative CRM schema in `001_crm_complete_schema.sql`. Any leads or member interactions would live in Space Agent's database, not feeding directly into the CRM tables. **OPERATIONAL OVERHEAD CONCERN**: Another SaaS subscription to manage, monitor, and maintain. For a small team already running Coolify infrastructure, this adds external dependency complexity without clear operational benefits. **SURVEILLANCE MECHANICS RED FLAG**: Lead generation chatbots inherently collect conversational data from community members. The platform's business model likely depends on data aggregation and analysis - directly at odds with BLKOUT's data sovereignty principles. ## Wishlist Mapping This tool doesn't cleanly map to any specific wishlist item: - **"Non-intrusive lead generation"** (Tier 2) explicitly calls for "community-appropriate discovery" and "values-consistent methodology" while excluding "surveillance mechanics." A chatbot that captures conversation data fails this test. - **"AIvor"** capabilities are already being developed internally with ethical guardrails baked in. Space Agent would compete with, not complement, this strategic direction. ## Technical Concerns **VENDOR LOCK-IN**: Conversational data and trained models would be trapped in their platform. No clear data portability mentioned. **SEQUENCING PROBLEM**: This jumps ahead to application-layer tools before Tier 1 infrastructure stability is confirmed. The guardrails explicitly prioritize "infrastructure before application." **CATEGORY MISMATCH**: BLKOUT needs member-controlled, transparent systems. Generic business chatbots optimize for conversion, not community care. ## The Fundamental Issue Space Agent AI is built for businesses trying to capture and convert leads through automated conversations. BLKOUT is building community infrastructure with radical transparency and member control. These are incompatible paradigms. The wishlist item for lead generation specifically calls for approaches that are "honest" and exclude "surveillance mechanics." A chatbot platform designed for business lead capture inherently operates through surveillance mechanics - it must capture, analyze, and act on conversation data to function. RECOMMENDATION: PASS

// 02 · ethicist

Murray

pass

values, sovereignty, community benefit.

I've reviewed Space Agent AI against BLKOUT's values and strategic priorities. **What Space Agent AI offers:** A conversational AI assistant for businesses that can handle customer inquiries, booking, and basic automation tasks. It's positioned as a customer service and lead generation tool with integration capabilities. **Values alignment assessment:** **Data sovereignty concerns:** The platform processes customer conversations and data through proprietary systems. There's insufficient transparency about data handling, storage location, or member control over their information. This directly conflicts with BLKOUT's principle that "members own their data" and the organisation "holds it in trust, not as an asset." **Surveillance mechanics:** A conversational AI that monitors and responds to member interactions has inherent surveillance characteristics. Without clear ethical guardrails and member consent frameworks, this risks crossing the line from care to surveillance that BLKOUT explicitly wants to avoid. **Wishlist mapping:** - Does not address the **AI policy** need (Tier 1) — in fact, adopting this tool before having that policy violates the principle of "infrastructure before application" - Could theoretically support **non-intrusive lead generation** (Tier 2), but the intrusive nature of conversational AI monitoring makes it inappropriate for BLKOUT's values-first approach - No clear connection to other wishlist priorities **Guardrail violations:** - **Pre-order model mismatch:** Space Agent appears designed for always-on customer service, not BLKOUT's waiting-list/pre-order model - **Infrastructure before application:** Adding an AI customer service layer before having an AI policy and stable tech infrastructure violates this guardrail **Missing foundation:** BLKOUT needs its AI policy established first (Tier 1, "do now") before evaluating any AI tools. The policy will determine "what BLKOUT will and won't do with AI, and why" — essential context for this evaluation. The tool doesn't align with BLKOUT's community benefit model, raises significant data sovereignty concerns, and would be adopted without the necessary ethical framework in place. RECOMMENDATION: PASS

// 03 · builder

Rustin

pass

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

Looking at Space Agent AI, this appears to be an AI-powered workspace automation platform that connects various business tools and automates workflows between them. ## Stack Compatibility & Infrastructure **PROBLEMATIC.** Space Agent operates as a cloud-based SaaS platform, not something you deploy on your own infrastructure. This creates an external dependency that sits outside your Coolify-managed VPS setup. For a community benefit society focused on data sovereignty, routing member data through a third-party AI automation platform raises immediate concerns about control and transparency. ## Guardrail Violations **HARD STOP.** This tool directly violates the "No n8n" guardrail. The guardrails explicitly state: "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." Space Agent is essentially a more complex, AI-powered version of what n8n does — workflow automation between different tools. If BLKOUT already determined that the operational cost of a workflow engine outweighed the benefits, adding an even more complex, AI-driven, externally-hosted workflow engine contradicts that decision entirely. ## Wishlist Mapping **WEAK CONNECTION.** While you could theoretically use Space Agent for various automation tasks, it doesn't map cleanly to any specific wishlist item. The closest might be "Partner tool and project management dashboard" but that item calls for something that "sits on stable infrastructure" — which an external SaaS doesn't provide. ## Vibe-Codeability & Maintainability **CONCERNING.** AI-powered automation platforms are notorious for creating "magic" that works until it doesn't. When Space Agent's AI makes incorrect assumptions or connections, debugging becomes a black box exercise. For a small team, this creates exactly the kind of operational overhead that the n8n guardrail was designed to prevent. ## Speed vs. Sustainability Trade-off While Space Agent might offer quick wins in automation, it introduces: - Another external service to monitor and pay for - AI decision-making that may not align with BLKOUT's values - Potential data privacy issues for member information - Vendor lock-in for critical workflows The guardrails exist specifically because BLKOUT has chosen to prioritize infrastructure ownership and operational simplicity over automation convenience. **RECOMMENDATION: PASS**

// 04 · inclusion

Rivera

pass

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

I've reviewed Space Agent AI against BLKOUT's needs and reach requirements. **What it is:** An AI-powered workspace management tool that automates file organization, meeting scheduling, and task management across various platforms like Slack, Google Drive, and calendars. **Guardrails analysis:** - **Schema ownership violation**: This tool would create its own data silos rather than reading from BLKOUT's authoritative CRM tables - **Infrastructure before application**: Adds operational complexity when BLKOUT is still building foundational stability - No direct conflicts with other guardrails, but the tool doesn't align with BLKOUT's pre-order business model or existing RSVP/Stripe infrastructure **Wishlist mapping:** This doesn't map to any specific wishlist item. The closest might be "Partner tool and project management dashboard" but Space Agent is designed for internal productivity, not transparent community relationships. **Reach interrogation:** - **ACCESSIBILITY FLOOR**: Assumes multiple paid subscriptions (Slack, Google Workspace, etc.), high digital literacy, and consistent internet access - **PRIVACY ARCHITECTURE**: Terrible for closeted members - requires connecting personal calendars, files, and communications through a third-party AI service - **COST TO USER**: Indirect but significant - assumes organization has enterprise software stack that many grassroots groups can't afford - **REGISTER**: Built for corporate productivity language and workflows, not community organizing contexts - **GEOGRAPHIC REACH**: US-centric integrations and assumptions about workplace tools - **ISOLATION vs NETWORK**: Serves people already embedded in digital workspaces, does nothing for isolated community members **The fundamental problem:** This is a tool for the over-served - people who already have too many productivity apps and need AI to manage them. It assumes a level of digital infrastructure and workplace formality that excludes most of BLKOUT's community. A closeted person sharing a computer, someone without consistent internet, or a community member who primarily uses WhatsApp and Facebook would be completely shut out. Space Agent optimizes for people who are drowning in productivity tools. BLKOUT's community includes people who can barely access basic digital services. 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: infrastructuremember experienceco-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