Writing

Writing grounded in evidence.

6 posts. Each one declares, in its front matter, the ledger claim ids it uses, the transcript it is grounded in and the named human editor of record — and the build fails without them.

  • Run a B2B quote approval workflow: from client brief to audit receipt

    2026-09-07 · edited by Aetha Editorial

    Run a synthetic 30-seat proposal through pricing, a 25% discount request, an agent refusal and a simulated user approval. Keep the local project and inspect the receipt.

  • Build a custom CRM with Claude Code: what day 30 looks like

    2026-08-19 · edited by Aetha Editorial

    Day one of an agent-built CRM goes well, and the weekend tutorials are not wrong about that. This is about the four things that are wrong on day 30, why they are the ones that get deferred, what a framework can carry instead, and when building from scratch is still the right call.

  • When to use a CRM platform instead of this

    2026-08-18 · edited by Aetha Editorial

    Most teams weighing this framework against a CRM platform should take the platform. A write-up of our competitor review, dated facts only, and the narrow case that remains.

  • What our inspector refuses to tell you

    2026-08-18 · edited by Aetha Editorial

    The application inspector emits its own blind spots as machine-readable limitation codes, in the same JSON as the capabilities. That is an affordance for agents, not a disclaimer for lawyers — and the difference is testable.

  • The sixteen ways we try to break a milestone before it merges

    2026-08-18 · edited by Aetha Editorial

    Every milestone in this repository is attacked against a standing checklist of adversarial categories before a human merges it. Here is the list, what three of the attacks look like in a real run, and what the list deliberately does not prove.

  • If a coding agent builds your CRM, what should it refuse to do?

    2026-08-09 · edited by Aetha Editorial

    A prompt can ask an agent to leave consequential decisions to a human. A refusal surface makes that boundary executable, tested, and visible after the fact.

What nothing published here would mean

These pages describe this repository at this commit. None of them implies the framework is deployable, and none of them is a roadmap: nothing that is not merged appears on this site, in any tense.

  • No authentication ships: the framework authenticates nobody. Production Spine v1 (ADR-038) gives the framework verified identity, organizations and memberships, server-authoritative authorization and one tenant per application instance — so tenancy and authorization now exist and are enforced. What does not exist is authentication: no login, password, session or OIDC implementation ships, and a deployment must supply the adapter that verifies the request. Production mode refuses to start without one. In local-development mode an actor header is accepted as an assertion and is not an identity, which is the default developer posture. This is not shared-database multi-tenancy and it is not a readiness claim.
  • Not shared-database tenancy. createAccordoAppAsync can boot one tenant onto dedicated PostgreSQL databases. Shared-database row-level tenancy is not implemented, and this is not a production-readiness claim.
  • Timers exist; a service that runs them for you does not. Durable jobs, a transactional outbox and scheduled asks exist for self-hosted applications that explicitly start a worker. Nothing autostarts; a timer opens an ask, never makes a decision, and no managed worker service or recurrence is included.
  • No email, calendar or marketing integrations. An in-memory notification provider contract exists. MK1 marketing records supplied funnel observations and human-reviewed proposals only; it has no sending, publishing or spending path.
  • The build benchmark has not been run. The protocol is designed and published; no Successful Agent Build Rate exists yet. Any number you see quoted for this project is not ours.
  • Ownership means vendored source: there is no framework dependency to bump. The published create-accordo@0.1.0 scaffolds vendored source; it is the August 19 snapshot, not the current repository feature set. Use a current source checkout for the capabilities described here; upgrades require merging source (L-08). The framework is copied into the project, not installed as a framework library dependency. The accordo npm name is an empty reservation; the @accordo scope is claimed and deliberately empty.

Every claim and every limitation is on one page, and the questions this project refuses to answer are published beside them.