The customer is on a grandfathered plan SKU and has requested a refund.slack:dm-2:17
Route the request through finance directly. Do not run it through the standard refund flow — the SKU check will reject it.slack:dm-2:17
CC Sarah (finance) on the original ticket. Sarah is the standing approver for grandfathered SKUs.slack:dm-2:17
All tiers eligible for refund within 30 days of purchase.
Submit ticket via #refunds channel. Approver: Marco T. (Ops)
— missing —
Chat threads where decisions get made. DMs where exceptions get handled. Wiki pages 14 months out of date. Your agent reads context windows; none of this gets there.
Even when policies are written down, no single artefact has been reviewed and approved by ops. Nothing your agent can be governed by.
When policy changes, the prompt doesn't. The agent acts on rules engineering wrote weeks or months ago. By the time someone notices the drift, it's been wrong in production for dozens of tickets.
When the agent fails, a human handles the ticket and the failure is forgotten. The substrate doesn't learn. Tomorrow it fails the same way.
Every incoming source is classified before any compilation runs. Triage decides which existing guide this source contributes to, whether it carries enough signal to compile at all, and which compile mode to route to.
The source compiles — together with related existing guides and citations — into a canonical guide. Two modes depending on routing: write (new guide) or update (structured diff against the live guide). Human-readable body with frontmatter and full citation chain back to source.
Operations reviews the compiled guide, edits where needed, approves. Diff review, version control, and rollback all on the guide. The audit gate — and because the skill is derived from the guide, approving the guide is approving the skill.
Once a guide is approved, the skill is mechanically rendered from it. No separate authoring step. If the guide changes, the skill re-derives; the agent's behaviour updates atomically.
The agent runs the derived skill via MCP, Anthropic Skills, OpenAI Agents, or any supported harness. Skills are read at runtime; the agent acts on the structured procedure.
The runner library reports execution outcomes back to Lorify — success, failure, escalation, deflection. Findings re-enter the pipeline as new sources at Stage 1. Guides update; skills re-derive; the substrate gets better with use.
Every output passes through a typed schema and a deterministic source-authority rule. Conflicts resolve by precedence, not by whatever the LLM decided this morning. BYOK on the model.
Plain markdown, exportable as a zip, owned by your team. Switch the LLM or the platform — your substrate travels.
Operations reviews, edits, and approves the canonical guide. Because the skill is derived from the guide, approving the guide is approving the skill.
Sources change, the guide updates. Production fails, the skill re-derives. The substrate gets stronger every week it runs — not staler.
Each template ships the whole pipeline — sources, schema, integration patterns, eval harness, reference guide — calibrated to a real production use case. Picked before any sources flow in; the pipeline runs within its configuration.
Production triage with edge cases, escalation criteria, and grandfathered policies.
Account context, competitor intel, and win/loss patterns for meeting prep.
Refunds, escalations, and exceptions handled consistently across the policy surface.
Triage incidents, route SEV1/SEV2, and execute runbook steps under pressure.
Four templates at launch. Each one comes pre-configured for the use case — sources, schema, integration patterns, eval harness.
Slack, Zendesk, Notion, Confluence, runbooks, voice memos. Or import an existing guide directly.
Lorify compiles your sources into a canonical guide. Your team reviews, edits, approves. Versioned, auditable, owned by you.
The skill derives from the approved guide. Ship to MCP, Anthropic Skills, OpenAI Agents, or your custom harness.