Axiomatic

Luca AI

Cross-app intelligence on your ledger and operations — chat, tools, and guardrails.

What is Luca?

Luca is Axiomatic’s built-in AI, named for Luca Pacioli — a conversational interface to your business data and workflows. It runs in-product (dedicated Luca area and chat entry points across modules) and is backed by tools that read and, where allowed, act on your tenant — always within identity, entity, and role boundaries.

Luca is not a separate server or bolt-on SKU. It is part of the same application as Ledger, CRM, BI, and the rest, so answers can combine operational and financial context without exporting CSVs.

What you can do

  • Ask in plain language — balances, trends, journal provenance, “what posted this?” style questions
  • Classify and reconcile — imported transactions, source-aware suggestions, batch operations where enabled
  • Work with documents — ingest, summarize, and map to accounts or projects where the product supports it
  • Author and refine rules — help draft or explain DSL rules; execution still follows your approval and posting policies
  • Navigate complexity — explain modules, reports, and workflows to onboard teammates

Exact tool coverage expands with releases; the in-app experience always shows what Luca can touch for your role.

Guardrails

  • Ledger authority — Posting, approvals, and irreversible actions follow the same permissions and credit/billing rules as the rest of the app. Luca does not bypass them.
  • Tenant isolation — Data access is scoped to your tenant and entity like any API route.
  • Policy — Administrators can constrain AI behavior via Admin → AI policy (where available).
  • Auditability — Actions that change financial state remain traceable through existing journal, event, and audit mechanisms.

Where to open Luca

Use the Luca area in the app for full conversations and history. Shortcut: G then L (when enabled). Module pages may expose contextual chat or assistants tied to that workflow.

Agent pods (Sales, PM, Design, Engineering)

Custom Luca agents are entity-scoped sub-assistants with their own system prompt and toolPolicy (module scopes, read-only mode, optional tool allowlist).

Setup

  1. Open Luca → Settings → Agents (/luca/settings/agents).
  2. Create from a pod template (Sales SDR, Marketing, PM, Design, Engineering) or customize manually.
  3. Invoke in chat with @agent:slug or sticky agent mode in the sidebar.

Luca can also design agents via tools: describe_cortex_agent_schema, create_cortex_agent (through Approve / propose_action).

Product pod workflow

RoleAgentKey tools
PMpmadd_task, update_project_task, list_project_tasks
DesigndesignDocuments (specs/wireframes), Website Studio (marketing site only), update_project_task for UX review notes
Engineeringeng-cursorlaunch_cursor_agent — opens Cursor Cloud Agent PRs; never edits code in-app

Project tasks support externalLinks: github_pr, github_branch, github_commit, cursor_run, spec_doc, vercel_preview. Link manually with update_project_task / work_update_item, or automatically via GitHub webhook (POST /api/webhooks/github/{entityId}) when the PR body, branch, or commit message contains a task UUID (task/<uuid>/...) or issue key (PLATFORM-11).

Integrations

  • GitHub — Admin → Integrations → Developer. Webhook secret verifies X-Hub-Signature-256. Optionally add Personal access token (pull_requests write): when Cursor Cloud Agents still open draft PRs, the webhook PATCHes them ready-for-review and advances linked in_progress tasks to review (and listens for ready_for_review when humans mark drafts ready).
  • Cursor — API key + defaultRepo on the connection; optional per-project override via jobs.metadata.githubRepo. Engineering agent calls launch_cursor_agent.

Delegations (cron + granted permissions) and invocation history live on each agent’s detail page.

Learn more

On this page