AI automation for Claris FileMaker systems that already run your business.
iRusty helps teams add practical AI to Claris FileMaker: private assistants, guided workflows, validation, summaries, reports, dashboards, FileMaker AI agents, and agentic tasks that stay grounded in your real business data.
AI grounded in FileMaker data
Generic AI does not know your customers, orders, jobs, inventory, or rules. iRusty builds assistants around the data and workflows your team already uses.
Human approval where it matters
Agents can draft, search, summarize, validate, and prepare actions while keeping approvals on sensitive or business-critical decisions.
Private options for sensitive work
When data should not leave your control, local/private AI patterns can support safer search, analysis, and automation.
Automation that pays for itself
The best AI work removes repetitive review, copy/paste, reporting, and routing tasks so your people can focus on decisions.
What this work looks like
FileMaker AI automation works best when it starts with a real operating bottleneck instead of a vague chatbot idea. The useful target is usually a queue, report, review step, handoff, reconciliation, or follow-up process where FileMaker already holds the trusted context and users need faster decisions.
iRusty designs those workflows so AI can read the right records, prepare a summary or proposed action, and show the evidence before anything sensitive changes. FileMaker remains the source of truth for records, permissions, business rules, and audit history.
Typical deliverables
- A FileMaker AI automation review that identifies repeatable review, reporting, routing, validation, and follow-up work.
- A first automation pattern such as an approval queue, exception reviewer, stale follow-up list, report brief, or missing-data checker.
- Model and privacy guidance for OpenAI, Claude, Gemini, Codex-style agents, local retrieval, or private model options depending on the workflow.
- Write-back controls, reviewer states, source-field notes, test records, and handoff documentation so the business can trust the automation.
How iRusty keeps it safe
FileMaker modernization should not create mystery changes. Work is scoped around backups, affected scripts and layouts, sample records, test notes, and clear approval points. When AI is involved, it drafts, summarizes, checks, and prepares work before FileMaker accepts a write-back.
Common questions
What should FileMaker AI automate first?
Start with narrow, reviewable work: stale follow-ups, report summaries, missing data, exception queues, duplicate checks, or proposed updates that a human can approve.
Can AI work with an old FileMaker database?
Yes. Older systems are often a strong fit because they contain years of operating rules. The first step is mapping the important data, scripts, reports, and approval points before adding automation.
Do sensitive records have to leave FileMaker?
No. Some workflows can use local retrieval, redaction, private models, or tightly scoped API calls. The right architecture depends on the data risk and the action being automated.
Start with a review queue, not blind automation
The strongest first FileMaker AI automation project is usually a controlled queue. AI reads trusted FileMaker records, drafts a recommendation, cites the fields it checked, and waits for a human to approve, edit, reject, or defer the action before the production record changes.
That pattern works for stale quotes, order mismatches, billing exceptions, missing customer details, production handoffs, and daily management reports. FileMaker keeps the business rules and audit trail; AI reduces the manual checking that slows the team down.
What gets built
- Source-field capture from FileMaker records, notes, reports, and related tables.
- AI summaries with confidence notes, risk notes, and the recommended next action.
- Approval screens for accept, reject, edit, defer, and write-back status.
- Logs that show who reviewed the item, what changed, and why.
Best first use cases
- Open quotes or stale follow-ups that need sales review.
- FileMaker, Shopify, accounting, or shipping totals that do not match.
- Daily reports that should surface exceptions before the morning call.
- Customer or job records missing data before the next workflow step.
How a first FileMaker AI automation rollout actually works
The right first implementation is usually narrow, visible, and ugly in the useful way. It should prove the agent can read the right records, explain itself, wait for review, and leave an audit trail before anyone trusts it with higher-volume work.
If the FileMaker system is already fragile, the safer first move is a reliability audit before ambitious AI rollout. Broken backups, risky scripts, hidden integration drift, or slow reports will poison the automation story fast if the operational foundation is already lying to the team.
Safe first phase
- Pick one recurring exception lane such as stale quotes, billing mismatches, or missing data.
- Have the agent draft a recommendation and cite the source fields it used.
- Store the proposal in a review table with reviewer, status, and timestamp fields.
- Let humans approve, edit, reject, or defer before any write-back script runs.
What comes after proof
- Scheduled report summaries that route exceptions into named work queues.
- Role-specific dashboards for sales, ops, finance, or service review.
- JSON-based script handoffs so subscripts receive explicit, typed inputs.
- Guarded write-back only after the review trail proves the workflow is honest.
Proof package: review queue pilot
A useful pilot should leave the team with evidence, not a demo script. The goal is to prove that the FileMaker AI workflow can select the right records, explain its recommendation, preserve reviewer control, and show exactly what would have changed before any production write-back is trusted.
Pilot deliverables
- One chosen exception lane, such as stale quotes, order mismatches, or missing customer data.
- A review table that stores source fields, AI recommendation, risk note, reviewer, and status.
- A FileMaker screen or WebViewer view for approve, edit, reject, defer, and inspect source record.
- A dry-run report showing proposed changes, skipped records, and records needing human judgment.
Pass/fail proof
- The agent cites the fields it used instead of producing unsupported advice.
- Every proposed action can be traced back to a FileMaker record and reviewer decision.
- Bad or incomplete inputs route to review instead of being written back silently.
- The team can explain the workflow in business terms before expanding the automation.