Can a Computer-Use Agent Safely Operate Your Legacy ERP?
Computer-use agents can click through legacy ERP clients with no API. Let them query and save drafts; keep posting and master data edits behind human approval.
AI-native transformation · Consulting · Training · FDE
Run your company
the AI-native way.
We find the workflow to change first, train your team to do daily work with AI, and assign engineers who connect agents to your systems. Delivery is remote-first.
Example workflow · Sales quotes
Before
Search chat history → check the price list → write the quote by hand → wait for manager sign-off
After
Agent reads the company knowledge base → drafts the quote → sales rep confirms
What we do
From plan to production
01AI transformation consulting →
We interview each department, rank the workflows to change, and agree on how results will be measured.
Related notes02Team AI training →
Sessions by role, practiced on real tasks. Each team keeps the reusable AI Skills it builds.
Related notes03Forward deployed engineering →
Remote-first engineers join your team and connect agents to your CRM, ERP, and HR systems.
Related notesNotes
Our methods, in public
How to Run a Private Codex Gateway for Your Company on Official API Keys
Run a private Codex gateway on official API keys: deploy LiteLLM with Docker Compose behind HTTPS, issue one key per employee with budgets, and log usage.
AI Data Queries Return Two Sales Figures: Which Metric Definition Do You Trust?
When natural-language data queries return two different sales figures, the fix is a governed metric dictionary the model must check before it writes SQL.
AI Resume Screening: Should a Human Review the Candidates the Agent Rejects?
A recruiting agent speeds up resume screening, but rejected candidates should not be archived unseen. Set up borderline spot checks, appeals, and audit logs.
AI Safety Inspection Flags a Hazard: Who Signs Off on the Fix?
Factories and construction sites use AI safety inspection to capture on-site hazards. The algorithm captures risk images. A safety officer verifies, grades, and assigns each case. The responsible team fixes it by the deadline, and the officer closes it after an on-site recheck.
Who Owns a Missed Defect in AI Visual Inspection, and How Much Manual Checking Should Stay?
When AI visual inspection lets a defect through, saved images and logs decide who is liable. How to split model and inspector duties and tune manual spot checks.
Topics
Find notes by topic
AI Basics8 notesWhat AI can and cannot do today, explained without jargon, so non-technical teams can decide where to use it.AI Coding9 notesHow engineering practice changes once AI writes code: constraints, boundaries, and how to accept the output.Enterprise AI29 notesPutting AI into real business workflows: the context it needs, the permissions it gets, and the process changes around it.AI Safety24 notesPermissions, audit trails, and explainability, so teams can trust AI output and trace problems when they happen.Loops and Methods2 notesDesigning plan, execute, observe, and correct loops so AI checks its own work before it hands anything over.Case Studies5 notesWrite-ups from real projects: the trade-offs, how results were verified, and the approaches that did not work.
Start with a 30-minute call.
Leave with the first workflow to change.
Free of charge. You can also email us at contacts@fxai.ai.