THE STARTING POINT
The workflow works. Its knowledge is scattered.
A release decision may depend on a screen, service code, database views, source tables and the judgment of experienced people. Adding a model before understanding those dependencies makes it harder to explain which records support an answer or what should happen when its knowledge changes.
Begin with a business question such as “Why is this batch waiting for release?” Trace the current system, record what is known and unresolved, then preserve the findings as knowledge your team can review and maintain.
WHAT YOU CAN INSPECT
See what the software
makes visible.
In the synthetic demonstration, a queue contains 8 of 40 registered batches. Compare the sources, preserve a source decision, then retire its bound asset and inspect how the digital expert asks for review.
- Synthetic source coverage
- 8 / 40
- Knowledge dependency
- Versioned
- Retired asset behavior
- Review required
Demo scope
Fictional enterprise and synthetic data. The demo traces a defined set of code patterns and uses rule-based responses; it does not connect to or migrate a production system.
WHAT CHANGES FOR YOUR TEAM
Outcomes you can check.
- Know which records actually support a decision before an AI uses them
- Keep expert rules and source choices in a versioned asset your team owns
- Start a pilot with read-only access, explicit review points and stop conditions
WORKS WITH YOUR STACK
Build on your existing systems.
- ERP and MES platforms, including SAP and custom builds
- LIMS, QMS and warehouse systems
- SQL Server, Oracle, PostgreSQL and MySQL schemas and views
- Historian, OPC UA and CSV exports
- Legacy Java, .NET and stored-procedure code
HOW THE ENGAGEMENT WORKS
From your question to a practical plan.
Choose the business action
Agree on one decision or handoff, its owner and the system boundary.
Output: A workflow question, object list and access boundary.
Trace the existing system
Follow the action through screens, service logic, views and source tables. Record references and questions for the system owner.
Output: A business-action-to-source map.
Check meaning and coverage
Compare candidate sources for population, filters, units, timing and missing records. Confirm meanings with the people responsible.
Output: A source decision log and coverage gaps.
Preserve a digital expert asset
Define the approved knowledge, source references, owner, scope, version and review conditions independently of a particular model.
Output: A first asset schema and change policy.
Plan a focused pilot
Choose read-only assistance or a controlled workflow, human review points, evaluation cases and conditions for stopping.
Output: A pilot scope and acceptance plan.
WHAT YOU RECEIVE
A practical handoff for your team.
- A workflow and source map with unresolved questions
- A source coverage assessment and decision log
- A versioned knowledge asset schema with ownership and review conditions
- A scoped pilot proposal, synthetic evaluation cases and handoff notes
WHAT TO PREPARE
Start with one workflow.
- One workflow and the person responsible for it
- A redacted architecture sketch or screen sequence
- Permitted read-only code, schema or sample exports after access is agreed
- A practical definition of an acceptable result
Access is agreed in writing first. A mutual NDA is available before you share architecture, code or data.
When this is useful.
Useful when a team needs to understand inherited software, preserve business knowledge or assess an AI pilot before committing to a wider replacement.
Scope and responsibilities.
A discovery engagement does not automatically replace an MES or ERP, recover every undocumented rule, or authorize AI to control production. Existing DCS, PLC and SIS responsibilities remain with the relevant engineering and safety teams.
QUESTIONS BEFORE WE START
Before we start.
Can we add AI without replacing the whole system?
A pilot can begin with one read-only workflow. Discovery identifies the interfaces, evidence and review responsibilities needed before deciding whether deeper integration is worthwhile.
How does this help us own a knowledge asset?
The proposed asset keeps source choices, business meanings, owners, versions and evaluation cases in explicit structures. These are intended to survive a model or supplier change. The demo illustrates that dependency; it does not establish a measured commercial moat.
What does Legacy Eater do here?
Legacy Eater is the discovery approach shown in the industrial demo: start from a business action, trace its implementation and data, compare source coverage, and preserve the reviewed findings. Source-system findings still require the owner’s confirmation.
How much does it cost and how long does it take?
A Decision Discovery typically takes one to two weeks and costs US$700–1,400. An Expert Knowledge Pilot typically takes three to six weeks and costs US$3,500–7,000. After a short scoping call you receive a fixed quote; wider implementation is a separate decision.
Do you need access to our production systems?
No. Discovery can start from screen recordings, a schema export, read-only code access or a redacted sample. Pilots begin read-only. Write access, if ever needed, is agreed separately with your system owner.
SCOPE AND BUDGET
Start small. Fixed scope first.
Decision Discovery
US$700–1,400
Pick one decision that depends on a few experts. We map how they make it, the rules and exceptions behind it, and the systems and data it touches. You receive a decision map, gap list, knowledge model and a pilot proposal you can use with any vendor.
Expert Knowledge Pilot
US$3,500–7,000
One decision workflow built inside your stack, with explicit knowledge, source links and review points. Evaluate it against agreed cases with your expert, then hand over the code and documentation.
Ongoing Engineering
From US$70 per hour
Extend a pilot to new workflows, connectors and knowledge assets, or add regression checks when models and rules change.
Typical ranges. You receive a fixed quote after a short scoping call. Working terms and FAQ →
A FOCUSED FIRST ENGAGEMENT
Discuss one legacy workflow.
Tell us the workflow, current system and the result you need to evaluate. You will hear back within one business day with questions, a view on fit and next steps.
Describe your workflowMutual NDA available before you share architecture, code or data samples. Please keep confidential records and credentials out of the public form.

