AI editing project
An editing environment such as Lovable, with the access and guidance your team needs. We confirm the chosen service’s capabilities for your project.
buildsfor · A development service by Nihonbashi AI Lab
Business software your team can keep improving.
Show us the documents, spreadsheets, and work you want to improve. NAL uses AI to build software around your workflow and helps your team learn to make the agreed everyday changes.
Start with a consultation. Scope, delivery, and costs are agreed before development.
Choose how you will keep working on it.
Delivery can combine an AI editing project, a GitHub repository, and a ZIP snapshot. We recommend a combination based on who will maintain the software and where it will run.
GitHub repository
Source code, change history, and instructions for building and updating the app. Useful for your developers or a future development partner.
ZIP snapshot
Files and guidance for an agreed delivery version. A snapshot is separate from the full change history and the environment needed to run the app.
Hosting, external services, and ongoing maintenance are agreed separately. Docker, internal servers, and other delivery environments require project-specific checks.
Know what your team can change.
We agree a practical scope for self-service changes and include hands-on handover. Optional support covers the work that needs specialist help.
Everyday changes your team practices
For example, update screen text or adjust supported export columns and settings. The scope depends on your app, with sample data and checks to confirm the change.
Changes with specialist support
Login and permissions, database changes, or complex integrations may need expert review and implementation. We make those boundaries clear at handover.
Agreed before full development begins
- Who edits it and which tools they use
- Projects, source files, and instructions to deliver
- Where it runs and what services it needs
- Account ownership and access responsibilities
- Development, running, and support costs
- Functional checks and the handover exercise
You do not need all the answers to start. NAL helps define them during scoping.
Try the workflow
Check order data. Export it your way.
Use fictional orders to correct missing data, check totals, and change the CSV layout yourself.
Operation example using fixed fictional data. No documents are uploaded or read by OCR. Edits stay in this tab and disappear when you leave or reload.
Fictional order reference
| Order number | Order date | Customer | Product | Quantity | Unit price | Amount |
|---|---|---|---|---|---|---|
| DEMO-001 | 2026-09-01 | Sample Office A | Notebook | 2 | 1000 | 2000 |
| DEMO-002 | 2026-09-02 | Sample Office B | Paper set | 3 | 1200 | 3600 |
Check and correct
Amounts are whole Japanese yen (JPY). Changing a value clears this order’s confirmation.
Change CSV column names and order
Try changing a header or moving a column. The order data stays the same.
CSV preview
| Order number | Order date | Customer | Product | Quantity | Unit price | Amount |
|---|---|---|---|---|---|---|
| DEMO-001 | 2026-09-01 | Sample Office A | Notebook | 2 | 1000 | 2000 |
| DEMO-002 | 2026-09-02 | Sample Office B | Paper set | 3 | 1200 | 3600 |
Spreadsheet formula prefixes are exported as literal text.
Correct the highlighted fields and check both orders before downloading.
Use the AI workspace to explore a problem
Software Foundry
From a problem to software that works in your operation
Start with one sentence, an AI conversation, a document, a specification, a prototype, or software already in progress. Continue from wherever you are today.
Continue to send this text to the buildsfor AI workspace. AI processing may temporarily store it with Google. When using Managed Agents, we delete the interaction and execution environment and confirm deletion before showing the answer. If deletion cannot be confirmed, processing stops.
0 / 1200How your text is handled
Only content-free operational metadata is retained. Do not enter personal data, secrets, credentials, source code, or private links. Continuing does not submit a request, promise work, or start development.
Or start with a prompt
Explore the public Registry
One agent-led path
Structure the problemConfirm the outcome, workflow, information boundary, constraints, and success measure before choosing a path.Review reusable problem patternsUse patterns to ask better questions even when no registered Build exists. A pattern is not a product or development promise.Inspect known Build factsWhen a current Build is relevant, inspect its exact product truth, BuildVersion, Evidence, and availability boundaries.
See how buildsfor works
AI Forward Deployment as a Service
AI agents deliver the work; every reusable change strengthens the product.
See the bounded loop from Problem Brief and fit/no-fit through implementation, Evidence, Owner acceptance, and a common successor Build.
Traceable change set
Owner decisions + acceptance
Common product revision
Agent reference layer
Start with the problem. Inspect a Build only when it matters.
The agent uses exact records to explain fit, limits, and uncertainty. A missing match can continue toward a common improvement, a reusable productized candidate, or refusal without inventing a product.
Analysis, not inventory
The value is the decision path, not the shelf size
buildsfor combines controlled agent reasoning with exact reusable assets. It can explain an existing fit and can also route an honest no-current-Build result without falling back to generic chat or bespoke development.
01
Controlled analysis
The customer-facing agent structures the problem and keeps visitor statements, model interpretation, eligible Knowledge, Registry facts, and Evidence distinct.
02
Exact reference assets
Product truth, BuildVersion, Registry, and Evidence provide inspectable facts when a candidate exists. Their count is not a product target.