For enterprises and the SI partners who deliver for them

Why create another legacy, just with faster tooling?

Bring AI into your core systems and stand behind each change it makes.

Become a design partner See how it works ↓

Many ways in. One Tallyseal. Many ways out.

What you already have

Talk with AI

Analysts’ spreadsheets

Specs, policies and documents

A legacy system’s export

Process and decision models

Tallysealreadable rules and definitions your people approve

What you get

A running application

An interface for AI agents

Your existing systems, wrapped

Runs from your definitions

your people approve

any bad change comes back exactly

hash-chained record

The problem

A bigger pile of code, made sooner, is still legacy.

Big firms run on decades of code that few people still fully understand, and the people who know it are retiring. AI code generators write code much faster. But a bigger pile of code, made sooner, has the same problems: nobody can explain it, it's hard to change safely, and it's hard to prove to a regulator.

Same underlying problems, just more code, sooner.

Legacy codebuilt over decades

AI-generated codea bigger pile, sooner

Readable rules and definitions

your people approvehash-chained recordbad changes come back exactly

Tallyseal semantic appconnect what you run

A different route

Don't write more code. Define what your business means; Tallyseal runs it.

What ‘semantic’ means

A semantic app is built from its meaning: readable rules and definitions, kept as data, that your people approve and that behave exactly as decided.

In plain terms: your entities, rules and processes are readable definitions in business terms, not code, so people and AI can check and change them.

Tallyseal runs the application from those definitions and regenerates its tables and screens when a rule changes, so the definitions stay the source of truth.

Your experts and AI design the application together as readable rules and definitions, and your people approve each change before it goes live. Tallyseal runs alongside the systems you already have and uses them as they are.

A bad change comes back exactly, data included, or it is refused with the reason. Each change leaves a hash-chained record your auditors can check with open tools.

Designed with your experts

AI drafts, and your people approve each change before it goes live.

Alongside what you run

It connects to the systems you already have and uses them as they are.

Put back exactly

A bad change comes back exactly, data included, or it is refused with the reason.

On the record

Each change leaves a hash-chained record your auditors can check with open tools.

In shortFuse your core systems with AI. Keep what works, build what's next, retire on your terms. Prove it all with evidence built in, not bolted on.

How it works

Connect. Build and modernise. Run. Prove. With AI at each step.

Not an IDE: an AI development environment. Design it with your experts, build it with AI, and your people approve each change before it goes live.

01Connect

Use what you already have.

Connect by web calls, files, queues, databases or existing code: your team or SI builds each connection on Tallyseal; each result returns through one door.

Over the web: rules and processes call the web services your existing apps already have, and each call is on the record.
Files and old formats: read spreadsheets, files and legacy record layouts as they are, and turn them into a working app.
Code and databases: Your team or SI can easily build calls to routines in your systems and connections to your other enterprise databases on Tallyseal.

What it meansNothing has to be rewritten to start.

02Build and modernise

Ship new products, and shrink the old estate as you go.

Wrap, re-use and extend the apps you already run. Your team or SI checks each new part against the old and switches the old off step by step; we're building the final switch-off check.

Build brand new applications with AI.
Generated, not hand-written: Tallyseal generates the tables, screens and the API description for changes from your approved definitions, and regenerates them when a rule changes.
Re-use: your experts settle the rules buried in existing apps once, and each answer stays linked to the source lines it covers.
Import your models: bring in your existing decision tables and process models.
Extend: AI drafts and your people approve, and a bad change to your data comes back exactly.

What it meansNew products without waiting on the integration queue, and the old estate shrinks with no big bang, so you stop paying twice.

03Run

Change the business without breaking it.

Bring in AI while the core runs. Application errors roll back changes for humans and AIs alike.

Real databases: your data sits in an enterprise database, a standard relational database, with tables built from your definitions.
Standalone code: we're building ahead-of-time compiled code you can inspect, which runs in your environment without calling us to process a transaction.
Explainable decisions. Trace any value to who changed it, when and why.
Fits your enterprise tooling: diff and test rules in your pipeline, export the record to plain files, and keep AI tools in one reviewed catalogue, with the API generated from the same definitions.

What it meansAI-speed delivery on a backend that's deterministic by design.

04Prove

Say yes to AI and stand behind it.

Show the board and the regulator who or what changed what and why, from your own record, with four-eyes sign-off where you set it.

Your record, not a sample: each field change records old value, new value, who and why, and exports as a signed evidence bundle for auditors and regulators.
The rule in force: each outcome shows the rule in force at the time and who approved it.
Checkable without us: evidence follows CRAWCUS, an open spec we publish (CC-BY-4.0), and an open-source verifier lets anyone check it.

What it meansAttest to every change, not a sample, and answer auditors from the record, not a spreadsheet.

Enterprise control, built in

People in the loop

Approval is yours to set: four-eyes sign-off on the work you choose, in your order, and the maker never signs as checker.

Roles and permissions

Roles, permissions and scope are clear records your team can review.

AI as a named actor

AI is named as the actor on each change it makes, and fenced out of the fields you choose.

Enterprise sign-in, one door

No back doors

Fixes, configuration and the data you load go through the same door onto the same record.

How Tallyseal is different

No one we track combines all four.

The application is its meaning.

It's a semantic app: your entities, rules and processes as readable definitions your people approve; the application runs from them, not a pile of code.

A bad change comes back exactly.

Data included, or it is refused with the reason.

Your auditors can check it.

Each change leaves a hash-chained record your auditors can check with open tools.

It retires the old step by step.

It works with the systems you already run. Your team or SI checks each new part against the old and switches the old off step by step; we're building the final switch-off check.

Use AI code generators to try a new idea. Use Tallyseal where a change touches your core systems and someone has to sign for it.

If you’re against more code, why does Tallyseal generate code?

Because the meaning lives in your definitions, not in code. Your people approve the definitions and rules; Tallyseal runs the application from them and regenerates its tables and screens when a rule changes, so the application follows what you decided. We're building standalone compiled code from the same definitions, which you will be able to inspect and run in your environment without calling us.

Questions worth asking

Three questions to ask about your core systems.

Change and risk

When a change to a core system goes wrong, how do you put it back, and what does it cost you in time, data and sign-off?

Signs it is costing youBackup restores, fix scripts, change freezes and long approval chains.

With TallysealNo restore, no fix script: a bad change comes back exactly, data included, or it is refused with the reason.

AI and accountability

If your board or regulator asked where AI makes or shapes a decision in your systems, and who signed it off, could you show them?

Signs it is costing youSampled testing, hand-built evidence files, and AI pilots that never reach production.

With TallysealAI drafts and your people approve; committed decisions run on readable rules with no model in the path, and AI is named on each change it makes.

The old estate

What stops you retiring the systems you most want to retire, and what would let you start one step at a time?

Signs it is costing youPaying twice, rules buried in code, key people leaving, and rewrites that failed.

With TallysealYour team or SI checks each new part against the old and switches the old off step by step; we're building the final switch-off check. So you stop paying twice.

Where it fits

Each group in the market solves part of the problem.

Cloud and mainframe modernisation tools

What it does wellThey analyse old code, help rewrite it, and compare the old and new outputs.

What's left to youThe result is still a large codebase, often tied to one cloud.

Rewrite specialists

What it does wellThey capture how the live system behaves and test the rewrite against it, or use AI to map and rewrite legacy code.

What's left to youThe focus is moving off the old system, not governing what runs afterwards.

Enterprise app platforms

What it does wellThey are strong on delivery, and have added AI builders and agents.

What's left to youThey run on their own platform, and the evidence is a log inside the product, not a record you can check on your own.

AI coding tools and app builders

What it does wellThey are great for new apps and prototypes.

What's left to youReverting restores the code, not the data it has already changed, and proving each change went through your controls is still your job.

Rules, spreadsheet and evidence tools

What it does wellThey turn spreadsheets into services, run rules, or collect delivery evidence.

What's left to youEach covers one part: the rule, the model or the record.

What’s coming

The trendModernisation tools are adding AI agents, app platforms are rushing out AI builders, and more tools will claim governed AI.

The gapThe gap is proof: a record a regulator can check without the vendor present.

Tallyseal is for the part they leave open: changes to your core systems that someone has to sign for.

Design partners

Bring one problem, and work through it with us.

We're taking on a small number of firms and delivery partners as design partners. Bring one problem, such as a rule set, a control or a feed, and we'll work through it together.

Email hello [at] tallyseal.com