Tileward

govern the model · govern the agents

Know what your AI knows.
Decide what it's allowed to say.

Tileward organizes what an AI model knows into named tiles, so you can see its knowledge, lock away the parts that are off-limits, and keep a record of every decision it makes.

models ~half the size, same answers locked topics stay locked, even when rephrased every decision recorded
Why Tileward

AI models are useful. They're also opaque.

Three problems come up the moment you put an AI model to work in a real organization. Tileward was built to answer all three.

"Please don't talk about that" isn't a policy.

The usual way to keep an AI away from a sensitive topic is to ask it nicely in its instructions. Rephrase the question cleverly and it often answers anyway, and there's no record of what it decided or why.

Small models make things up.

Compact, affordable models are fast, but when they don't know something, they confidently invent an answer instead of saying so.

Big models are expensive to run.

Full-size models need serious hardware. Most teams would take one that's half the size, if the answers stayed just as good.

How it works

Map it. Watch it. Govern it.

Tileward's core idea is simple: once a model's knowledge is sorted into named tiles, you can treat knowledge the way you treat rooms in a building: see who goes where, and lock the doors that matter.

Map

Tileward sorts what the model knows into named tiles: finance, medicine, software, and so on. Knowledge stops being a blur and gets an address.

Watch

Every question is matched to its tile before the model answers. You can see, in plain terms, which part of the model's knowledge each question touched.

Govern

Lock a tile, and questions about it are politely declined, even reworded ones. Every declined question is recorded, so you can prove the rule held.

Try it

Lock a topic. Watch it hold.

This is a miniature of the real console. Flip the lock on the Stock options tile and see how the same three questions are treated.

Lock the “Stock options” tile ← flip this
log: every decision lands here, with a timestamp.
What you get

Honest numbers, measured in the open.

Everything below was measured head-to-head inside the console, and you can re-run every comparison yourself.

~60×

faster at saying no

The usual approach has the model write a whole reply just to decide whether to refuse. Tileward decides before a single word is written: about 60× faster, using about 6× less computing per decision.

1.9×

smaller models, same answers

Tileward's compression makes a model roughly half the size and about 1.4× quicker to respond, with answers that are nearly indistinguishable. Compare them side by side, live.

0

made-up answers about your documents

Point Tileward at your own files and it answers from what they actually say, quoting its sources, instead of guessing. That stops the confident inventions small models are known for.

100%

of decisions on the record

Every conversation, every comparison, and every declined question is saved. Dashboards roll it up per person and across the whole team, so "did the rule hold?" is a lookup, not a debate.

Straight talk: a lock is a guard at the door, not an eraser.

Locking a tile doesn't delete knowledge from the model. Genuinely erasing something from an AI model is an unsolved problem, and we'd rather tell you that than pretend otherwise. What Tileward gives you is a guard that recognizes the topic even in disguise, declines to discuss it, and writes every decision down. For "don't surface this topic," that is the strongest tool available today. And unlike a promise buried in instructions, you can audit it.

The console

One place to see it all.

Tileward ships as a single web console. Eight rooms, each with one job.

Dashboard

The big picture: how well the locks are holding, and what they're saving you.

Chat

Talk to the model. Locked topics are declined, everything else just works.

Documents

Upload your files and get answers drawn from them, with the sources shown.

Compare

The full-size model and the half-size one, answering the same question side by side.

Arena

Tileward's lock vs. the "just ask nicely" approach, scored on the same test.

Tiles

Browse the map of what the model knows, tile by tile.

Administer

Set the rules: lock a tile, unlock it, or switch the guard on and off.

History

Every conversation and every test, saved and replayable.

Questions

The short answers.

Do I need to be technical to use it?

No. The console is point-and-click: browse the tiles, flip a lock, chat, upload a document. Setting up the system itself is a job for your technical team, but using and governing it isn't.

What happens when someone asks about a locked topic?

They get a polite, clearly-marked refusal, and the attempt is recorded with a timestamp. Reworded and disguised versions of the question are caught too; that's exactly what the Arena room measures.

Does locking a topic make the model worse at everything else?

No. The lock sits in front of the model and only intercepts questions that match the locked tile. Unrelated questions pass straight through, unchanged.

Is the locked knowledge deleted?

No, and we say so plainly: it's access control, not deletion (see "Straight talk" above). The knowledge stays inside the model; Tileward makes sure it doesn't come out, and keeps the receipts.

Where does my data live?

On your own machines. The models run locally, your documents stay in your corpus folder, and history is stored in your own database. Nothing is sent to a third party.

How is this different from writing rules into the AI's instructions?

Instructions are a request; Tileward is a checkpoint. In our head-to-head tests the instruction approach was slower, cost about six times more per decision, blocked things it shouldn't have, and could be talked around by rephrasing. The tile lock decides before the model writes a word, and it leaves an audit trail.

Talk to us

See it on your own use case.

Register interest in a live demo, or just start a conversation. Prefer email? hello@tileward.com reaches us directly.

See your model's map.

Tileward runs on your own hardware and comes with everything included. Ask us for a walkthrough. We'll bring the console.