Know what your AI costs. Prove what it got right.
Analect is ETT's platform for running AI as an accountable operating cost. It forecasts what each AI workload should cost and which model should do it, and it certifies AI outputs claim by claim against the documents they came from.
Where to start Two fixed-price services are the way in. Each runs for three weeks on your own bills or outputs, and leaves you with a report you keep.
Two fixed-price services, three weeks each
Each runs on your own bills or outputs, at a fixed fee agreed before work starts, and leaves you with a report and a working file you keep.
Try the method before you talk to anyone
Built on the same method as the paid work, with no account needed. They live on Analect's own site, analect.ettgroup.ai.
The workflows behind the services
Both services run on Analect. These are its workflows, and how you can use each one today.
Analect Forecast
Prices every AI workload across the model catalog, from your bills or a plain description, with the reasoning behind each pick and the catalog's date on every figure.
Part of the AI Spend ForecastAnalect Evidence File
Breaks an AI output into its claims and checks each one against its source with two independent models, quoting the passage every verdict rests on.
Part of the Accuracy Evidence FileAnalect Explorer
Decomposes documents into knowledge fragments, each tied to the sentence it came from, so you can see what a document actually asserts.
Access arranged as part of a pilotAnalect Proof
Asks the same questions of a document and its fragments, and reports agreement, correctness and completeness separately, with the tokens each route used.
Access arranged as part of a pilotAnalect Store
Weighs every form your material could be kept in, in actual bytes, and models keeping your sources against replacing them.
Access arranged as part of a pilotChange the unit of knowledge
A language model has no index into a document. To answer a question it reads everything, so every question pays for every token, and the same document is paid for again on the next question. Analect's knowledge engine reads a document once and decomposes it, one way, into knowledge fragments: small structured statements of what the document asserts, each tied to the sentence it came from. A question can then retrieve the fragments that hold its answer rather than the pages around them.
The engine is in pilot. We will publish its figures when they hold beyond our own sample, with the method beside them, and not before. Until then the way to find out what it does on your material is a pilot that compares it with your current retrieval and reports the questions where it did no better.
Four situations where it does not pay
You need the whole document every time
Summarization, full-document review and drafting from a complete source all need the entire text. Fragments are larger than the source at that level, so this costs more, not less.
Your documents change constantly
Decomposition has an up-front cost and is paid again whenever a document changes. A corpus rewritten weekly may never repay it.
You ask each document one question, once
The saving comes from asking a stable corpus many questions. One question against one document does not amortize the processing.
Your corpus is small
If reading everything is already cheap, the arithmetic does not need changing. Fix the problem you have.
What we keep, and what we don't
Your bills stay in your browser
The AI Spend Forecast reads your billing files in your browser and never uploads them. We keep the forecast built from them, and you can leave the cost figures out.
Your documents are not kept
The Accuracy Evidence File never keeps your source documents or the outputs themselves. We keep the certificates: the claims, and the quotes each verdict rests on.
Named models, named terms
Checks run on models from Anthropic and OpenAI, through Vercel's AI Gateway, under their commercial API terms. Our sub-processor list is available on request.
Deployment options, controls and procurement detail are on our trust page.
Start small, and decide on evidence
A fixed-price service
Three weeks on your own bills or outputs. You keep the report and the working file whatever you decide next.
A pilot
Where the service shows something worth going further on, a fixed-fee pilot puts the workflows in front of your team on an agreed slice of your estate.
The platform
Where the pilot earns it, Analect in your environment, with routing, governance and the evidence trail set up to run.
- Every stage has a fixed fee, agreed in writing before work starts.
- Every report includes what came back flat, not only the wins.
- If the numbers do not justify going further, you stop, and the report is still yours.
The Cost of Asking
Why enterprise AI bills keep rising as token prices fall, and how changing the unit of knowledge changes the arithmetic. The public edition is free. A fuller edition with the detailed method is shared under a standard mutual NDA.
- The bills of enterprise AI, and why reading documents whole is the structural cause
- Where Analect sits against compression, retrieval and gateways
- The early measurements from our own sample, and what they do not cover
- How to test the approach on your own estate
Get the public edition
Free, from the Analect site. A fuller edition with the detailed method is shared under a standard mutual NDA on request.
Book a thirty-minute demo
We show the Forecast and the Evidence File on worked material, then talk about what either would look like on your bills or your outputs, or about a pilot on your own documents. We agree the scope and the fee in writing before anything starts.
Requesting a call commits you to nothing.
Ask for a time
Booking is on the Analect site. Tell us what you want to look at and we come back with times that suit.
Or email sales@ettgroup.ai.
Procurement and technical questions
What is Analect?
Analect is ETT's platform for running AI as an accountable operating cost. It forecasts what each AI workload should cost and which model should do it, and it certifies AI outputs claim by claim against the documents they came from. Most customers start with one of two fixed-price services: the AI Spend Forecast or the Accuracy Evidence File.
Do we need to buy software to start?
No. Both services are delivered by ETT on Analect, at a fixed fee, over three weeks. Your team gets its own logins to the working forecast or evidence file for the length of the engagement.
Where does our data go?
The AI Spend Forecast reads your billing files in your browser and never uploads them. The Accuracy Evidence File does not keep your documents or outputs; it keeps the certificates. Checks run on models from Anthropic and OpenAI under their commercial API terms, and our sub-processor list is available on request.
Does Analect reduce what we spend on AI?
The AI Spend Forecast shows where model choice, caching and seat decisions would change your bill, and by how much, and it says what to test before you move anything. The knowledge engine, which is designed to cut the context each question needs, is in pilot, and we will publish its figures when they hold beyond our own sample.
Is Analect a RAG tool?
Its knowledge engine solves a related problem differently. Retrieval sends less of a document; the engine changes what a retrievable unit is. Fragments are structured statements tied to their source sentences rather than prose chunks. Whether that is better for you is a question for a measured comparison against your existing retrieval, which is what a pilot runs.
Do we have to delete our source documents?
No, and nothing about Analect suggests you should. Fragments are an index into your knowledge, not a replacement for the record. Each fragment links back to the sentence it came from, which only works while the source exists.
Which workloads does the knowledge engine not help with?
Four of them. Summarize-everything work, because at whole-document level a fragment set is larger than the source. Corpora that change constantly, because decomposition is paid again on every change. Documents you question once, because there is nothing to amortize against. And small corpora, where reading everything is already cheap.