Make Every Commercial Decision From the Evidence of How You Win.
Your team gets answers grounded in how your company wins and grows customers, and sees the patterns worth acting on while there is still time to act. The brain looks for patterns across every source, inside the business and outside it, and a commercial architect weighs each one with your team before anyone relies on it.
Answers Your Team Can Act on, From Everything Your Business Already Knows.
Ask Liffey Any Commercial Question, and See the Evidence Behind the Answer.
Liffey answers from 2 places at once: the record your team has agreed, and everything you have connected, read at the moment you ask.
Every passage keeps its own date, so the answer knows which debrief is the most recent, and shows you which ones it used.
Every Signal Is Kept Until It Becomes a Pattern Worth Acting On.
A single remark in 1 call is noise. The same remark from 4 accounts over 2 months is a pattern, and the brain tells them apart by keeping the first one until the fourth comes in.
Evidence builds against the pattern it belongs to, weighted so recent evidence leads while older evidence stays in the count. Keeping evidence between sessions is what lets the engine weigh it, and it is what makes a company brain more than a search index.
You See a Pattern the Moment It Matters, With the Case for It and Against It.
Each night the engine attaches what is new to the patterns it is already tracking. Each is scored on how often it recurs, across how many distinct sources, and how strongly against your own baseline.
When one crosses the bar, the record is swept for corroboration and for contradiction, and the counterpoints go on the card. A pass that only ever confirms is confirmation shopping.
Your Team Knows What Was Decided, When, by Whom, and What Would Change It.
Conclusions are recorded as decision blocks, and each one states when it was made, by whom, whether it is locked, working or gated, and what would have to change for it to stop being true.
When one of those conditions breaks, the brain raises it straight away.
Your Team Starts Every Week From the Same Numbers, Read the Same Way.
The pipeline is snapshotted on your meeting day and at every month end, so this week is read against last week, on the same numbers. One definition of a qualified lead is set once and used by every surface that counts one.
Month-to-date is compared on elapsed days, so day 3 is read against the first 3 days of the month before it.
The Weekly Snapshot
The pipeline is snapshotted on the day your team meets, and again at every month end, so this week reads against last week on the same numbers.
Notes Go Onto Each Deal
Choose the call where your team reviewed the pipeline, and Liffey writes a note and a next step against every deal it discussed, which owners can then edit.
New Evidence Weighed
What is new is attached to the patterns already being tracked and scored against your own baseline. A quiet night stays quiet.
Patterns Raised Once
Liffey reads the open findings together and joins any seen under 2 names, so your team makes 1 call on each.
An Owner Decides
A finding waits for a verdict with its corroboration and its counterpoints attached, alongside member proposals and generated documents.
Proposals, Decks and One-Pagers Your Team Can Use the Same Day, Built From What You Have Already Agreed.
Assets are built with the artefact on the left and the chat on the right, so each draft improves on the last. Versions stay live, with a present mode and a PDF alongside.
At build time you pull a company, contact, deal, meeting or transcript straight in, so a one-pager starts from the real account.
- One-pagers
- Sales presentations
- Qualification checklists
- Handover briefs
- Expansion proposals
- Board-ready decks
- Whitepapers
- Value calculators
Your Knowledge Stays Current Every Night, From the Systems You Already Run.
Connections cover CRM, meetings and calls, documents and drives, chat, analytics, advertising, search and design. Each connected system syncs nightly with content-hash change detection, so only what actually changed is read again.
Connecting a credentialed system is an owner action and the tokens are encrypted at rest. Every link, upload and forwarded email appears as its own row, with who added it and when.
Reach Liffey From the Assistant Your Team Already Has Open.
Every workspace is an MCP server your own assistant can read from. Connect it inside the assistant your team already uses and ask your own model questions grounded in your own record, in the tool they are already working in.
Access runs on personal, workspace-scoped tokens: hash-stored, shown once, revocable. A versioned REST API and a CLI have the same standing.
In Slack, type /liffey or mention it, and the answer comes back to you privately with its sources linked. A connected AI reads your writing rules first and checks its draft against them before it delivers.
You Can See Exactly What Happens to Your Data, From the Moment It Comes In.
A CRM record, a recorded call, a support thread, an ad account, a spreadsheet, a forwarded email, a page you pointed us at. All of it takes the same path in.
Anything You Connect Is Read to Text
A deal record, a call transcript, a chat thread, a campaign report and a web page all come in as text. Word, Excel, PDF and PowerPoint are parsed on the way in. What moves forward is the extracted text, and the text alone is what the product keeps.
Personal Details Are Scrubbed, If You Ask for That
With redaction on, email addresses, phone numbers and bank identifiers are replaced with typed placeholders at this point: before storage, before embedding, before any model sees it, so what is stored already contains the placeholder. Names are kept deliberately, because naming your champion is part of reasoning about the account.
The Text Is Split Into Passages and Embedded
The text is divided into passages, and each one is turned into a vector so it can be found by what it means. Every passage keeps its source and its date. Embedding and storage both happen in Frankfurt.
Later Syncs Re-Read Only What Changed
Each sync compares a content hash against what is already stored, so only what changed is parsed and embedded again. That is why a nightly rhythm across your whole stack stays cheap and quiet.
New Material Is Weighed Against Everything Else
The nightly pass reads every new call, email, file and web page in full, and attaches what it finds to the patterns already being tracked, scoring each on how often it recurs, across how many distinct sources, and how strongly it reads against your own baseline. A Sunday pass then merges the strands that turn out to be a single pattern seen under 2 names. A pattern surfaces once it crosses the bar, so a quiet night stays quiet.
The Right Passages Are Retrieved When Somebody Asks
Each question is asked several ways, recent evidence is weighted higher, and the answer shows which passages it used and when each was written. The agreed record is read too, so an answer draws on what your team decided as well as on what the sources say.
The Personal Material Ages out. The Commercial Record Stays.
Transcripts, email and chat have a retention window you set, 365 days by default. When material reaches it, the substance is first distilled into a dated, scrubbed summary that joins the permanent record, and only then is the raw item and its passages deleted. Your own documents and uploads are exempt as curated material; connected CRM and analytics regenerate on every sync. Components, decisions, findings and the weekly history stay for the life of the workspace.
Specification.
Retrieval
- Grounding
- The component record and your connected knowledge base, both always active
- Query handling
- Fan-out to several phrasings, reranked with a recency weighting
- Provenance
- Every passage keeps its source and date, shown with the answer
- Live web
- Fetches a named page mid-answer, behind request-forgery checks, and keeps it as a real source
Weighing New Evidence
- Cadence
- Nightly, with a weekly consolidation pass that merges duplicate strands
- Scoring
- Recurrence, distinct sources, and intensity against your own baseline
- Surfacing
- A finding appears once it crosses a bar. A quiet night stays quiet
- Verdicts
- Set aside, Monitor, or Lock it in
Sources
- Connections
- Reads the commercial systems you already run, and leaves them as your team left them
- Sync
- Nightly, with content-hash change detection so only changes are re-read
- By email
- Each workspace has an address; forward a thread and it is added
- Removal
- Archive and keep what was learned, or purge source and passages together
Your AI
- Routes
- MCP endpoint, versioned REST API, and a CLI. Each one reads your record
- Tokens
- Personal, workspace-scoped, hash-stored, shown once, revocable
- Your model
- Anthropic, Gemini, or any OpenAI-compatible endpoint, tested before it saves
- Managed
- EU inference on AWS Bedrock, with per-workspace daily limits
Control
- Roles
- Owners, members and platform admins. Removal revokes every session
- Versioning
- Every edit versioned, one-click restore, owner-gated
- Redaction
- Every workspace can enable PII redaction at ingestion
- Retention
- A window you set, with the record itself kept beyond it
Where Liffey Runs
- Residency
- Database, compute, inference and embeddings in Frankfurt
- Model terms
- Inputs excluded from training, processed in memory
- Audit
- Append-only, enforced by database grant, actor and before-and-after state
- Hosting
- Shared, your own dedicated database, or inside your own cloud boundary
Your Team Stays in Control of Every Decision and Every Message.
Questions About the Platform.
What Data Does Liffey Read?
Liffey reads the core commercial systems where commercial knowledge already collects: your CRM, meeting recordings, shared drives, chat, email, analytics and advertising. You choose which sources connect and which parts of each one it reaches. Liffey reads them and leaves them exactly as your team left them.
Where Does Liffey Store and Process Our Data?
Every layer runs inside the European Union. The database is managed PostgreSQL in Frankfurt, application compute runs on serverless functions pinned to Frankfurt, and AI inference is Claude via AWS Bedrock in eu-central-1 with Amazon Titan embeddings in the same region.
What Happens to a File After Liffey Reads It?
The text is extracted on the way in, and the extracted text is what the platform keeps. It is split into passages, each one turned into a vector so it can be found by what it means, and every passage keeps its source and its date. Embedding and storage both happen in Frankfurt.
Can We Use Our Own AI Model With Liffey?
Yes. Liffey's own AI can be routed through your governed endpoint: Anthropic, Google Gemini, or anything OpenAI-compatible, which covers Azure and enterprise gateways. A live call is made against your endpoint before the setting is accepted, and one click returns you to managed EU inference.
How Long Before Liffey Is Useful?
The free plan is live in minutes, seeded from your domain's public footprint. With your systems connected, the first answers come back grounded in your own numbers within days. Within weeks, your architect and your team have the strategy written down, and everyone describes what you do the same way.
“We’ve grown by nearly 50% over the past year. In that time, Liffey has helped us better articulate our unique value proposition, evolve our pricing model, reset our go-to-market strategy and build scalable commercial systems. All of which has enabled us to make better decisions on a day-to-day basis and grow with more confidence.”
Nick Comer, Founder & CEO
First Commercial Insights Within Minutes.
Connect the systems you already run, and the first answers come back within days. The full commercial architecture takes weeks, alongside your team.