Service / AI
Give your AI a memory that lasts.
Persistent memory and knowledge graphs for agents and teams: facts, decisions and commitments extracted from your work and kept with their sources.
[ 01 ]The short answer
What is AI Memory and Knowledge Graphs?
AI memory is the layer that lets an assistant or agent keep what it learned beyond one conversation. We build it in tiers: a durable record of events, a background process that extracts facts, decisions and commitments, a knowledge graph that links them, and retrieval that brings the right ones back at the right moment. Every fact keeps a link to its source and nothing is overwritten, so the memory can be checked and corrected.
What you get
- Memory service with source-linked facts
- Knowledge graph schema and store
- Extraction pipelines
- Graph and timeline views
- Retention and redaction policies
[ 02 ]What we build
The pieces, built to last.
- 01
Event records
An append-only log of meetings, messages, tickets and documents: the source of truth every memory points back to.
- 02
Extraction agents
Background jobs that pull commitments, decisions, entities and obligations out of raw activity.
- 03
Knowledge graphs
Entities and relationships in a graph you can query, visualise and correct.
- 04
GraphRAG retrieval
Graph traversal combined with semantic search, for questions about how things connect.
- 05
Decision history
Superseded and rejected options kept with dates, so the system knows what changed and why.
- 06
Forgetting rules
Expiry, redaction and per-user scoping, because some things should not be remembered.
[ 03 ]Where it pays off
Where it earns its keep.
- 01
Enterprise implementations
Commitments and decisions tracked across months of calls and tickets, with slippage flagged.
- 02
Legal matters
Terms and edge cases from past matters surfaced when a new one looks similar.
- 03
Account management
Every promise to a customer remembered, so a handover does not reset the relationship.
- 04
Long-running agents
Agents that pick up where they left off, instead of starting each session from zero.
[ 04 ]How we deliver
Four steps, one team, start to finish.
The same people scope it, build it and stay after launch. Timings are typical for a first release; we agree yours after the deep dive.
- 01Week 1
Find the decision
We pick the decision or task worth automating, measure how it is done today and agree what better means in numbers.
- 02Week 1 to 2
Build the eval first
A labelled test set from your own data comes before any prompt or training run, so every change is scored, not argued.
- 03Weeks 2 to 10
Build with guardrails
Models suggest, code decides. Permissions, injection checks, human override and audit logs are part of the first version.
- 04Ongoing
Ship and improve
We launch to real users, watch cost, latency and quality per request, and feed failures back into the eval set.
[ 05 ]Stack
Tools we reach for.
Chosen per project, and we work in yours. Nothing here is a lock-in: you own the code and the accounts.
- Neo4j
- Postgres
- pgvector
- Rust
- Python
- Claude
- Gemini
- Microsoft GraphRAG
- Slack and Teams APIs
[ 06 ]Related work
Built by the same team.
[ 07 ]Further reading
Problems we found, and how we would solve them.
- Retrieval3 min read
RAG still hallucinates. Grounding takes more than retrieval
ProblemRetrieval-augmented systems still invent facts, cite passages that do not support the claim, miss the decisive document and agree with false premises.ProposalTreat grounding as a pipeline with checks: structure-aware chunking, hybrid retrieval and reranking, citations at passage level that are verified after generation, abstention when evidence is missing, and evaluation of retrieval and answers separately.Read the proposal - AI agents3 min read
Why AI agent pilots stall before production
ProblemAgent pilots impress in demos and stall before production because nobody can show they work, limit what they can do, see what they did, or overrule them.ProposalDraw a hard decision boundary: the model scores and drafts, deterministic code decides and acts, every step is logged with its reasoning, and a person can overturn any decision in one click.Read the proposal
[ 08 ]FAQ
Questions buyers ask.
RAG searches documents as they are. Memory processes activity into facts and decisions over time, keeps their history, and links them, so it can answer what changed and who agreed to what.
Yes. We build memory to be inspectable: every fact has a source, a date and an owner, and can be corrected or removed.
Yes. DeltaMemory and Holmes both run on memory architectures we designed; both are on our work page.
[ 09 ]More AI services
- Custom AI Model DevelopmentA model trained on your data, owned by you.
- LLM Fine-Tuning and DistillationFrontier quality at a fraction of the cost.
- AI Agent DevelopmentAgents that finish the job, inside the rules.
- AI Workflow AutomationHours of back-office work, done in minutes.
- RAG DevelopmentAnswers from your documents, with citations.
- MCP Server DevelopmentYour product, usable by every AI assistant.
- Voice AI AgentsEvery call answered, qualified and logged.
- Document AI and Intelligent Document ProcessingPaperwork turned into clean, checked data.
- Private LLM DeploymentAI on your infrastructure, data never leaves.
- LLMOps, Evaluation and GuardrailsKnow your AI works before customers find out.
- Predictive ML and ForecastingDecisions made on what will happen next.
One company at a time