Koca Ventures Ltd
71-75 Shelton Street
Covent Garden, London
WC2H 9JQ, United Kingdom
Registered in England & Wales — 16231043
AGENTIC SYSTEMS & AUTOMATION
Agents that do the work —built for production, owned by you.
The demo is the easy part — the moat is agentic AI that survives real load, real data, and a real audit. We build custom agent harnesses around your team's workflow, with the code and the keys in your hands.
▶Product walkthrough — an agent loop running end to end (coming soon)
WHAT WE BUILD
Four ways teams put agents to work
FLAGSHIP — BUILT AND RUN BY US
Real systems, not slideware
01
On-premise document intelligence for a property brokerage
A local-first brokerage CRM with a hand-built RAG layer: documents ingested, embedded, and answered with citations entirely on the firm's own hardware — hybrid retrieval, a local LLM, and an MCP server exposing the corpus as read-only tools.
02
Agentic ops + secure edge for the field
For environments where the data can't leave the perimeter: private agentic software over a client's own RFIs, SOPs, and project documents, paired with on-device vision at the edge — local inference, signed updates, audit logs.
03
A B2B platform we built and operate
atmosverde — a B2B carbon platform we designed, built, and run in production. A real shipped product behind the same engineering bar we bring to client work.
A lot of “agentic” projects are expensive automation wearing a new label. We'll tell you when you don't need autonomy — a bounded agent that handles the routine and hands the rest to a person is usually cheaper, more reliable, and easier to trust.
Also: edge AI & computer vision (on-device perception) and robotics simulation. The same low-level systems depth shows up in our security research, which has been acknowledged by NVIDIA.
QUESTIONS
Straight answers
Is this just no-code automation?
No. No-code tools (Zapier, Make, n8n) are great for simple glue. We build what they can't reach: custom agent harnesses with real tool use, memory, approval gates, and on-premise deployment — wired into your actual systems. Most pilots fail on integration and operational fit; that's the gap we work in.
Does our data leave our network?
Only if you decide it should. On-premise deployment is first-class: self-hosted inference, local vector and graph stores, signed updates, role-based access, audit logs. The default keeps documents and customer data inside your infrastructure; hosted models are an opt-in.
What happens when the model gets something wrong?
We design for it: bounded harnesses with approval gates on anything consequential, structured outputs validated before they're acted on, and tracing showing why the agent did what it did. Fully autonomous is rarely what you want — the agent handles the routine and routes the hard cases to a person.
Are we locked into you?
No. You own the runtime, the keys, the data stores, and the source — built on open standards, handed over so your own engineers can run and extend it. Discretion is part of the deal: we don't put your name on our website either.
How do you price it?
Per engagement — there's no list price. The typical shape: a short paid scoping, a fixed-scope build, then an optional retainer. Tell us the problem and we'll scope it honestly.
Which models do you use — Claude, GPT, or local?
Whichever fits the workload. Sensitive on-premise work runs local models via vLLM or Ollama; where data sensitivity permits and the reasoning is hard, Claude or GPT through their agent SDKs. Many production systems are hybrid.
Last reviewed:
READY TO TALK?
Start with one pain point
The strongest opening isn't a generic AI pitch. Share one workflow that hurts — document Q&A, follow-up chaos, after-hours calls, procurement — and we'll scope a small build around your real data before any larger commitment.