From the lab.
Notes on runtimes, measurement, and what we find in production.
- 2026-09-14 · Xplore Intelligence
Xplore Intelligence at Cambridge Tech Week 2026
We're one of five finalists in the Live Pitch Competition on Wednesday 16 September, and on the stand at Innovation Alley on Tuesday and Wednesday. Here's what to expect and where to start.
#company#events - 2026-06-16 · Xplore Lab
How we verify AI agent output: architecture of deterministic integrity
LLM-as-judge shifts the problem — it doesn't solve it. Here is how Xplore Integrity captures agent work mechanically, builds a provenance graph, and verifies every claim without another model in the loop.
#agents#integrity#architecture#verification - 2026-06-08 · Xplore Intelligence
Xplore Intelligence at London Tech Week 2026
We're at London Tech Week this week — pitching One to Win on the Ignite stage and running a live agent-vs-human benchmark on the floor.
#company#events - 2026-06-05 · Xplore Lab
Data integrity for AI agents: an old idea, a new producer
Integrity has always meant: does the data still faithfully represent reality? Agents are a new kind of data producer — here is how that classic guarantee can be measured for what they output, and how it compares to today's tooling.
#agents#methodology#integrity - 2026-05-17 · Xplore Intelligence
Xplore Intelligence in Tech Nation's Breakout 50
Recognised as one of the UK's 50 most promising early-stage startups for building reliability infrastructure for AI agents.
#company#recognition - 2026-04-09 · Xplore Lab
Measuring agents you cannot see into
Why the eight-evaluator chain is the lower bound of what a production eval should check — not the end state.
#measurement#methodology#evaluators - 2026-03-26 · Xplore Intelligence
Xplore named among Europe's most innovative startups (Vestbee, March 2026)
Vestbee highlighted Xplore alongside other European teams building in Foodtech, Regtech, SaaS, Medtech, and Edtech.
#company#recognition#europe - 2026-03-21 · Xplore Lab
From training LLMs to training agents
The centre of gravity is shifting. Here is what actually changes when it does — and why the runtime comes before the training method.
#agents#training#runtime - 2026-03-19 · Xplore Intelligence
Xplore joins Scotland's Critical Technologies Supercluster
Building governed, traceable agent execution from inside the UK deep tech ecosystem.
#company#scotland#ecosystem - 2026-02-14 · Xplore Lab
Not another dashboard. Agents that write provenance.
Observability is necessary. It is not enough. Here is what a runtime adds on top of Galileo, Arize, Langfuse, and Braintrust.
#observability#runtime#provenance