Enquire
Menu
← Research

Research · page 03 of 10

Further back in the archive.

Articles

10 Oct 2026 Make model routing earn its own cost Cheaper small models change the economics of deciding which model to call. Compare direct calls, upfront routing and sequential escalation, including the cost of selecting and checking each answer. Method 09 Oct 2026 Give agents a stop condition at the effect boundary A recent report of unintended model actions shows why an agent needs a defined, testable way to stop at a tool boundary. Permission checks and monitoring must decide the outcome when the task cannot be completed safely. Architecture 08 Oct 2026 Trace an agent evaluation back to the run The UK AI Security Institute’s open-source Transect makes long agent evaluations easier to inspect. Its source-linked labels can help reviewers find episodes worth checking, but do not validate the labels or the final score. Method 07 Oct 2026 Set the boundary for multimodal search EmbeddingGemma 2 brings text, images, video and audio into one local search space. The architecture decision is which content and derived vectors may stay on a device, and which may enter a shared index. Architecture 06 Oct 2026 Plan the evaluation route before healthcare AI scales The Government has accepted all 44 recommendations on artificial intelligence (AI) in healthcare, but much of the implementation detail is still forthcoming. Providers can prepare by deciding how local evaluations will be classified, governed and connected to clinical safety evidence. Governance 05 Oct 2026 Design a content record around the watermark signal OpenAI’s textGrain adds a detectable statistical pattern to selected model output. Publishing systems should treat a positive result as one content signal and retain source, editing and approval history separately. Architecture 04 Oct 2026 Give long-running agents a working account of the task New research on explicit belief states gives agents a way to track what remains unknown and recognise stalled progress. The opportunity is a more useful investigation workflow, with a measurable cost for maintaining that state. Architecture 03 Oct 2026 Choose analysis work with an independent check BootLoops gives AI agents a toolkit for exact and checkable quantitative work. Its useful design lesson is to choose analyses where an independent computation can verify the result, while a domain expert still decides whether the question matters. Method 02 Oct 2026 Hold out the customer before funding the rollout Fresh tickets from familiar accounts do not establish performance on unseen customers. Match the evaluation boundary to the proposed rollout and report the evidence for each population separately. Data 01 Oct 2026 Restore the AI service from a compatible record Approve an AI recovery plan against a restored service that completes useful work. Test document and index compatibility, reconcile current access permissions and state the recovery scope that the evidence supports. Architecture 30 Sept 2026 Test the questions your documents cannot answer Test how an assistant responds when its permitted evidence does not contain the answer. Separate unsupported answers from unnecessary refusals, and measure the human handoff before approving the service scope. Method 29 Sept 2026 Randomise the capacity pool before testing the AI When trial users compete for shared appointments, stock or staff, treatment can change the control group’s opportunities. Design the comparison around that resource before inferring the effect of a full rollout. Method

Bring us the question

Something here already on your desk?

Bring the question, the systems involved and the decision you need to make. We will confirm whether a scoped engagement is appropriate.