Jev: AI Tools & Fast Decisions
A new Jev section covering decision tools, integration choices and the published evidence.
New sections, new pages and meaningful revisions — a dated record of how this website is evolving.
Use this log to catch up on the material added or revised since your last visit. Each entry links to the page itself and explains what changed, so you can decide whether it is relevant to your work. These are changes to our website content; a new technology guide does not mean we have launched a model or deployed a customer system.
A new Jev section covering decision tools, integration choices and the published evidence.
A proposed model-routing workflow, with evaluation, budget controls and fallback design.
How focused checks can support agent input screening, evidence review and action policies.
Live decision loops, parallel typed outputs and the limits of real-time deployment claims.
Provider-reported comparisons, with methodology, dates and limitations beside the charts.
Persistent sessions, sandbox choices and enterprise pilots for managed agent workflows.
Agent-to-agent handoffs, shared context and the distinction between A2A and MCP.
A source-linked September review of model releases and enterprise agent technology.
Revised for V4.1-Flash, including native vision, deployment considerations and dated API pricing.
Updated model availability, enterprise considerations and attributed provider benchmarks.
Updated live voice coverage, with full-duplex interaction and backend delegation considerations.
New marks a newly published page or section. Updated marks a meaningful revision to existing content: for example, a model release, a revised comparison or a change to implementation guidance. Small spelling corrections and routine deployments do not restart a page’s update badge.
Navigation badges remain visible for 30 calendar days, including the publication or update date. The records on this page remain available after that period. A newly published page keeps its New label during that window even if it receives an early revision.
The date here refers to our content, not the launch date of a third-party product. Technology pages carry their own source links, research dates and qualifications. Use those sources to understand the evidence behind a claim and the conditions under which a capability is available.
The work we can name, with the live site, our scope and the boundary made explicit. Select a project to see the evidence; each is a full case study, not a logo or a claim.
Cognitive AI Ltd · 2026
A free sound-wellness app, described by its publisher as AI sound therapy that reads a short vocal sample at the start of a session and generates a soundscape for that moment. We designed and built the website and its backend, produced assets for the iOS and Android apps, and supported the application prototype.
Podswap · 2026
A social-media growth engine for Instagram creators, with YouTube and TikTok to follow. We built all of it — the mark and brand, the website, the prototype, the iOS, Android, Windows, macOS and Linux apps, the AI backend that runs the system, the automated email engine, and the algorithm-intelligence reports it publishes from its own data.
unOpen.AI · 2026
Roxy is a private AI assistant with permanent memory, on a dedicated deployment per user rather than a shared endpoint. We built it from nothing: the mark, the site, the product design, the backend, and the conversational work that makes Roxy feel like a person rather than a prompt box. Currently in closed beta with an open waitlist.
Coherence · 2026
Coherence describes itself as the group behind Sonora, AboutAI, WakeUp and MudShadows — four properties built around ethical, human-centred AI. We generated the identity using AI agents, built the motion system that carries it, and designed and built the landing page now live at coherence.com. AI agents for the business itself are in build.