Experiments

Experiments

One question, one attempt, one honest account of how it went. Each write-up carries its hypothesis, its architecture, what came out of it, and what it does not prove.

In productionPrototypeExploratoryStatus is the state of the work, not an aspiration.
  1. Prototype

    Reading what the customer actually sent

    Customers do not send clean text. They send a scanned price list, a photographed sign and a PDF exported from a word processor in 2011.

    multimodaldocumentsragknowledge
  2. Exploratory

    MCP as the tool boundary for a multi-tenant agent platform

    MCP standardises how tools are described and transported. It does not standardise who is allowed to call them - and in a multi-tenant product that is most of the work.

    mcpagent-infrastructuretool-useintegrations
  3. Exploratory

    A browser agent for portals that have no API

    Reading from portals was tractable. Writing to them was not - and the honest conclusion was to stop trying to make it autonomous.

    computer-usebrowser-agentsautomationsafety
  4. Prototype

    One agent, four inboxes: sharing context across channels

    The channel adapters were the easy part. Deciding that the caller and the web visitor are the same person is the actual research problem.

    omnichannelagent-memoryidentityconversational-ai
  5. In production

    Barge-in without false interruptions

    Interruption handling is a two-sided error problem: stop too eagerly and the agent is skittish, stop too late and it talks over the caller.

    voice-aiturn-detectionbarge-in
  6. In production

    Where the milliseconds go in a phone call

    A turn-level latency budget for a telephone voice agent, stage by stage - and the three places where overlapping work buys more than a faster model does.

    voice-airealtimelatencyarchitecture
  7. In production

    Booking an appointment end to end, without a human in the loop

    The model part is trivial. The hard parts are concurrency, timezones, and what the agent says while a calendar API is thinking.

    ai-agentstool-usevoice-aiintegrations
How to read these

An experiment is not a product announcement. Where a number appears as a diagram it is a design budget unless a sentence says otherwise, and where we do not have a figure we are willing to defend, we say that instead of publishing one.