Hyperdrift

Hyperdrift · Field notes

AI agents
field notes.

What an agent should be allowed to do, how it proves the work is done and where it fits in work your team already runs.

← All field notes
More topics

8 of 16 · AI agents ·

What an agent should be allowed to do, how it proves the work is done and where it fits in work your team already runs.

  1. A processor's key opens one tool compartment while the other compartments remain locked.

    Delegation / Helm

    AI agent permissions: how much authority should you delegate?

    Helm separates diagnosis from action and restricts disruptive operations to Cargo. Its completion-reporting gap shows why permissions and outcome checks need separate tests.

    Recorded demonstration
    Read →
  2. One conversation request rises above routine activity, still linked to its supporting records.

    Priorities / Standup

    AI daily briefs: turn activity into useful priorities

    Standup puts people waiting for a maintainer before routine work. Its recorded output and later MCP checks show why each recommendation needs a source the reader can inspect.

    Public project
    Read →
  3. Application panels open to reveal the project folder behind the controls.

    History and human capability / UI and accessibility

    Is UI holding us back?

    New interfaces can remove work or move it into checking and correction. A historical argument for judging the whole task.

    Historical synthesis
    Read →
  4. One retained shortlist remains connected to a microphone, keyboard and speaker.

    The future of UI / UI and accessibility

    Your work should survive a change of interface

    Speak, inspect, correct and continue. A future interface should preserve the task when the person changes how they interact.

    Design position and research agenda
    Read →
  5. A working app sits on a maintenance cradle with an accessible component, backup cartridge and control dial.

    App operations / Orchestra OS

    Your app works. Who runs it now?

    A live app creates five jobs every week. Give them named owners, agents with limits and receipts, and keep the decisions. What that looks like, and what to ask whoever runs your app.

    Our own apps run on it first
    Read →
  6. An observation board shows work moving through a mechanism beside a manual approval control.

    A peek into Traction / Traction

    Here’s the new deal. UI is for intel. Agents are for operating.

    A peek into Traction’s 24 October release: the board shows what the Growth Manager and Builder are doing and what they delivered. The agents do the work. We decide what becomes work.

    Our Orchestra board · 24 October 2026
    Read →
  7. One mint conversation signal runs through a processor and tool inside an opened computing machine.

    OSSAgent telemetry / OpenTelemetry GenAI conventions

    We got our first PR merged into OpenTelemetry

    OpenTelemetry's GenAI conventions now say how an agent framework can share its conversation ID with the model and tool calls nested inside it. Review narrowed the rule to that one ID; agent naming continues in a separate draft.

    Merged upstream · 30 October 2026
    Read →
  8. An unfinished product sits in a supporting structure between building tools and customer conversations.

    Traction · Part one / Motivation

    Give motivated founders a fair chance

    Why I built Traction to give eager founders sustained help turning their vision into growth.

    Founder perspective
    Read →

Where could this help you?

Bring one workflow, a question or a product you want to improve. We’ll work out a useful first step together.

Describe your workflow →

Get in touch

We’ll use these details to reply to your enquiry.