todo: split the watcher — a script transcribes, an agent reads
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
@@ -57,14 +57,22 @@ the owner's OS user and can never be granted. Indirection there really is accide
|
||||
prompt from the prompt library, or a chat message; and how a file is marked consumed so it is not
|
||||
picked up twice.
|
||||
|
||||
**This may not need building at all — check that first (owner, 2026-08-21).** A recurring agent
|
||||
job already does it: the same hourly loop that logs a heartbeat can instead be told "look in this
|
||||
folder for new markdown files and file what they contain as todos". No registry, no new trigger,
|
||||
no `pushTurn` door — the agent is already the thing that acts, and the prompt is the
|
||||
configuration. So the honest question before writing any code is **what a built-in watcher would
|
||||
buy over a standing agent job**: probably arrival-time firing instead of a poll, a UI to see and
|
||||
manage watchers, and surviving without a session open. If those are not worth it, the feature is
|
||||
a prompt, not a subsystem.
|
||||
**The split, settled by the owner 2026-08-21: it is two stages, and only one of them is an
|
||||
agent.**
|
||||
|
||||
1. **Audio lands → transcribe.** Purely mechanical: watch the directory, call the transcription
|
||||
service, write the markdown out. A script and a service call, no model anywhere. This is the
|
||||
part that genuinely needs building, and building it as a script is the point — an agent here
|
||||
would be cost and nondeterminism for a job with one correct answer.
|
||||
2. **Markdown appears → read, understand, act.** Reading a note and deciding it is a todo (and
|
||||
which one, and where it belongs) is real agent work. This half needs no new infrastructure:
|
||||
a recurring agent job already does it — the same hourly loop that logs a heartbeat can instead
|
||||
be told "look in this folder for new markdown and file what it contains". The prompt is the
|
||||
configuration.
|
||||
|
||||
So the watcher to build is the dumb one. What a built-in watcher buys over a standing agent job
|
||||
for stage 2 — arrival-time firing instead of a poll, a UI to manage watchers, working with no
|
||||
session open — is worth re-asking then, not now.
|
||||
|
||||
## Prompt library
|
||||
|
||||
|
||||
Reference in New Issue
Block a user