refactor(handoff): remove prescriptive batching — subcontractor determines its own methodology
This commit is contained in:
+50
-83
@@ -131,44 +131,36 @@ Build an internal working list of all user labels with:
|
||||
|
||||
---
|
||||
|
||||
## Phase 4 — Build Batch Plan
|
||||
## Phase 4 — Prepare the Task Order
|
||||
|
||||
Divide the label inventory into batches. Each batch becomes one task order.
|
||||
Claude's job here is to prepare the context — not to plan the subcontractor's methodology.
|
||||
A capable peer model will determine its own optimal approach once it has the project context
|
||||
and the output requirements. Do not prescribe how many messages to review, how to split the
|
||||
work, or in what order to process labels.
|
||||
|
||||
### Primary split: by top-level label category
|
||||
### Step 4.1 — Compile the full label inventory
|
||||
|
||||
Each top-level category (Finance, Vendors, Clients, etc.) is one batch.
|
||||
From the label list built in Phase 3, prepare a complete LABEL_LIST.csv containing ALL user
|
||||
labels with message counts, scan priority guidance, and bylaw references. This is the
|
||||
subcontractor's working inventory — give it everything.
|
||||
|
||||
### Sub-batch trigger: split a top-level category if EITHER is true
|
||||
- The category has more than 5 sublabels
|
||||
- The category has more than 500 total messages across all its sublabels
|
||||
### Step 4.2 — Create the initial task order
|
||||
|
||||
When sub-batching, split by:
|
||||
- Natural sublabel groupings (e.g., Clients/Resellers as one batch, Clients/Corporate as another)
|
||||
- Or alphabetically for very large flat lists
|
||||
Generate one task order covering the full label inventory. The subcontractor decides
|
||||
whether to process everything in one pass or propose its own batching plan. Both are fine.
|
||||
|
||||
### Batching rules
|
||||
- Never put more than 8 labels in a single task order
|
||||
- Never put more than 1,000 messages in a single task order (estimate from counts)
|
||||
- Always keep a top-level category whole if it fits within the limits
|
||||
- Notifications, Personal, and system-like labels (low volume, clear rules) can be
|
||||
grouped together into a single "Miscellaneous" batch
|
||||
If the subcontractor returns a batching proposal rather than results:
|
||||
- Review the proposal with the user in plain English
|
||||
- Ask for approval
|
||||
- Create additional task order folders for subsequent batches as requested
|
||||
|
||||
### Present the batch plan to the user
|
||||
### Step 4.3 — Confirm with the user before creating Drive files
|
||||
|
||||
Before generating any files, show the user the plan:
|
||||
> "I'm going to prepare a task order with your full label inventory and let [tool] determine
|
||||
> the most efficient way to work through it — it may do everything in one pass or propose
|
||||
> splitting into batches. Either way works. Ready to go?"
|
||||
|
||||
> "Here's how I'm going to split the work into task orders:
|
||||
>
|
||||
> Batch 1 — Finance (3 labels, ~800 messages)
|
||||
> Batch 2 — Vendors (4 labels, ~400 messages)
|
||||
> Batch 3 — Clients/Resellers (5 labels, ~2,100 messages)
|
||||
> Batch 4 — Clients/Corporate (2 labels, ~300 messages)
|
||||
> Batch 5 — Development + Notifications + Personal (6 labels, ~600 messages)
|
||||
>
|
||||
> That's 5 task orders total. Does this look right, or do you want to adjust anything?"
|
||||
|
||||
Wait for approval. Adjust if needed. Then proceed.
|
||||
Wait for confirmation, then proceed to Phase 5.
|
||||
|
||||
---
|
||||
|
||||
@@ -184,68 +176,52 @@ Inside each batch subfolder, create 4 files using `create_drive_file`:
|
||||
This is the text the user pastes into the subcontractor tool. It must be entirely
|
||||
self-contained — the user pastes it without modification.
|
||||
|
||||
**PROMPT.md template (ChatGPT with Gmail skill):**
|
||||
**PROMPT.md template (ChatGPT with Gmail skill / Gemini):**
|
||||
|
||||
```
|
||||
You are a Gmail classification analyst working on an inbox organization project.
|
||||
You are a Gmail classification analyst. You have been given a Gmail inbox organization project.
|
||||
|
||||
PROJECT CONTEXT: Before doing anything else, read the file CONTEXT.md that has been
|
||||
attached to this message. It contains the taxonomy, bylaws, and project rules that
|
||||
govern all rules you propose. Do not proceed without reading it.
|
||||
Read CONTEXT.md before doing anything else. It contains the taxonomy, bylaws, and project
|
||||
decisions that govern all rules you propose.
|
||||
|
||||
YOUR TASK — [BATCH NAME, e.g., "Finance label tree"]:
|
||||
Walk the Gmail labels listed in LABEL_LIST.csv. For each label:
|
||||
Your goal: analyze the Gmail labels in LABEL_LIST.csv and propose classification rules that
|
||||
will automatically sort incoming email according to the taxonomy in CONTEXT.md.
|
||||
|
||||
STEP 1 — Review messages
|
||||
- Open the label in Gmail
|
||||
- Review the 20-30 most recent messages (not just subject lines — look at sender domains)
|
||||
- Note: who is sending mail to this label, what subject patterns appear, any attachment types
|
||||
You have direct access to the Gmail account. Use that access as you see fit to identify
|
||||
sender patterns, domain signals, subject patterns, and attachment types — whatever gives
|
||||
you confident rule proposals.
|
||||
|
||||
STEP 2 — Identify patterns
|
||||
For each distinct sender domain you find:
|
||||
- Does it clearly belong in this label? Or in a different one?
|
||||
- Is a subject qualifier needed to avoid labeling too broadly?
|
||||
- Does it send emails that clearly require separate work-type labels
|
||||
(e.g., invoices vs. general updates from the same domain)?
|
||||
- Are there attachment patterns (file types, naming conventions)?
|
||||
Return your findings using the exact schemas in OUTPUT_FORMAT.md:
|
||||
|
||||
STEP 3 — Propose rules
|
||||
Return exactly three CSV files using the schemas in OUTPUT_FORMAT.md:
|
||||
filter_rules.csv — rules Gmail can execute natively (domain, subject, participant)
|
||||
apps_script_rules.csv — rules requiring attachment filename/extension inspection
|
||||
taxonomy_notes.csv — taxonomy gaps, policy observations, and anything needing review
|
||||
|
||||
filter_rules.csv — rules Gmail can apply natively (domain, subject, participant pattern)
|
||||
apps_script_rules.csv — rules that require attachment filename inspection
|
||||
taxonomy_notes.csv — taxonomy gaps, policy observations, things that need Claude's review
|
||||
If the label inventory is large and you prefer to work in batches, propose a batching
|
||||
plan and execute the first batch. Subsequent task orders will be prepared for remaining work.
|
||||
|
||||
IMPORTANT RULES:
|
||||
- Include your basis for EVERY rule in the notes column
|
||||
- Use participant-domain logic (from OR to OR cc) for client/reseller domains
|
||||
- Use from-only logic for vendors, notification services, and financial senders
|
||||
- Do NOT propose rules that depend on reading email body text — filters and Apps Script
|
||||
work from headers, subject lines, and attachment filenames only
|
||||
- Confidence and risk ratings must reflect your actual certainty
|
||||
- Flag ambiguous cases in taxonomy_notes.csv with status "do_not_automate_yet"
|
||||
Hard constraints that must be respected:
|
||||
- Participant-domain logic (from OR to OR cc) for client and reseller labels
|
||||
- From-only logic for vendors, services, and financial senders
|
||||
- No rules dependent on message body text — filters and Apps Script work from headers,
|
||||
subjects, and attachment filenames only
|
||||
- Document your basis for every proposed rule in the notes column
|
||||
- Use taxonomy_notes.csv status "do_not_automate_yet" for anything you are not confident about
|
||||
|
||||
Return all three CSV files as attachments. Do not summarize them — just return the files.
|
||||
Return all three CSV files. Do not summarize — just return the files.
|
||||
```
|
||||
|
||||
**PROMPT.md template (Gemini):**
|
||||
Use the same content as ChatGPT above. Gemini's Gmail integration works identically
|
||||
for this task.
|
||||
|
||||
**PROMPT.md template (Generic / Unknown tool):**
|
||||
|
||||
```
|
||||
You are a Gmail classification analyst working on an inbox organization project.
|
||||
[Add this preamble before the main prompt above:]
|
||||
You need direct Gmail access for this task. Before proceeding, confirm that you can
|
||||
read Gmail labels and message sender information for this account. If you cannot, say
|
||||
so immediately — do not attempt to work around it.
|
||||
|
||||
You need Gmail access for this task. Before proceeding, confirm that you can read
|
||||
Gmail labels and message sender information (not message bodies) for this account.
|
||||
If you cannot, say so immediately.
|
||||
|
||||
[Then continue with the same STEP 1-3 content as ChatGPT template above]
|
||||
[Then continue with the ChatGPT template above]
|
||||
```
|
||||
|
||||
Substitute `[BATCH NAME]` with the actual batch name (e.g., "Finance label tree").
|
||||
|
||||
---
|
||||
|
||||
### File 2: `01_CONTEXT.md`
|
||||
@@ -463,16 +439,6 @@ Notes: Batches created: [list batch names]. Each returns 3 CSV files to import.
|
||||
|
||||
---
|
||||
|
||||
## Batch Size Reference
|
||||
|
||||
| Condition | Action |
|
||||
|---|---|
|
||||
| Top-level category ≤ 8 labels AND ≤ 500 messages | One batch |
|
||||
| Top-level category > 5 sublabels OR > 500 messages | Split into sub-batches |
|
||||
| Never more than 8 labels per batch | Split further |
|
||||
| Never more than ~1,000 messages per batch | Split further |
|
||||
| Notifications + Personal + low-volume misc | Group together |
|
||||
|
||||
---
|
||||
|
||||
## Embedded Template: Rule ID Format
|
||||
@@ -509,3 +475,4 @@ FINANCE / VENDOR / CLIENT / OPS / DEV / SALES / TRAVEL / NOTIF / SUPPORT / DOC /
|
||||
|
||||
5. The subcontractor proposes. Claude decides. Always.
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user