oneshot-gtm

Taste

Taste is a list of refusals, enforced in code.

A model writing one email cannot see the ninety-nine before it. So the decisions that need that view are made before it writes.

drafts 1 to 99draft 100 sees only itself

The dossier

Research in. Empty data out.

One record per person, built before a word is drafted.

  • research.person$0.050

    the person record

  • live profile

    when LinkedIn is connected

  • enrich.company$0.005

    cached 30 days

  • their product

    two of their pages, then research

dossiersigned
currentRole
title · company · since
organizations
up to 8, current first
company
domain · industry · stage
status
complete | partial
research.person$0.050

4,000 characters, never trimming the current role. Cached 90 days, shared across workspaces.

  • location: "United States"

    Refused: a place, not a person

  • {"status":"failed"}

    Refused: a failed lookup

  • "… is a role based email address"

    Refused: a shared inbox

  • "Nothing Here, Yet"

    Refused: an empty profile page

The prompt

Built in a fixed order.

Dashed blocks appear only when there is something true to put in them.

profile-intro-email.md+ _humanizer.md
FOUNDER
PRODUCT
ICP
PROSPECT
COMPANY
ANGLE
DOSSIER
SOCIAL PROOF
ADMISSION
VOICE
FORMAT
ANGLE
PROSPECT_FIRST_NAME
CURRENT ROLE
DEMO DAY
↓ { "subject", "body" }
The first touch knows your argument but not your product. The reply knows your product but not your argument.
docs/prompt-inputs.md

The angle

Picked before the model writes.

Left to choose, the model reached for the most writable angle.

Before, on a live ledger

25 of 30 accelerator-batch drafts on one angle
26 of 36 luma-events drafts on one angle

Now, a separate call at temperature zero

the prospect
  • angle A
  • angle B
  • angle Cfits
  • angle D
  • Judge fit from the PROSPECT block only.
  • When none clearly fits, choose the most general angle, never a specific one that would be false for this reader.
  • Ignore how well-written an angle is. Writability is not fit.

“A fabricated citation is worse than no evidence at all.”angle-synthesis.md, checked in code

  • dossierkept
  • replies:2kept
  • github:livekept
  • https://… not in the evidencedropped

The linter

Sounds like a template? Held.

The product’s own linter, run on two letters from the demo’s fictional cast.

post-funding

Northwind + background job traces

Hi Priya, I came across Northwind's engineering blog and wanted to reach out — the post on queue backpressure was a great read. Tracepoint helps teams leverage per-job tracing, so incidents get faster, cheaper, and clearer. I'd love to connect if you are open to it. Best, Mira

  • em-dash
  • banned-opener:I-came-across
  • banned-cta:love-to-chat
  • ai-vocab
  • rule-of-three
HELD
competitor-switch

The line in your postmortem about turning off tracing

Hey Grace, Your postmortem says you disabled tracing on the worker fleet because per-host pricing made it untenable, and then the next incident took six hours to reconstruct. Those two sentences are the whole pitch. Tracepoint prices per job, not per host. Worth a look? Mira

CLEAR

Each count is quoted from the comment beside the rule it caused.

What this does not do

Where the rules stop.

  • Nothing checks the finished draft line by line

    Citations are checked on the angle, not on every sentence of the email.

  • Your edits do not train the next email

    Learning from edits exists for LinkedIn replies only.

  • Nothing drafts from their posts yet

    Posts can be captured. No prompt reads them.

  • No reply-rate lift is measured

    Each rule is measured against the failure it fixed, not against replies.

Every rule is a file in the repo. Fork them and argue.