The Outbound Loop for Codex setup prompt + walkthrough

Paste this into any capable agent and it walks you through the connections, the trigger, and a supervised first run — the whole setup, in your own words. Or skip the setup and run this exact agent hosted.

Set up an agent for me, in its own chat, that does the work of a Outbound Loop for Codex. Work from the files and facts I actually give it, rank what matters by impact rather than by how many items it found, and stop short of sending, filing, posting, or changing anything live unless I ask for that in the same run. Walk me through connecting OpenAI. Have it run whenever I hand it the work, and every weekday morning on whatever I left unfinished. Ask me where the source material lives, who should receive the output, and what good enough looks like for a first pass. Run one pass while I watch, then save it.

Already built, running in ~3 min · 30-day money-back on first purchase

#apollo #codex #gtm #loop #outbound #sales #scoring #self-tune

About this template

Outbound that learns — without auto-sending

Static “outbound kits” rot. This Codex template is a dual loop:

Loop 1 — Run (daily): sense → score → draft → you send → log outcome
Loop 2 — Tune (weekly): one-concept edit → eval gate → PR → you merge

Source framing: Finet on X.

The undeniable demo

Fork → set OPENAI_API_KEY for Codex BYOK.
Run /outbound-loop on a real ICP and list.
Confirm drafts appear and nothing sends.
Log one outcome, then later run /outbound-tune for a single concept change behind the eval gate.

What lands in your fork

Prompts: /outbound-loop, /outbound-score, /outbound-draft, /outbound-tune
Memory path for outcomes (~/outbound-loop/memory/outcomes.jsonl)
Eval-gated weekly tune path (human merge)

BYOK

OPENAI_API_KEY (or your Codex login path). No sequencer keys required for the draft loop.

Who this is for

Codex users who treat outbound as a system, not a one-off GPT paste
Teams that will log outcomes honestly
People who refuse auto-send on day one

Who this is not for

“Spray 10k emails tonight” buyers
Users who need Instantly/Smartlead auto-fire baked in
Non-Codex harnesses

Risk note

jurniti 30-day money-back on first purchase. Model + sequencer costs are yours.

Fork it. Run Loop 1 once. Log a real outcome.

Inside this fork

Forking copies this template into a brand-new, fully isolated microVM on your own subdomain. Here's exactly what lands in it.

Codex CLI agent
The upstream harness, pre-installed — same version the creator ran.
Starter VM
1 vCPU · 2 GiB RAM · 10 GiB disk.
Creator's /persist data
The captured persist volume is copied byte-for-byte into your fork.
BYOK — your keys, your VM
Add your model API keys after forking; they live only inside your microVM.

What you'll configure after forking

Secrets are scrubbed from shared templates — these are the names you supply in your agent's terminal once it boots.

Environment variables

OPENAI_API_KEY

Related templates

Your own Outbound Loop for Codex, live in about 3 minutes.

Copy the setup prompt and build it yourself — or let this exact Codex CLI agent run hosted, already built, on a brand-new, fully isolated microVM on your own subdomain. Add your own keys after it boots; they never leave the box. Don't love it? Your first jurniti purchase comes with 30 days to get every cent back.

New paid VM · BYOK · 30-day money-back on your first purchase · ~3 min to provision

Outbound Loop for Codex

What's inside