# How we run personalized outbound

An agent connected to our CRM, enrichment, and email that researches each lead, drafts a genuinely personalized sequence, logs it to the CRM, and holds every send behind human approval with a daily cap.

Canonical page: https://openchatly.com/use-cases/outbound-outreach

Personalized outbound doesn't scale by hand, so most teams give up the
personalization: a mail-merge template with a first name swapped in, sent to a
list. It's fast and it's ignored. Real personalization means researching each
account and writing to its actual context, which is exactly the part that doesn't
scale.

We run an agent on Kortix that does the research and the writing per contact, then
holds every send behind a person. It enriches each lead, drafts a first-touch and
follow-up grounded in the account's real context, logs every draft to the CRM, and
sends nothing without approval, capped daily. This is how we run our own outbound.

- **Team:** Kortix
- **Runs on:** A new segment or lead list
- **Connected systems:** CRM · Enrichment · Email
- **Mode:** Every batch approved by a person · daily cap

## The problem

Outbound has a tradeoff most teams resolve the wrong way. Personalized messages
land, but researching and writing each one doesn't scale, so the list wins: a
template, a merge field, a send button. The result is volume without relevance,
and the reply rate shows it.

The usual tools don't fix it. A sequencing tool blasts the same template on a
schedule. An AI writer produces fluent copy with no real account context, which
reads as personalized but isn't. And any tool that can mass-send is one wrong
segment away from putting unreviewed email in front of thousands of people.

## What we built

On Kortix, a periodic sweep triggers the agent in a fresh session (a cloud
sandbox) with scoped access to enrichment, the CRM, and email. The agent works
through the batch of new contacts one by one, researches each account, drafts
a first-touch and a follow-up sequence grounded in what it found, and logs
every draft to the CRM. No message sends on its own: every batch waits for a
person to approve, under a daily cap.

## How it works

### Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it.
The agent writes the agent file, the outreach skill and the weekday trigger, and
opens a change request for you to review. Prefer clicks? Choose **Use this
template** instead.

**Setup prompt**

```
Set up an outbound outreach agent in this workspace.

1. Create the agent agents/outbound-outreach.md. Its job is to draft personalized outbound sequences for new HubSpot contacts. It may use the HubSpot and Clearbit connectors.

2. Create the skill skills/personalized-outreach/SKILL.md with these rules:
   - Work on contacts in the New Prospects list without the kortix_outreach_drafted property. Take at most 25 per run.
   - Enrich each contact first: role, seniority, company size, industry and recent signals such as funding or hiring.
   - Pick the angle and the proof point from memory that fit the account. If a draft reads the same without the enrichment data, rewrite it.
   - Write a first-touch email and its follow-ups with one clear ask, and log the drafts and research notes to the HubSpot contact. Never change deal stage, pipeline or lifecycle stage.
   - Never send. Hold the batch in the email channel for a person to approve and send, then set kortix_outreach_drafted on each contact.

3. Add a cron trigger outreach-sweep to kortix.yaml. It runs the outbound-outreach agent every weekday at 08:00 with the prompt "Load the personalized-outreach skill and run one outreach sweep on the New Prospects list."

4. Tell me which of these connectors are not connected yet.

5. Open a change request with all of it. Do not merge it.
```

### Connect your tools

Open **Connectors** in your workspace and connect your CRM and an enrichment
provider. Connect the email account that holds the drafts under **Settings →
Channels**. Credentials are brokered server-side and never enter the agent's
machine.

- **HubSpot** (Required):
Reads new leads from the list and logs each sequence.
- **Clearbit** (Required):
Enriches each lead with company and role details.
- **Gmail** (Required):
Drafts the outreach sequence for approval.

### Run it once with this prompt

Merge the change request, then start a session with the **outbound-outreach** agent
and send this prompt. Read a few drafts against their accounts before you let the
schedule take over.

**Prompt**

```
Run one outreach sweep on the New Prospects list in HubSpot.

1. Find up to 25 contacts in the list without the kortix_outreach_drafted property.
2. Enrich each contact with Clearbit: role, company size, industry and recent signals.
3. Draft a first-touch email and its follow-ups, each grounded in one specific fact about the account.
4. Log the drafts and research notes to each HubSpot contact.
5. Hold the batch in the email channel for me to review, and set kortix_outreach_drafted on each contact. Do not send anything.
```

### Let the weekday schedule take over

The change request added this trigger to `kortix.yaml`. From now on the agent
runs every weekday at 08:00, each run in a new session on its own cloud computer.
To change the time, edit the cron line, or open **Triggers** in the workspace.

**kortix.yaml**

```yaml
triggers:
  - slug: outreach-sweep
    name: Outbound outreach sweep
    on:
      cron: "0 0 8 * * 1-5"
    run:
      agent: outbound-outreach
      prompt: Load the personalized-outreach skill and run one outreach sweep on the New Prospects list.
```

### Cap each batch and send nothing

Each run drafts at most 25 contacts, however large the list is. The agent
never sends an email. A person reviews the batch, edits what needs it and
sends. HubSpot writes stay limited to notes, drafts and the drafted marker, so
deal and lifecycle stages never change.

### Read the batch

Each run ends with a batch of drafts in the email channel. This is what a run
looks like in the session:

> **Outbound outreach sweep · 08:00**
>
> Prompt: Load the personalized-outreach skill and run one outreach sweep on the New Prospects list.
>
> Drafted sequences for **25** of **61** new contacts in New Prospects, the
> run cap. **7** use the recent-funding angle and **5** the hiring angle. All
> **25** wait in the email channel for review, and the other **36** carry over
> to the next sweep.

> **The pattern**
> A **trigger** on a new list fires a fresh session with scoped
> **connectors** into enrichment, the CRM, and email. The outreach approach is
> encoded as **skills** and **memory**. Every batch is approved by a person and
> the daily cap meters the sends — nothing mass-sends unreviewed.

## Make it do more

Once it works, paste any of these into the same session.

**Stop on a reply**

```
Before you draft a follow-up, check the HubSpot timeline for a reply, and drop the sequence for any contact who already answered.
```

**Learn from edits**

```
Every Friday, compare the emails people sent with your drafts and propose skill changes for the edits they make most often.
```

**Plan by account**

```
When two or more contacts at one company are in the batch, give them different angles and note the link on each HubSpot record.
```

## Guardrails

The agent can draft and send email, so the send is the tightly controlled step:

- **Isolation.** Each sweep runs in its own fresh isolated sandbox, torn down when
  it finishes. The session reaches only enrichment, the CRM, and email, and only
  drafted messages leave it; nothing sends from inside the sandbox. A failure on
  one contact is logged and skipped — it never blocks or corrupts the rest of the
  batch.
- **Scoped secrets.** The enrichment, CRM, and email credentials are encrypted in
  the Secrets Manager and injected into the sandbox at runtime, scoped to the agents you grant them to.
- **Human approval gate.** Nothing sends without a person approving it. Every batch
  is reviewed before send, and a **daily cap** limits volume even after approval,
  so a wrong list can never mass-send unreviewed.
- **Everything is code.** The agent's configuration, skills, and permissions are
  files in the repo, versioned and changed through a reviewed **change request**
  rather than a dashboard setting.

## The outcome

- **Every send:** Approved by a person and metered by a daily cap
- **Per account:** Research and copy grounded in real context, not a merge field
- **3 systems:** Enrichment, CRM, and email in one agent

Outbound is now personalized per account and sent at a safe rate: each contact is
researched, each message is written to its context and logged to the CRM, and
every batch is cleared by a person under a daily cap. The personalization scales
because the research does, and nothing mass-sends without review.
