When does an AI agent use this pattern?

When the trigger described above matches the situation the agent is handling. The agent queries FusedFrames at runtime, this pattern is returned and the agent follows the recorded reasoning and steps to reach the recorded outcome.

How were the steps captured?

By the desktop app on the machine of someone who actually does this work. It records clicks, keystrokes, copy and paste, drag and drop, selected text and screen regions across Salesforce, LinkedIn Sales Navigator and Outreach, then groups them into the meaningful steps shown above.

Where does the reasoning come from?

From the operator. When the desktop app sees a decision the action alone cannot explain, it asks why in the moment. The operator's answer is recorded and becomes the reasoning attached to the pattern, so the AI agent gets the thinking and not just the steps.

What if my team handles this differently?

Capture how your team actually does it. The desktop app records what your operator does on your tools and the web app distills that into a pattern shaped by your team. Each team's library reflects their own approach rather than the example shown here.

What happens when a case looks like this pattern but does not quite fit?

The connections shown on this page link to related patterns that may match the case better. The agent can follow those edges to find a closer fit.

How does my AI agent actually call this pattern?

Through the read-only REST API or the npm CLI. Create an API key in the dashboard, choose whether it accesses all libraries or specific ones and have your agent query at runtime. The response is structured JSON ready for tool use.

Is the data shown on this page from a live customer?

No. Example libraries on this site are illustrative. Patterns in your own account are built from your team's captured actions and stay private to your workspace.

How do I build a pattern like this for my team?

Install the desktop app on the machine of the person who already does this work, ask them to handle a real case end to end, then distill the captured action into a pattern in the web app. The pattern you end up with mirrors how your team actually operates.

Adding a prospect to a personalised cold email sequence

From a Salesforce lead, the SDR enrols the prospect in an Outreach sequence and overwrites the first email's placeholder with a hook drawn straight from the prospect's recent LinkedIn activity. The first touch always references something specific the prospect themselves has said or done in public.

Tags

outreachsalesforcesales-navigatorsequencepersonalisationcold-email

Lets your agent filter to the right pattern

Categories and tags scope the retrieval set, so your agent receives only the patterns relevant to the task instead of scanning the full library.

What and why

The observed behaviour and the reasoning behind it.

Behaviour

From a Salesforce lead record, the SDR clicks the Add to Outreach button, picks the sequence template that matches the prospect's persona and the account size, then opens the first step in the Outreach compose window to overwrite the placeholder with a personal hook taken straight from the prospect's recent LinkedIn activity. They never start the sequence from a blank template, the first email always references something specific the prospect themselves has said or done in public.

Reasoning

Generic cold emails are the fastest way to burn an address. The team has learned that the only first email that gets a reply is one that quotes a specific public action the prospect took, ideally inside the past fortnight. The hook lives in the first paragraph and never the subject line, putting personalisation in the subject reads as a phishing attempt and tanks open rate. Lower-case subject lines outperform title-case at this team's send volume by roughly ten percent on the same body, the look feels less templated. Launching the sequence from inside Salesforce, not from inside Outreach, stamps owner and territory data onto the Outreach prospect record so reporting joins up later.

Gives your agent an operator's reasoning

Behaviour records the action; reasoning records the rationale. Your agent applies both to handle cases that diverge from the captured examples.

Cause and effect

What initiates this pattern and what it produces.

Trigger

An outbound lead has been researched and the buying committee mapped, or an inbound b-grade lead has been triaged and routed to a sequence as the next action.

Outcome

The prospect is enrolled in an Outreach sequence whose first email references a specific public action of theirs. The matching Salesforce lead is automatically updated to status 'Working - In Sequence' by the Outreach Salesforce sync within sixty seconds.

Tells your agent when to act and what to verify

Your agent stays within the scope set by the trigger and outcome, so it doesn't extend beyond the work or finish before the outcome is met.

Standard operating procedure

Step-by-step instructions to reproduce this pattern.

Salesforce

Open the prospect's Lead record in Salesforce and click Add to Outreach in the Outreach panel on the right sidebar.

Always launch the sequence from Salesforce, not from inside Outreach. Going through Salesforce stamps the lead's owner, source and territory onto the Outreach prospect record so the joined reporting works later. Launching from Outreach skips this and the lead shows as territory 'unassigned' in pipeline reports.

Expected: The Outreach Add to Sequence dialog opens with the prospect's email pre-filled.

Outreach

Pick the sequence template that matches the prospect's persona and the account head-count band.

Personas are coded by job function in the template name. The 'rev-ops-mid-market' template performs nine percent better than 'rev-ops-smb' for companies above 500 head-count even when the prospect title is the same, because the second-step talk-track on 'mid-market' references budget cycles which lands harder on enterprise buyers.

Expected: The chosen sequence template is loaded with all steps visible in the dialog.

Outreach

Click into the first step of the sequence and open the Compose Email view to read the placeholder hook.

Never use the bulk-add button until the first email is overwritten. Bulk-add fires the templated first email at the next send window, which means a generic opener for high-effort prospects. The team has had AEs flag this as a deliverability risk on the strategic accounts list.

Expected: The first email is open in the compose view with the {{personal_hook}} placeholder visible.

LinkedIn Sales Navigator

Open the prospect's LinkedIn Sales Navigator profile in a second tab and copy a recent post, comment or shared article from the past fortnight.

If nothing exists from the past fortnight, fall back to a podcast appearance or a published interview. Never default to 'I see your company recently raised', the entire team uses that and reply rate has died on it. A direct quote from a post is the strongest hook tested, paraphrasing reads as templated.

Expected: A specific public action of the prospect's is on the clipboard ready to paste.

Outreach

Replace the {{personal_hook}} placeholder in the first email with the captured material in two short sentences.

Two sentences max. Anything longer reads as a research dump and prospects skim past it. The format is one sentence quoting or summarising what they said, then one sentence connecting it to the reason for reaching out. Lower-case the subject line and never include the company name in it, the team has tested this and the lower-case form lifts open rate by about ten percent.

Expected: The first email body now opens with a personalised hook and the rest of the template follows unchanged.

Outreach

Confirm the sending mailbox, the prospect's local time-zone and the start date, then click Add to Sequence.

The team's outbound deliverability rules require Tuesday to Thursday starts, never Mondays or Fridays. Time-zone defaults to the SDR's, switch it to the prospect's local time-zone using the dropdown otherwise the open rate drops sharply on west-coast prospects from a UK SDR. Always confirm the sending mailbox is the persona-aligned one, not the SDR's personal mailbox.

Expected: The prospect is enrolled and the sequence shows in the SDR's Outreach dashboard with the next send time visible.

Salesforce

Return to the Salesforce lead record and confirm the Lead Status has flipped to 'Working - In Sequence' via the Outreach sync.

If the status has not flipped within sixty seconds, the Outreach Salesforce sync is failing. Raise it in the rev-ops Slack channel before adding any more leads. Working from a stale Salesforce status is the fastest way to double-touch a prospect, an AE has called this out twice already this quarter.

Expected: The Lead Status reads 'Working - In Sequence' and the next-touch date appears in the Outreach widget on the lead.

Hands your agent your team's exact steps

Your agent executes the documented procedure in order, against the applications named at each step, producing consistent output across human and agent runs.

Book a demo

Related patterns

How this pattern connects to other patterns in the library.

Often previous

Building a target prospect list in Sales Navigator Researching a single account before outreach Triaging a newly assigned inbound lead

Often next

Sending a soft-touch LinkedIn connection request Moving an unresponsive prospect to a break-up sequence Booking a demo from a positive email reply

Lets your agent confirm the match and its scope

Alternative patterns let your agent compare candidates and select the closest match. Previous and next patterns define position in the workflow, so the agent operates within the scope of this one.

Supporting actions

Actions that provide evidence for this pattern.

Added Director of RevOps at Marlowe Capital to 'rev-ops-mid-market' sequence

Personalised first step referencing prospect's recent LinkedIn post on MEDDPICC

Enrolled 4 new leads from the 'Week of 5 May' list into outbound sequence

Replaced template hook with quote from prospect's podcast appearance on RevOps Co-op

Switched start time-zone from UK to Pacific before enrolling prospect at Quayside Logistics

Shows your agent the evidence behind the pattern

Each pattern is derived from captured action sequences. Your agent can reference the source actions to verify any field, so nothing it acts on is authored by hand or hallucinated.

Metadata

Timestamps and identifiers.

Evidence	Observed 1963 times across 5 connections
Applications	Salesforce, LinkedIn Sales Navigator, Outreach
First seen	19 Jan 2026, 12:35
Last seen	7 May 2026, 15:18

Helps your agent rank patterns by confidence

Action count and last-seen timestamp weight each pattern by frequency and recency, so your agent selects the highest-scoring match rather than the first returned.

Questions

Frequently asked questions

Book a demo View all examples

Speak to the founder

Get a demo. Watch a live capture, then an AI agent query the result.

Ask anything. Pricing, security or integrating with your stack.

No purchase obligation

Book a call

Start capturing

Record in minutes. Install once and work as normal.

Plug AI agents in. One API call from any AI agent stack.

Refund on unused credits if you cancel