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 LinkedIn Sales Navigator, Salesforce 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.

Sending a soft-touch LinkedIn connection request

48 hours after the first cold email step lands as Delivered, the SDR sends a no-note LinkedIn connection request mid-week between 09:00 and 11:00 local to the prospect. The touch is logged as a 'LinkedIn Touch' Salesforce activity so any AE who picks the lead up later can see the multi-channel cadence.

Tags

sales-navigatorsalesforcelinkedinconnection-requestmulti-channel

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

Forty-eight hours after the first cold email step lands as Delivered, the SDR opens the prospect's LinkedIn Sales Navigator profile and sends a connection request without a note. They time the request mid-week between nine and eleven in the morning local to the prospect, never paired with a pitch, and they then log the request as a 'LinkedIn Touch' activity on the matching Salesforce lead so the multi-channel cadence is visible to any AE who picks the lead up later.

Reasoning

The team has tested noted versus no-note connection requests and the no-note option accepts at almost double the rate, prospects assume any note is a sales pitch and decline anything that looks templated. The forty-eight hour gap after the cold email is deliberate: sending both inside an hour reads as a coordinated bombardment, prospects who would have read the email simply mute the sender. The morning local-time band lifts accept rate by about a third over evening sends. Logging the request in Salesforce stops AEs from accidentally double-touching the prospect when they later inherit the lead.

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

Forty-eight hours have passed since the first email step in the prospect's Outreach sequence sent successfully and the prospect has not yet replied or unsubscribed.

Outcome

The prospect has a no-note connection request from the SDR and the touch is logged as a Salesforce activity of type 'LinkedIn Touch' on the lead. If accepted, the prospect surfaces in the SDR's LinkedIn feed and warms the channel for the next touch.

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.

Outreach

Open the prospect's Outreach record and confirm the first email step shows status 'Delivered' and at least forty-eight hours have passed since send.

If the first email bounced, hold the connection request and raise the lead in the rev-ops channel for email cleansing. Connecting on LinkedIn after a bounce wastes a touch and the prospect now sees a stranger trying to add them with no warming via email first.

Expected: The first email is delivered and the cooldown window has elapsed.

LinkedIn Sales Navigator

Open the prospect's Sales Navigator profile via the LinkedIn link on the Outreach record.

Use the link from Outreach not a fresh search. The Outreach link points at the verified profile, a fresh search occasionally surfaces a different person with the same name and the connection request lands on the wrong inbox.

Expected: The verified Sales Navigator profile is open in the browser.

LinkedIn Sales Navigator

Click Connect and choose Send without a note when the dialog appears.

The team's tested copy on noted requests has not beaten no-note. Even 'thanks for the recent post' notes are flagged as templated by anyone in a sales-adjacent function. Send without a note unless the SDR has a personal mutual connection of any kind, in which case mention the mutual by name in a one-line note.

Expected: A connection request is sent and the button changes to Pending.

LinkedIn Sales Navigator

Check the prospect's local time before sending and hold the request if it is before nine or after eleven in the morning their time.

The team batches connection requests into the prospect's nine-to-eleven local window where accept rate is highest. Sending at eight at night UK time to a Pacific-time prospect lands on their morning but reads as automation, accept rate halves. Hold and send the next morning instead.

Expected: The request is sent within the prospect's nine-to-eleven local-time band, or queued mentally for the next morning.

Salesforce

Open the matching Salesforce lead, log a new Activity of type 'LinkedIn Touch' with subject 'Connection request sent' and save.

Use the picklist Activity Type 'LinkedIn Touch', not the free-text Comment field, the Activity Type drives the multi-channel touch report leadership review on Mondays. Always save the activity with the same date as the actual send, not the date of the lead update.

Expected: A LinkedIn Touch activity is recorded on the Salesforce lead and visible to any AE who later inherits it.

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

Researching a single account before outreach Adding a prospect to a personalised cold email sequence

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.

Sent no-note connection request to VP Operations at Pyramid Foods

Logged 'LinkedIn Touch' activity on Salesforce lead after Sales Navigator request

Held off connection request after first cold email bounced for prospect at Tetrapod Inc

Queued connection request for next morning after spotting Pacific prospect at 19:00 local

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 856 times across 4 connections
Applications	LinkedIn Sales Navigator, Salesforce, Outreach
First seen	22 Jan 2026, 09:50
Last seen	6 May 2026, 10:36

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