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 and Salesforce, 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.

Building a target prospect list in Sales Navigator

At the start of each week, the SDR runs the team's shared persona search in LinkedIn Sales Navigator and saves around thirty leads into a list named after the current Monday. The list is bulk-pushed to Salesforce, ownership reassigned to the SDR and each lead set to 'New - Not Contacted' ready for research.

Tags

sales-navigatorsalesforceicplist-buildingweekly

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

At the start of each week, the SDR opens LinkedIn Sales Navigator, runs the team's shared Persona search filtered to the agreed ICP and ticks up to thirty leads to save into a new Sales Navigator lead list named after the current Monday's date. They then bulk-push the list into Salesforce as Lead records using Save to CRM, reassign ownership from the integration user to themselves and set Lead Status on each new record to 'New - Not Contacted'.

Reasoning

Building lists from a shared saved search at a fixed weekly cadence keeps every SDR working a fresh pipeline that matches the current ICP, not the leftovers from the previous quarter. Excluding head-counts under fifty and titles containing 'intern' or 'co-op' avoids burning sequence steps on accounts that cannot sign a contract. Naming the list after the Monday's date makes it trivial for the head of sales to spot-check Friday whether the weekly volume target was hit, because the report filters on list name.

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

The Monday morning prospecting block, or any time during the week when an SDR finishes their existing list and needs a fresh batch of accounts to work.

Outcome

Roughly thirty new Lead records sit in the SDR's personal Salesforce queue, each tagged with the source week and Lead Source 'Sales Navigator', ready to be researched and added to an Outreach sequence.

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.

LinkedIn Sales Navigator

Open LinkedIn Sales Navigator and click Saved Searches in the left sidebar.

Use the team's shared Persona search rather than running a fresh one. Personal searches drift from the agreed ICP and produce inconsistent volume between SDRs.

Expected: The list of saved searches loads with the team Persona search visible at the top.

LinkedIn Sales Navigator

Open the team's 'ICP - Director+ Ops at 50-500 SaaS' Persona search and sort results by Most Recent.

If the search shows new results since the last visit, a green badge displays the count next to the search name. Sort by Most Recent to focus on profiles updated in the last week, the strongest 'why now' signal.

Expected: The Persona search results page loads showing the freshest matching prospects across the ICP.

LinkedIn Sales Navigator

Apply a Last Activity filter of 'Posted on LinkedIn in past 30 days' and exclude head-count bands of 1-10 and 11-50.

Active posters reply to outreach at roughly twice the rate of dormant profiles. Companies under fifty staff rarely have the budget split for our price point so are not worth a sequence step. Both filters are saved into the Persona search anyway, but always re-confirm in case anyone has edited the search this week.

Expected: The result count drops by roughly a third and only matching prospects remain.

LinkedIn Sales Navigator

Tick up to thirty leads using the row checkboxes and click Save to list, then choose 'Create new list' and name it 'Outbound - Week of [Monday's date]'.

Thirty is the team's agreed weekly volume per SDR. Going higher inflates the funnel without lifting bookings. The 'Week of [date]' naming is non-negotiable, the head of sales pulls a Friday report filtered by list name and any other format gets dropped from the dashboard.

Expected: A Sales Navigator lead list is created containing the selected leads and shows in the Lists tab.

LinkedIn Sales Navigator

Open the new list and click the Save to CRM bulk action, then choose Salesforce as the target.

Save to CRM respects Salesforce duplicate rules, so any prospect already in the CRM as a Lead or Contact is skipped silently. Watch for the toast confirming the count synced, it should match the number of leads minus any pre-existing duplicates.

Expected: A confirmation toast appears showing how many leads were created in Salesforce.

Salesforce

Open Salesforce Leads, filter by Lead Source = 'Sales Navigator' and Created Date = Today, then bulk-edit Lead Owner to your own name.

Sales Navigator pushes default the owner to the integration user, not the SDR. Without this step the leads do not appear in the SDR's personal queue and the round-robin breaks. Always confirm the count in the bulk-edit dialog matches the toast from the previous step.

Expected: Every new lead from today is owned by the SDR and appears in their personal lead queue.

Salesforce

Bulk-edit the new leads to set Lead Status to 'New - Not Contacted' and add a tag for the source week using the Tags field.

The default status from CRM Sync is blank. Any lead with a blank status is excluded from the SDR dashboard reports, so without this step the work disappears from leadership view.

Expected: All new leads have a status and a week tag and are visible on the SDR dashboard.

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 next

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.

Built outbound list 'Week of 28 April' with 28 director-level leads in Sales Navigator

Synced 27 Sales Navigator leads to Salesforce as new Lead records

Bulk-reassigned 27 newly synced leads from integration user to herself

Created Sales Navigator lead list 'Week of 5 May' with 30 ICP-matched prospects

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 73 times across 5 connections
Applications	LinkedIn Sales Navigator, Salesforce
First seen	19 Jan 2026, 10:22
Last seen	4 May 2026, 09:48

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