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 and LinkedIn Sales Navigator, 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.

Triaging a newly assigned inbound lead

When the round-robin assigns a fresh MQL, the SDR verifies the company match in Sales Navigator and grades the lead 'a', 'b' or 'c' on the custom Inbound Score field. A-grade leads get a same-day call attempt, b-grade leads enter a tailored sequence and c-grade leads are disqualified with a structured reason.

Tags

salesforcesales-navigatormqlinboundscoring

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

When the round-robin assigns a fresh MQL to the SDR in Salesforce, they verify the prospect's identity in LinkedIn Sales Navigator before any outreach happens. They confirm the company match, sense-check the seniority of the title and grade the lead 'a', 'b' or 'c' on the custom Inbound Score field. A-grade leads get an immediate phone call attempt, b-grade leads go straight into a tailored Outreach sequence and c-grade leads are disqualified before they reach the broader pipeline.

Reasoning

Prospects often submit free-trial or demo-request forms with personal email addresses, mismatched company names or titles that look senior but are not. Without verifying in Sales Navigator first, the team has wasted the first touch responding to job seekers, students or competitors. Calling within five minutes of an a-grade lead arriving lifts contact rate by roughly four times, every minute beyond that drops the chance of getting hold of them. The grading discipline is what stops the SDR from defaulting to the same first-touch sequence for every inbound regardless of fit.

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 Salesforce Web-to-Lead workflow assigns a fresh MQL to the SDR via the round-robin, fired off a marketing form fill, free-trial signup or demo request.

Outcome

Each MQL has a verified company match, a recorded Inbound Score and a chosen next action. A-grade leads get a same-day call attempt, b-grade leads enter a tailored sequence and c-grade leads are disqualified with a structured reason stored on the lead.

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 new lead from the round-robin notification and read the Lead Source, Lead Source Detail and any Marketing Notes.

The Lead Source Detail field stores the form path the prospect submitted from, e.g. 'pricing-page-trial' or 'whitepaper-2026-state-of-rev'. Trial signups are higher intent than whitepaper downloads, prioritise them on a busy day. Demo-request forms beat both.

Expected: The SDR knows the marketing surface that produced the lead and the rough intent level.

LinkedIn Sales Navigator

Search Sales Navigator for the prospect by name and company and confirm both match what was submitted on the form.

About one in five MQLs cannot be found in Sales Navigator at the company they listed. Common causes are personal email signups by job seekers, agencies submitting on behalf of clients or competitors snooping. If the search returns no match, lower the grade by one tier before any further work.

Expected: The prospect's profile is open and matches the form submission, or the mismatch is noted for the score.

LinkedIn Sales Navigator

Confirm the prospect's title is decision-maker level in the relevant function and that the company matches the team's ICP.

Manager-level titles in product or engineering are not buyers for this product even if the company is in ICP. SDRs have learned that 'Head of', 'VP', 'Director' or 'Founder' is the bar for grade a. Manager and below default to grade b unless the company is on the strategic accounts list maintained by the head of sales.

Expected: The SDR has formed a view on grade based on title and company alone before opening the score field.

Salesforce

Return to the Salesforce lead record and set the Inbound Score field to a, b or c.

Grade 'a' is decision-maker title plus ICP company plus high-intent action like demo request or trial. Grade 'b' is one of those three criteria missing. Grade 'c' is two or more missing. Always pick a grade, leaving the field blank pulls the lead out of the SDR dashboard and it gets forgotten.

Expected: The Inbound Score field is populated and the lead is queued in the right next-action bucket.

Salesforce

Take the next action: log a Call Attempt for grade-a leads, click Add to Outreach for grade-b leads, or use the Disqualify quick action for grade-c leads.

Grade-a leads must be called within five minutes of arriving in the SDR's queue. The team's contact-rate dashboard tracks this and underperformers get coached on it weekly. Grade-c quick-disqualify always asks for a reason picklist value, never leave it blank.

Expected: The lead is in motion on the right channel and the activity is logged on the timeline.

Salesforce

Tag the lead with the current Inbound Score grade and the form source, then save.

Tags drive the conversion-rate dashboard the head of sales reviews on Mondays. The format is '{score}-grade' and 'src-{form-name}', no spaces, no capital letters. Anything else fails the dashboard pivot silently.

Expected: The lead is fully tagged and ready for the next channel-specific pattern.

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

Adding a prospect to a personalised cold email sequence Logging a discovery call outcome Disqualifying a lead with a documented reason

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.

Triaged inbound 'pricing-page-trial' lead from Brava Health, scored grade a

Disqualified inbound MQL with mismatched company and personal Gmail address

Verified 'Director Operations at Lumen Cloud' against Sales Navigator profile

Set Inbound Score = b on Senior Analyst at a Q2 strategic account

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 218 times across 4 connections
Applications	Salesforce, LinkedIn Sales Navigator
First seen	21 Jan 2026, 14:08
Last seen	6 May 2026, 16:42

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