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 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.

Logging a discovery call outcome

Within ten minutes of hanging up from a discovery call, the SDR logs a structured Salesforce activity against the team's BANT-plus-Pain template. They quote the prospect's exact words for any phrase the AE will reuse and schedule the next concrete touch as a dated Salesforce task.

Tags

salesforceoutreachdisco-callbantqualificationactivity-log

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

Within ten minutes of hanging up from a discovery call, the SDR opens the Salesforce lead, logs a new Activity of type 'Discovery Call' and pastes their notes structured against the team's BANT-plus-Pain template. They quote the prospect's exact words wherever a phrase would land directly in the AE's first email, set the Lead Status to reflect qualification, then click Save and Add Task to schedule the next step with a hard date before the activity closes.

Reasoning

A disco call without a written outcome is worth nothing twenty-four hours later. The prospect's exact phrasing is freshest in the SDR's head right after the call, and that phrasing is what the AE will quote back at them on the demo. The ten-minute discipline matters because the team makes forty calls a day and memory blurs by the third one. Always scheduling a follow-up task before saving is the team's hard rule, leads slip through the cracks otherwise: the audit shows leads with no follow-up task convert at a quarter the rate of leads with a date in the queue.

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

A discovery call has just ended, whether inbound (the SDR phoned a fresh a-grade MQL) or outbound (the prospect replied to a sequence and agreed to a fifteen-minute fit call).

Outcome

The Salesforce lead has a structured Discovery Call activity logged, the Lead Status reflects whether the prospect is qualified or not and a follow-up Salesforce task with a date sits on the SDR's queue for the next concrete 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.

Salesforce

Open the prospect's Salesforce lead within ten minutes of the call ending.

The team's hard rule is logging within ten minutes. Memory of the prospect's tone, exact phrasing and concerns degrades quickly. Calls logged the next day average a third the field completion of calls logged inside the ten-minute window, the disco notes are noticeably thinner.

Expected: The lead record is open and the Activity tab is visible.

Salesforce

Click Log a Call and set Activity Type to 'Discovery Call' and Outcome to either 'Connected - Qualified', 'Connected - Not Qualified' or 'Voicemail'.

Outcome 'Voicemail' triggers an automated next-day reattempt task, never log a no-answer as 'Connected', the reporting goes wrong and the prospect drops out of the queue. Always pick from the picklist, free text in Outcome breaks the dashboard pivot silently.

Expected: The Activity record is open with Type and Outcome populated.

Salesforce

In the Notes field, paste the team's BANT-plus-Pain heading template and fill it in with the prospect's own words wherever possible.

The five headings are 'Budget', 'Authority', 'Need', 'Timeline' and 'Pain Quote'. Always quote the Pain in the prospect's exact words inside double quotes, the AE will quote it back to the prospect on the demo and a paraphrase always loses the impact. If the prospect did not mention something, write 'not surfaced' rather than leaving it blank.

Expected: The Notes field contains a structured account of the call ready to be read by the AE later.

Salesforce

Update the Lead Status to 'Working - Qualified' if the prospect cleared three of the four BANT signals, or 'Working - Nurture' if they cleared one or two.

Disqualified leads do not flip to 'Closed' on this step, that happens in the disqualify pattern. Nurture leads move to a slower sequence cadence, the rev-ops automation reads the status field on save and adjusts the Outreach sequence accordingly.

Expected: The Lead Status reflects the call outcome and the lead is in the right next-touch bucket.

Salesforce

Click Save and Add Task immediately, never just Save.

Save and Add Task forces a new task with a due date before the activity closes. Plain Save closes the activity with no follow-up scheduled, and that is exactly when leads slip. The team's audit shows leads with no follow-up task convert at a quarter the rate of leads with a date in the queue, this is the single most enforced step in the playbook.

Expected: The Add Task dialog opens linked to this activity.

Salesforce

Set a Subject describing the next step, a Due Date inside the prospect's stated timeline, and Save.

Subject formats are 'Send security one-pager', 'Schedule demo with [AE name]' or 'Follow up on Q3 budget question'. Vague subjects like 'Follow up' do not survive the SDR's busy queue, they get triaged out. The Due Date never sits more than seven days out unless the prospect explicitly asked for a longer delay.

Expected: A Salesforce task with a clear next step and a hard date is on the SDR's queue.

Outreach

Open Outreach, find the prospect and either pause the sequence (qualified, going to demo) or move them to the Nurture sequence (qualified - long timeline).

Never leave a qualified prospect inside an active cold sequence after a connected call, the next email reads as if the SDR did not pay attention to what was just said. Always synchronise the Outreach state to the Salesforce status before walking away from the keyboard.

Expected: The Outreach state matches the Salesforce status and no auto-emails will fire that conflict with the call outcome.

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

Triaging a newly assigned inbound lead

Often next

Disqualifying a lead with a documented reason Booking a demo from a positive email reply Converting a qualified lead and handing off to the AE

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.

Logged disco call with Director Ops at Brava Health, Outcome = Connected - Qualified

Pasted BANT-plus-Pain template into call notes for Lumen Cloud follow-up

Scheduled 5-day follow-up task after voicemail to Heliograph Labs

Updated Lead Status to 'Working - Nurture' for prospect with 2026 H2 timeline

Quoted prospect's pain verbatim: 'we manually reconcile every Monday and it takes four hours'

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 487 times across 5 connections
Applications	Salesforce, Outreach
First seen	26 Jan 2026, 11:08
Last seen	7 May 2026, 17:12

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