LinkedIn + captured conversations / A WORKFLOW WITH YOUR AGENT

Recover the story behind the name.

Someone mentions a potential customer in a group chat. You remember the organization but not the introduction or what you discussed. The answer may be spread across LinkedIn, messages and your own notes.

ASK FOR THE OUTCOME

Give your agent a clear starting point.

“Prepare a brief about this person using the selected LinkedIn profile, our accessible conversation and my captured notes. Save the evidence in PocketContext. Separate confirmed facts, possible connections and missing information. Suggest a next step without sending a message.”

An example request for an agent configured to use PocketContext. Reading this page does not run it.

CAPTURE ONCE, THEN REUSE

From browsing to stored context.

Read the selected sources

With LinkedIn signed in in the agent’s browser, ask it to read a specific profile and conversation. It can also consult selected material already in PocketContext or another authorized tool, such as your CRM.

Give the information structure

An entity page holds the person’s profile in Markdown, with properties for the captured role, organization and source URL. Related conversation pages link to it when the agent has verified the connection.

ILLUSTRATIVE PAGEentity

Alex · Example Studio

source_app: linkedin
organization: Example Studio
role: Operations
captured_at: 2026-11-03

See the Markdown body

## Professional background
A readable profile based on captured material.

## Conversation context
Relevant discussions, with evidence and links.

Properties for querying. Markdown for the detail. Citations and links connect the evidence.

AN EXAMPLE OF THE RESULT

Before you follow up

A useful brief makes the evidence and the uncertainty visible. The following is fictional reader-style content, not a live account or a completed capture.

Confirmed

Alex works on operations at Example Studio, according to the captured profile.

Read example evidence 1

Fictional LinkedIn profile capture: “Alex — Operations, Example Studio.” This reflects the profile at capture time.

Context

Your last captured conversation was about reducing the time spent preparing weekly reports.

Read example evidence 2

Fictional conversation capture: “Our weekly report takes a lot of manual preparation. I would like to understand your approach.”

Next step

Ask whether reporting is still a priority. No meeting or buying commitment is recorded.

Read example evidence 3

Fictional brief: a suggested action based on the captured conversation. The captured material contains no confirmed meeting or purchase decision.

THE NEXT QUESTION

Query the knowledge.
Skip the repeated scrolling.

Find the person’s page, search for mentions in captured conversations and inspect supporting passages. An authorized agent can check a live CRM separately when you need the current follow-up status.

SQL reads, full-text search and authenticated REST APIs let the agent retrieve stored context directly. The browser reader gives you published pages, properties, citations, originals and revision history.

Keep the browser for changes

Computer use can be slow and token-intensive. Reusing captured information avoids repeating the same navigation for each question. Capture and refreshes still cost time and model usage; savings are workflow-dependent.

Profiles and relationships change. A matching name is not proof of identity, and an old expression of interest is not a current commitment. Check the original source before acting.

AFTER A SUCCESSFUL FIRST CAPTURE

Make the useful part repeatable.

“Each night, check new messages in these selected LinkedIn conversations. Capture accessible changes and update the related person briefs. Keep possible identity matches separate from confirmed links. Report what could not be read. Do not send replies.”

Use a scheduler supplied by your agent, such as Grok Bot routines . Start with a small selection, verify the results and choose a frequency that fits how quickly the information changes.

The agent supplies browser access and scheduling; PocketContext has no built-in connector for this service or recurring scheduler. Sessions can expire and captures can be incomplete. This routine has not been rehearsed end to end.

KEEP THE CONTEXT USEFUL

Readable detail, queryable properties.

These sample properties are conventions your agent can adopt, not dedicated service schemas. Record source URLs and capture dates alongside them. Markdown bodies, properties, citations and history live together in the database. The agent must verify identity matches and create links between related pages.

Capture only the material you choose. External model providers receive the context your agent sends. A citation helps you inspect a claim; it does not prove the conclusion is correct.

Explore the shared data model

Start with a small collection.

Bring one source, ask for a useful brief, and inspect the evidence.

Set up PocketContext Explore more workflows

Fictional example · PocketContext 0.24.0 · Product data model