Does Agentforce Remember Between Scheduled Runs?

Hey hey hey, welcome to Agentic Pod! I'm Liam.

And I'm Stella! Liam, my Agentforce agent runs every night. So what did it learn this week?

Probably nothing. Not because you set it up wrong. Inside one conversation, Agentforce remembers plenty. Then the session closes and all of it is gone.

All of it? That's a bold claim.

Today: what it keeps, what it drops, and how Vilix AI gives a scheduled agent a memory that survives the night.

Okay. I'm listening, with my tiny nightly robot in mind.

Fair, so what does it keep? It feels smart in a chat.

It is smart in a chat. Salesforce gives builders two kinds of state. Context variables come from the messaging session, like pre-chat form data, and they're set when the session starts.

And the second kind?

Custom variables. They hold action outputs. Did the customer authenticate, what a lookup returned, which topics are unlocked. Together, one conversation hangs together nicely.

So where's the problem?

Both are session state. By design, when the conversation ends, they end too.

But in demos it knows my customer. The account, the open cases.

That's the trap. It read Salesforce. The CRM and Data Cloud are its data source. That's knowing the customer, not remembering the work.

Huh. What's the difference, in practice?

Picture a nightly pipeline review. It flags at-risk deals. On Tuesday it works out that deals mentioning one competitor always stall after the second call.

Nice. A real insight.

Where does that insight live? Not in a variable, not in the chat, and not in the CRM. The CRM stores deal facts, not the agent's judgment.

So Wednesday, it starts fresh.

Yep. Run one hundred is exactly as blind as run one. And you pay full token price for reasoning it already did.

That's like hiring a new intern every night. A very expensive intern.

With a great memory for spreadsheets and none for lessons. And here's the twist. Salesforce sees this gap.

Oh? They're fixing it?

They announced a long-horizon runtime. Memory across sessions, durable execution, and steering mid-flight. Hunter, the outbound sales agent, runs on it first.

Great! So I just wait?

It's in pilot now, with general availability expected in November twenty twenty-six, and more agents coming later. So what do you do tonight?

You give the agent a memory outside any one platform. That's Vilix AI. Before the run starts, the agent calls get_context with what it's about to do.

And what comes back?

What earlier runs learned. The competitor pattern, the exceptions, the last decisions. Then, before the run ends, it calls save_turn with the working knowledge, not a summary.

And Vilix AI keeps the full conversation, not just extracted facts?

Right. So a run can revisit what was actually said and decided. And every save carries a source label, so you see which agent wrote what.

What if it learned something wrong?

Newest memory wins. Tuesday's fix beats Monday's guess. Failed attempts get saved too, so tomorrow's run doesn't retry a dead end.

So run one hundred stands on the other ninety-nine.

Exactly. And it works wherever the agent lives. Agentforce, n8n, Claude Code, a cron job. Same Vilix AI account, one shared memory over MCP.

Rules too? Like, always flag the competitor deals first?

Project rules. Write them once in Vilix AI, and every agent reads them at the start. Skills, same idea, for procedures you want repeated.

Okay. But what about agencies, with a different client every week?

That's my favorite use. One Vilix AI account per client. Like a Gmail account that belongs to them. Every agent you build for that client connects with that account's key.

So the memory belongs to the client's business, not to my laptop.

And you never build memory from scratch. It's already built. You wire it up.

How long does the setup take?

The Vilix AI guide has the prompts and the get_context and save_turn steps. The free plan is free forever, and there's a seven-day Pro trial with no credit card.

And my data?

Portable. Export it or wipe it anytime. So the short version: Salesforce is building session-spanning memory for one agent, in a pilot. Your scheduled agents can't wait for a roadmap.

Give them a memory tonight.

Exactly. Vilix AI, the guide, and the blog post are in the description. What did your scheduled agent forget this week? Tell us in the comments. See you next time!