A good AI context migration from your current LLM doesn't mean taking everything over. It means strategically selecting the information and routines that keep your agent working reliably.

---

The 7 Principles for Successful Context Migration

1. Completeness isn't a quality measure here

An agent with 200 facts, 30 of which are outdated, works worse than an agent with 40 verified facts.

Here's why: False facts get applied with the same confidence as correct ones. The error usually only becomes apparent when the result is already wrong.

Better to have fewer pieces of information that are verified and reliable.

2. A chat history is a record, not a knowledge base

A chat history contains discarded ideas, corrections, misunderstandings, and old figures, often sitting right next to information that still applies.

The person who wrote the chat history usually knows what's still relevant. An agent reading the history later doesn't.

That's why a chat history isn't automatically a suitable source for long-term agent context.

3. A longer prompt doesn't increase available data

No matter what you ask your LLM to extract: the model can only access its stored memory and the conversations available to it.

A detailed extraction prompt can structure this material better. But it doesn't create additional information.

More prompt doesn't mean more source material.

4. Small units help with extraction

Extract information for one recurring task at a time, rather than pulling everything from existing conversations all at once.

This keeps extraction manageable and makes results easier to verify. Plus, errors can be traced back to specific documents more quickly instead of getting lost somewhere in 40 pages of content.

So migrate strategically, not everything at once.

5. Verification is the crucial quality step

The handover document was created by a model summarizing itself. Once this document becomes the authoritative source for your agent, any mistakes become invisible: there's nothing left to compare the result against.

That's why verification matters so much.

Ten minutes of reading per document make the difference between a good migration and one that looks plausible but falls short.

6. Don't transfer anything your target system already knows

Customer lists, project status, due dates, or who's working on what: awork already contains this information live.

If we copy it into agent context as well, we create two sources for the same information. They'll immediately start diverging, and errors often go unnoticed.

Remove such information from the migration and let your agent read the real, current data.

7. It's not the history that's missing, it's the routines

That feeling of "starting from scratch" doesn't come from missing chat histories. It mostly comes from having to explain recurring tasks all over again.

That's why it's often enough to migrate the five to ten tasks someone actually repeats regularly.

This removes that restart feeling without needing to bring over the entire archive.

---

What Can't Be Transferred

Over months, you develop how your agent should work: what tone it uses, how much pushback you want, and when your agent should ask questions instead of just diving in.

This fine-tuning can't be fully transferred. Especially at first, you'll probably still need to make corrections.

This process should be complete after about a month.

---

Testing Whether the Migration Worked

Take five real tasks where you still have good results from your old system.

Run those same tasks in the new system and compare the results.

If the results hold up, the migration was successful, no matter how little you actually transferred.