Migrating AI Context to awork

Here's how to transfer instructions, knowledge, skills, and saved information from your LLM to awork in a meaningful way - without bringing along your entire chat history.

Key Benefits and Use Cases

You don't need to transfer your chat conversations from an LLM to awork. In fact, doing so would be counterproductive: chat histories contain not just valuable information but also discarded ideas, corrections, misunderstandings, outdated figures, and small talk. A new agent can't reliably distinguish between these and might end up drawing on information that's long since obsolete.

What's actually worth transferring is much more compact:

• Project instructions and personas

• Knowledge files and other already structured content

• Skills and recurring workflows

• Saved information about your work style

• Recurring rules and preferences

You can take much of this directly. A complete export often isn't necessary at all.

How Does the Transfer to awork Work?

Here's how to map your existing content to the right place in awork:

The Workspace Context is especially important: it's maintained once for the entire workspace and available to all agents. Shared company knowledge belongs there instead of being copied into individual agents. You'll need workspace settings permissions to edit it. Assign one person as the responsible owner.

Migrating Larger, Already Structured Setups

If you already have an extensive setup with multiple Markdown files, skills, reference materials, and workflow logic, you don't need to map and recreate each component individually.

Use the awork MCP Server together with our Migration Skill. You can analyze your existing setup, map each component to the appropriate awork structure, and automatically create much of your new setup.

In the sections below, you'll learn the basic principles of migration so you can follow the general process and verify the results of an MCP-assisted migration.

The Quick Version in 30-60 Minutes - Without Export

This gets you roughly 80% of the results - completely without an export. Only do the full export afterward if something's still missing.

Step 1: Import Existing Skills Directly

If you've written Claude Skills, you can import a single SKILL.md file or a skill package directly. No need to rewrite anything.

Step 2: Take Over Already Structured Content

Open your project or custom assistant and transfer:

1. Project instructions / System Prompt - Insert into the awork agent's system prompt

2. Knowledge files - Attach as files to the agent, or include in the Workspace Context for company-wide content

You've already created and reviewed this content, so it's a good starting point. Before transferring it, still check whether the content and scope still fit your new agent. This ensures you only take over relevant content. This step already covers most of what you want to migrate from your previous setup.

Step 3: Transfer Memory

Memory from your LLM isn't part of the export. But your assistant can read it out. Open a new chat in the same account and use this prompt:

List everything you have stored in memory about me and my work.

Include: my role and background, my company and products, my recurring
responsibilities, my preferences for how you respond, explicit corrections
I have given you, terminology I use, and any people or projects you know about.

Mark each item with where it came from:
- [memory] something you have actually stored about me
- [chat] something you retrieved from an earlier conversation
- [inferred] something you are concluding rather than reading

Rules:
- Only list what you can actually access right now. If memory is unavailable
  or empty, say so plainly instead of reconstructing it from this conversation.
- Never claim to have read memories or past chats you cannot actually access.
- Do not turn a question I once asked into a lasting preference.
- Do not include passwords, API keys or access tokens.

At the end, state briefly what you were able to access and what you could not.

Output as a plain Markdown list, grouped by topic.

Review the results afterward and remove information that's incorrect or outdated. Split the remaining content:

• Personal work preferences - transfer to your own agent

• Company facts - include as Workspace Context

Step 4: Create a Document for Recurring Tasks

You don't need to go through your entire chat history. Focus on the five to ten tasks you regularly use an assistant for.

Open the relevant project or thread and ask the assistant about each recurring task:

I am moving this work into a new AI assistant that has access to our
project management system.

Produce a single handover document for the recurring task "<name the task>",
using exactly these sections:

## Background that always applies
## How I want this done (rules, format, tone, banned wording)
## Decisions already made - each with the date it was decided
## Still open / undecided
## No longer valid - things we tried, changed our mind about, or dropped

Rules:
- Only include what is actually supported by this project or conversation.
- Do not turn your own past suggestions into decisions I accepted.
- Do not turn a question I once asked into a lasting preference.
- Date anything that changes over time: numbers, prices, deadlines, statuses.
- If something is contradictory or you are unsure, put it under "Still open"
  rather than guessing.
- Leave out anything that is simply current project status, task lists,
  client lists or who is working on what. The new system has that live.

Step 5: Review Content Before Upload

Review each document before uploading. Pay special attention to:

• Decisions: Was this actually decided?

• Timeliness: Is this information actually still current?

• Preferences: Does it apply generally or just to one specific task?

• Company data: Should this information leave your organization?

Correct the information directly in the document.

Step 6: Remove What awork Already Knows Live

Many old context snippets are just static copies of data awork already manages live. This includes things like customer lists, project status, deadlines, and responsibilities.

Remove this kind of content from your handover documents. Let the agent use the live data from the system instead. This prevents outdated duplicate sources and creates real added value.

Step 7: Place Each Piece of Content in the Right Location

Use the mapping from the table above. As a quick guide:

• "If X happens, do Y" - Skill

• Information only one agent needs - file attached to agent

• Information for the entire company - Workspace Context

If multiple people are migrating, everyone shouldn't maintain their own version of company facts. Assign one person as responsible for the Workspace Context.

Skills can be shared across the workspace or kept private. Decide this consciously for each skill.

Tip: Give each document a date and an owner.

Step 8: Verify With Real Work

Successfully transferring files and instructions doesn't automatically mean your new agent will work the same way as your previous LLM.

Take five real tasks from the past few months where you got good results from your previous LLM. Run the same tasks with the awork agent and compare the results.

Pay special attention to workflows that depend on:

• Multiple skills or reference files

• Important decision paths

• External tools or data sources

• Fixed output format requirements

If the results are worse, you have a concrete clue about what information is still missing. Fill in that information specifically rather than preemptively transferring more files or materials.

Afterward, expect two to four weeks of small adjustments. Keep a list of changes you need to make repeatedly, and regularly incorporate consistent rules into an agent's System Prompt or the Workspace Context.

Alternative: Use a Complete Export From ChatGPT or Claude

Export From ChatGPT or Claude

1. Open Settings > Privacy > Export data on Claude or Settings > Data Controls > Export Data on ChatGPT.
   Both providers will send you a download link via email. (Note: the link expires.)

2. For team or enterprise plans, contact your administrator, as individual members typically can't start an export.

3. Unpack the download. You'll find one or more large JSON files with all your conversations. These are unsorted. Some exports include a manifest file that only contains download links. Use the actual conversation data.

4. Find the conversations you need and process them individually with the handover template from Step 4. (Don't just summarize the entire export.)

5. Keep the complete export as an archive outside your systems and set a deletion date.

Important Notes

Make sure:

• The Workspace Context remains a shared source

• Personal preferences stay separate

• Skills are consciously shared or kept private

• Documents have an owner and a date

• Results from your new awork agent are verified using real tasks

• Recurring corrections are regularly converted into consistent rules

Handling Company Data

An export can contain customer names, contract details, internal decisions, and personal data about colleagues and third parties.

Transferring this to another system is therefore a data transfer. For a company account, this isn't a decision individual employees should make alone.

FAQ

Can I import my ChatGPT or Claude conversations directly to awork?

No. Conversations can't be imported directly. Besides, taking over raw data from the chats wouldn't make sense anyway, since they can contain discarded, outdated, or misunderstood content.

Can I export only specific conversations?

No. Providers typically export your entire account history as a bundle of JSON files. You can't select individual conversations during export.

Where does company knowledge belong?

Company-wide facts belong in the Workspace Context. Content that only one agent needs goes as files attached to that agent.

How long does migration take?

The quick version takes about 30 to 60 minutes according to the documentation and delivers roughly 80% of the results. Afterward, you can typically expect two to four weeks of small adjustments.

What should I do with the complete export?

Only use it if you need information from old conversations that doesn't exist anywhere else. Process the needed conversations specifically and then keep the raw export as an archive outside your systems.