AI context is a section on a story or bug where AI tools can store and reuse context as work progresses. It captures research, decisions, and changes so future work—by a person or another agent—can pick up with the right context.

Created and updated through the Atono MCP server, it can also be edited manually in the Atono web application and becomes visible after the first context is added.

As teams rely more on AI, work moves faster—but context often gets lost across tools, sessions, and conversations. By keeping decisions and changes visible, teams can stay aligned and move quickly without losing clarity or repeating work.

📘
To use AI context from your IDE, your AI coding assistant must be connected to the Atono MCP server.

Access AI context

In the Atono web application, AI context (if available) is accessible from the details panel of a backlog item.

Open a backlog item (story or bug).
In the details panel, select AI context.
In the AI context dialog, select a tab:
- Design decisions
- Technical investigation
- Technical changes

What’s included

Design decisions

Design decisions capture product and scope decisions made during AI-assisted story authoring. This helps coding agents understand why a story is structured the way it is and supports ongoing refinement as the story evolves.

Use this tab to record:

Tradeoffs considered
Acceptance criteria framing decisions
Scope boundaries and constraints
Items explicitly deferred

This content should reflect current product intent. Update it as decisions evolve rather than treating it as a running log.

When your assistant updates acceptance criteria, it may also update Design decisions if the changes reflect a meaningful shift in scope.

Technical investigation

Technical investigation captures discoveries, research findings, and constraints gathered during AI-assisted implementation. It helps future agents avoid redundant work and build on what is already known.

Use it for:

Findings and constraints
Relevant files, endpoints, or dependencies
Open questions and decisions
Recommended next steps

Technical changes

Technical changes is a current record of implementation changes made by AI tools for the backlog item. It reflects the current state—changes that have been reverted should be removed.

Use it for:

What was added, changed, or removed
Test updates
Behavior changes
Outcomes (what works now)

Using AI context from your IDE

AI context is most useful when your IDE assistant treats it as shared memory for a backlog item. Instead of relying on chat history—which can become fragmented or lost—AI context stores important information directly on the story or bug.

When your assistant retrieves a story or bug using the Atono MCP server, it automatically reads all available AI context for that item before acting. You don't need to ask separately. For story creation specifically, your assistant will also capture design decisions to the Design decisions tab immediately after creating the story—but mentioning it in your request is the most reliable way to ensure it happens.

To get the most out of AI context, instruct your assistant to keep it updated as work progresses. That way, each session picks up where the last one left off.

📘
When prompting your IDE assistant, include the backlog Item ID (for example STORY-98 or BUG-123) so it knows which item to update.

Keep AI context updated

At the start of the session, instruct your assistant to maintain AI context continuously. This is what turns AI context into a reliable handoff for the next person—or the next AI session. For example:

“While you work on STORY-98, keep the AI context up to date. Use DESIGN for product and scope decisions, INVESTIGATION for research and findings, and SUMMARY for implementation changes. Update AI context after each meaningful step.”

Capture design decisions

Use this when making or revising product or scope decisions. For example:

"Update AI context for STORY-98. In DESIGN, capture the tradeoffs we discussed and why we chose this approach."

Capture investigation notes

Use this when discovering constraints, dependencies, or insights. For example:

“Update AI context for STORY-98. Add the key findings and constraints to INVESTIGATION.”

Capture implementation changes

Use this after meaningful implementation steps (new behavior, refactors, tests, schema changes). For example:

“Update AI context for STORY-98. In SUMMARY, record the changes you just made, including behavior and tests”

Wrap up with a clean handoff

Before finishing work, ensure AI context reflects the current state so the next developer or agent can pick up the work without guessing. For example:

“Before we finish work on STORY-98, update AI context. Clean up DESIGN to reflect final scope, ensure INVESTIGATION lists remaining questions, and confirm SUMMARY reflects the current implementation.”

Using AI context in Atono

You can view and edit AI context directly in the Atono web application.

View AI context

Open a backlog item (story or bug).
In the right-side panel, click AI context.
Select Design decisions, Technical investigation or Technical changes.

Edit AI context

Open the tab you want to update.
Modify the content.
Click Save.

AI context becomes visible once any of the fields contains content.

Version history

Atono tracks changes to AI context so you can review what changed over time and restore earlier versions if needed. In the version history, the diamond (✦) icon indicates a version was created by an MCP tool.

AI context has its own version history, separate from a backlog item’s content version history. Changes to one do not affect the other.

Each tab—Design decisions, Technical investigation, and Technical changes—has its own version history. Changes to one do not affect the others.

Restore a version

Open a backlog item (story or bug).
In the details panel, select AI context.
Select a tab.
In the version list on the right, hover over the version you want to restore.
Select the ellipsis (...) icon and choose Restore this version.
In the Restore version dialog, confirm by clicking Restore version, or click X to cancel.

Restoring creates a new version identical to the one you selected, and makes it the current version for that tab.

Delete a version

Open a backlog item (story or bug).
In the details panel, select AI context.
Select a tab.
In the version list on the right, hover over the version you want to delete.
Select the ellipsis (...) icon and choose Delete this version.
In the Delete version dialog, confirm by clicking Delete version, or click X to cancel.

Deleting a version only affects the version history for the selected tab.