# Recordings in coding sessions (/docs/context-capture/video-import-coding)



Using recordings in coding sessions [#using-recordings-in-coding-sessions]

Every recording you import becomes searchable context for your AI coworkers. In code-mode, repo-based coding sessions can reference transcripts, keyframes, summaries, and decisions from your walkthroughs.

What your AI coworker sees [#what-your-ai-coworker-sees]

Recordings are broken into layers of progressively deeper context:

| Layer          | What AI sees                             | When it's used                                     |
| -------------- | ---------------------------------------- | -------------------------------------------------- |
| **Summary**    | Chapters, decisions, action items        | "What was discussed in the design review?"         |
| **Transcript** | Timestamped speech with speaker labels   | "What exactly did the designer say about the nav?" |
| **Keyframes**  | Frame images + AI-generated descriptions | "Show me the mockup from the walkthrough"          |
| **Metadata**   | Title, participants, duration            | Matching the right recording to your prompt        |

Your AI coworker reads these artifacts — it doesn't watch the video.

Example: Implement from a design walkthrough [#example-implement-from-a-design-walkthrough]

Ask a repo-based AI coworker to implement a feature based on a recorded walkthrough:

> "Look at the UX walkthrough 'Checkout Flow Redesign' and implement the bottom action bar shown at 2:30"

The AI coworker:

* Reads the summary to find the "Action Bar Design" chapter
* Finds the keyframe at 2:31 showing the mockup
* Extracts requirements from the transcript (2:15-3:45)
* Implements based on what the designer explained

The result: implementation that matches design intent, not just a static screenshot.

Example: Reference a design decision [#example-reference-a-design-decision]

Ask about decisions from past discussions:

> "What did the team decide about the notification system in the last design review?"

The AI coworker finds the relevant recording, reads the summary, and returns:

* **Chapter:** "Notification Redesign" (3:20-5:45)
* **Decision:** Toast notifications replace the modal dialog
* **Action item:** Implement toast component with auto-dismiss (5s default)

No digging through Slack threads or meeting notes.

Example: Debug from a bug report [#example-debug-from-a-bug-report]

Ask a repo-based AI coworker to analyze a recorded bug report:

> "Watch the bug report 'Cart Total Mismatch' and find the root cause"

The AI coworker:

* Reads the transcript describing the issue (total shows $0 after removing last item)
* Examines the keyframe showing the empty cart state
* Traces the issue to `CartTotal.tsx` where `reduce()` has no initial value

Bug reports with video context lead to faster fixes.

Best practices [#best-practices]

**Give recordings descriptive titles**
AI coworkers search by title. "Sprint 12 Checkout Flow Redesign" beats "Recording 47".

**Narrate while recording**
Transcript quality drives extraction quality. Silent recordings produce no searchable context. Talk through what you're doing and why.

**Keep recordings 5-10 minutes**
Focused context is more actionable than hour-long meetings. Split long sessions by topic.

**Reference recordings by title in prompts**
"Look at the checkout flow walkthrough" works better than "check that recording I made".

**Use 720p resolution**
AI processes 720p images faster with zero loss in code/UI comprehension. 4K adds processing time with no benefit.

How it connects [#how-it-connects]

Your recording flows through this pipeline before your AI coworker sees it:

<Mermaid
  chart="graph LR
    A[Import] --> B[Transcribe]
    B --> C[Extract Keyframes]
    C --> D[Summarize]
    D --> E[Commit to Team Context]
    E --> F[AI Coworker Access]"
/>

1. **Import** — uploaded via web UI
2. **Transcribe** — audio extracted, transcribed with speaker identification
3. **Keyframes** — scene changes detected, frames analyzed by vision AI
4. **Summarize** — chapters, decisions, and action items generated
5. **Commit** — artifacts committed to your Team Context
6. **Access** — AI coworkers load these in code-mode via `ox agent prime` at session start

What's next [#whats-next]

* [Video Import](/docs/context-capture/video-import) — import recordings from Loom, Figma, Cap
* [Team Context](/docs/features/team-context) — where recording artifacts live
* [Claude Code Integration](/docs/developers/claude-code) — how context flows into coding sessions
* [SageOx + Figma](/docs/cookbooks/figma) — design walkthrough workflow