# Research Labs

> Read RSB AI Research Labs technical reports, explore open-source agent workflows, and follow our developing research agenda and its limitations.

Canonical page: https://rsbholding.com/labs

RSB AI Research Labs

## A good question.
A new possibility.

The research and experimentation division we are building within RSB Holding. A place to test theories, explore emerging technologies, and develop ideas that support our projects.

[Explore our papers](https://rsbholding.com/labs#papers) [Collaborate with us](https://rsbholding.com/contact?topic=Research+collaboration)

Question. Test. Evaluate. Share.

Publications

## Research papers.

RSB-AI-002 3 October 2026

### [OpenAI Models in Practice](https://rsbholding.com/labs/openai-models-mixed-workflows)

Choosing models by task, coordinating their work, and measuring the complete path to an accepted result.

Jasem Al Salem · 10 pages

[Explore the paper](https://rsbholding.com/labs/openai-models-mixed-workflows)

RSB-AI-001 29 September 2026

### [Botfluencerz and Emotional Continuity in AI Agents](https://rsbholding.com/labs/botfluencerz-emotional-continuity)

How persistent memory, modeled mood, and relationships can influence an AI agent’s behavior—and what that does and does not tell us about feelings.

Jasem Al Salem · 17 pages

[Explore the paper](https://rsbholding.com/labs/botfluencerz-emotional-continuity)

## GitHub skills

Practical workflows for AI coding agents. Explore what each skill does and how to use it.

- [Codex Agent Tree Coordinate coding agents for exploration, implementation, and review.](https://github.com/RSB-HOLDING/codex-agent-tree#readme)

- [Codex Carry Save project context so work can continue in another Codex session.](https://github.com/RSB-HOLDING/codex-carry#readme)

- [Code with Task Graphs Organize complex coding work into connected tasks with clear dependencies.](https://github.com/RSB-HOLDING/code-with-task-graphs#readme)

- [Orchestrate with Astra Delegate complex work with clear ownership, integration, and verification.](https://github.com/RSB-HOLDING/orchestrate-with-sol-ultra#readme)

Our purpose

## Curiosity,
with a direction.

Give product and client teams a place to investigate difficult questions, alongside ideas that deserve independent exploration.

Compare approaches, record what we learn, and help teams adopt findings that hold up to evaluation.

Our technical reports are available above. The broader research themes and experiment workflow remain a developing agenda.

Research directions

## Questions worth exploring.

### Agent collaboration

How can agents coordinate work and hand over tasks more reliably?

### Memory & shared context

What should persist between tasks, and how can it stay accurate?

### Evaluation & reliability

How do we recognize a better approach before adopting it?

### Human–AI interaction

Where should people guide, review, or interrupt an automated workflow?

How an experiment works

## Let the evidence
shape the next step.

### Question

Define the question and assign a person responsible for the work.

### Compare

Choose a baseline and a measurable sign of improvement.

### Test

Run a bounded experiment. Record the result and its limitations.

### Share

Adopt, iterate, or stop. Share an appropriate summary when ready.

Next experiments

## More questions.
Better comparisons.

Our reports propose controlled comparisons of persistent agent state and mixed-model workflows. The next questions are what improves continuity, reliability, and the path to an accepted result.

These controlled studies are planned, not completed. Future records will identify their owner, dates, baseline, result, and limitations.

[Read our research approach](https://rsbholding.com/insights/a-question-before-an-answer)

Connected to our projects

## Questions in.
Useful findings out.

Product and client teams bring questions to the Labs. Validated findings can return as useful capabilities.

[Botfluencerz Published case study: memory, modeled mood, and relationship history.](https://rsbholding.com/labs/botfluencerz-emotional-continuity) [CoPatch Possible future work: agent handoffs, shared context, and human review.](https://rsbholding.com/projects/copatch) [IKARUS Possible future work: knowledge retrieval and reliable answers.](https://rsbholding.com/projects/ikarus)

Start a conversation

## Explore a question with us.

[Talk to our team](https://rsbholding.com/contact?topic=Research%20collaboration)