Samik Hafeez
All work

Personal exploration · private and unfinished

Exploring agent orchestration

A personal experiment in coordinating agents and approval steps to build applications and services. I am exploring how these workflows could run with local language models.

Context
Personal exploration
My role
Designer and developer
Dates
2026 – present
Status
Private · unfinished · not on GitHub

Exploring

  • Agent orchestration
  • Approval workflows
  • LLM-assisted development
  • Local language models

Scope of this pageThis project is unfinished and private. It is not on GitHub or available as a product, and local-model support is still being explored. The diagram shows the workflow I am aiming for, not a tested result.

On this page

Why I'm exploring this

I enjoy finding new ways to solve problems. Agent orchestration connects that with system design: how to break a goal into work, coordinate agents, and decide when an output is ready to move forward.

What I am working on

I have been experimenting with a system that can create or adjust agents and coordinate their work on applications, with approval steps along the way. Some paths work already; the system as a whole is not finished and is not ready to publish.

The experiment builds on OpenClaw, an existing open-source agent platform. My work is the orchestration around the agents; I did not create OpenClaw.

Illustrative workflowIntended workflow of a private, unfinished project; not a record of tested behaviour

The workflow I am working towards

The workflow I am working towardsThe shape of the workflow I am working towards: approval before work starts, and review before a task counts as done. Local-model support is still in progress.A goale.g. “build a small web service”Break it into tasksand suggest an agent for eachApprove the plan?Create or adjust agentsAgents work in OpenClawsessionsOpenClaw is an existingopen-source platformReview the outputchecks and a person's decisionNext task, or doneLocal language modelsintended backend; support still inprogressreviseapprovechanges neededaccepted
The workflow I am working towardsThe shape of the workflow I am working towards: approval before work starts, and review before a task counts as done. Local-model support is still in progress.A goale.g. “build a small webservice”Break it into tasksand suggest an agent foreachApprove the plan?Create or adjustagentsAgents work inOpenClaw sessionsOpenClaw is an existingopen-source platformReview the outputchecks and aperson's decisionNext task, or doneLocal languagemodelsintended backend;support still in progressapproveaccepted
  • External service or data
  • Decision
  • Planned or proposed — not built
  • Conceptual or illustrative
The shape of the workflow I am working towards: approval before work starts, and review before a task counts as done. Local-model support is still in progress.

The workflow I am working towards

100%
The workflow I am working towardsA goale.g. “build a small web service”Break it into tasksand suggest an agent for eachApprove the plan?Create or adjust agentsAgents work in OpenClawsessionsOpenClaw is an existingopen-source platformReview the outputchecks and a person's decisionNext task, or doneLocal language modelsintended backend; support still inprogressreviseapprovechanges neededaccepted
Text version of this diagram

Parts

  • A goal — e.g. “build a small web service”; conceptual
  • Break it into tasks — and suggest an agent for each; conceptual
  • Approve the plan? — conceptual
  • Create or adjust agents — conceptual
  • Agents work in OpenClaw sessions — OpenClaw is an existing open-source platform; conceptual
  • Review the output — checks and a person's decision; conceptual
  • Next task, or done — conceptual
  • Local language models — intended backend; support still in progress; planned, not built

Connections

  • A goal → Break it into tasks (conceptual)
  • Break it into tasks → Approve the plan? (conceptual)
  • Approve the plan? → Break it into tasks: revise (conceptual)
  • Approve the plan? → Create or adjust agents: approve (conceptual)
  • Create or adjust agents → Agents work in OpenClaw sessions (conceptual)
  • Agents work in OpenClaw sessions → Review the output (conceptual)
  • Review the output → Create or adjust agents: changes needed (conceptual)
  • Review the output → Next task, or done: accepted (conceptual)
  • Local language models → Agents work in OpenClaw sessions: intended backend (planned, not built)

The questions guiding the work

  • How should a larger request be divided into useful agent tasks?
  • Where should a person review a plan or an output before work continues?
  • What evidence should support a claim that a task is complete?
  • How far can local models support these workflows, and where do their limits appear?

It also connects to my interest in responsible AI: building such a system raises practical questions about permission, oversight and accountability. I am treating it as a learning project, with no release date and no claim of production readiness.

Contact

I’m looking for graduate and early-career roles in AI/ML and software engineering.