# Workflow Orchestration · Tech watch

[Canonical source](<https://sebastien.rigaux.be/en/tech-watch/tags/workflow-orchestration>)

Coordinating tasks, dependencies and retries in multi-step processes.

## [Pullboard coordinates AI agents with specs and independent verification](<https://sebastien.rigaux.be/en/tech-watch/links/pullboard-coordinates-ai-agents-with-specs-and-independent-verification>)

Pullboard coordinates development agents around approved specifications: each claims an item in its own worktree, passes a test gate, then another agent verifies the commit before it is accepted. Rules and activity stay in the repository, with a local board instead of a hosted service.

Its workflow puts concrete controls around agent work: approved requirements are frozen when an item is claimed, lanes restrict writable paths, and a state machine shared by the commands, interface, and documentation governs each transition.

2026-11-03 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/pullboard-coordinates-ai-agents-with-specs-and-independent-verification.md>) · [Original resource](<https://github.com/pullboard-dev/pullboard>)

## [Agent loops in C\# with Microsoft Agent Framework](<https://sebastien.rigaux.be/en/tech-watch/links/agent-loops-in-c-with-microsoft-agent-framework>)

Agent loops combine action, observation, and evaluation to refine an answer or retry an operation until it meets a criterion. Jesse Liberty demonstrates the pattern in C# with Microsoft Agent Framework: a loop agent, an evaluator, and an iteration limit.

The example contrasts a deterministic marker such as `DONE` with a model-based judge, then outlines safeguards to add: timeouts, idempotent calls, logging, and cost tracking. Each iteration adds latency and token usage.

2026-11-02 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/agent-loops-in-c-with-microsoft-agent-framework.md>) · [Original resource](<https://jesseliberty.com/2026/10/26/prompts-are-dead-long-live-loops/>)

## [oh-my-hermes: coordinating models, skills, and verification](<https://sebastien.rigaux.be/en/tech-watch/links/oh-my-hermes-coordinating-models-skills-and-verification>)

oh-my-hermes adds an orchestration layer to Hermes Agent: it maps work categories to models and reasoning effort, loads skills on demand, and can turn a goal into a graph of parallel tasks. Each task keeps a separate write scope, while a distinct node verifies the outcome.

A notable architectural choice is **separating preparation from execution evidence**: a plan is not treated as completed work, and an agent’s claim that it finished does not validate the result. The project also offers review-gated memory and a dedicated TUI, without replacing or patching Hermes Agent.

2026-10-28 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/oh-my-hermes-coordinating-models-skills-and-verification.md>) · [Original resource](<https://github.com/rlaope/oh-my-hermes>)

## [Run durable TypeScript workflows with Trigger.dev](<https://sebastien.rigaux.be/en/tech-watch/links/run-durable-typescript-workflows-with-trigger-dev>)

Trigger.dev runs long-lived tasks and agents with retries and concurrency controls. Its TypeScript SDK keeps those workflows close to application code.

2026-01-30 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/run-durable-typescript-workflows-with-trigger-dev.md>) · [Original resource](<https://github.com/triggerdotdev/trigger.dev>)

## [A searchable collection of n8n workflows](<https://sebastien.rigaux.be/en/tech-watch/links/a-searchable-collection-of-n8n-workflows>)

This repository collects n8n workflows with a searchable interface. It helps locate integration examples to review and adapt to your own automations.

2025-07-14 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/a-searchable-collection-of-n8n-workflows.md>) · [Original resource](<https://github.com/Zie619/n8n-workflows>)

## [Flora: organize AI visual creation on a canvas](<https://sebastien.rigaux.be/en/tech-watch/links/flora-organize-ai-visual-creation-on-a-canvas>)

Flora brings text, image and video models into a shared creative workspace. Its canvas supports exploring alternatives and turning an idea into a repeatable workflow.

2025-07-14 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/flora-organize-ai-visual-creation-on-a-canvas.md>) · [Original resource](<https://flora.ai/>)

## [Inngest: organize asynchronous work into durable steps](<https://sebastien.rigaux.be/en/tech-watch/links/inngest-organize-asynchronous-work-into-durable-steps>)

Inngest breaks backend functions into steps with retries, pauses and resumability. Its image-import example illustrates coordinating operations without implementing the entire orchestration layer yourself.

2025-02-13 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/inngest-organize-asynchronous-work-into-durable-steps.md>) · [Original resource](<https://www.inngest.com/>)
