DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to design a custom workflow with fail and rollback paths with Grasp

Edit the FSM canvas to add nodes, guards, and fail or rollback edges.

Who it is forA developer or team lead who wants a repeatable delivery pipeline that retries or rolls back when a step fails.

The problemA fixed linear agent pipeline cannot route failed tests or rejected reviews back to the right step.

The outcomeA published workflow where each node has explicit success, fail, and rollback edges, with when guards controlling transitions.

What you need first

  • A Linux host with Git, Docker, and Docker Compose installed
  • An API key for at least one supported agent backend, or a ~/.codex/auth.json login for codex
  • Optional Git credentials if agents should push branches or open PRs or MRs

Steps

  1. Open the workflow canvas after the setup wizard finishes
  2. Add agent, input, output, assign, branch, or human gate nodes as needed
  3. Connect nodes with success, fail, and rollback edges and add when guards where needed
  4. Declare the required artifacts for each node so the engine knows what must be submitted
  5. Publish the workflow and start a run from the home page to confirm the path

Prompt for your agent

Using the Grasp repo (cocofhu/grasp), create a workflow in <Grasp workspace> on the FSM canvas that adds a rollback edge from the test node to the implement node. Verify the rollback edge is saved and report the node list and edge list.

Caveat. The README does not document the exact steps for declaring required artifacts on a node, so check the Concepts guide before relying on that step.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page