--- updatedAt: 2026-09-30T10:53:38.000Z agentTools: projectIndex: https://docs.hud.io/llms.txt --- # Agentic Workflows Give your coding agents real production context — automate PR risk checks, health reports, dead-code cleanup, and rollback decisions with Hud runtime data. An **agentic workflow** is a task you describe once — usually in plain Markdown — and a coding agent (Claude, Codex, Cursor) executes automatically whenever a defined event fires: a pull request opens, a deploy lands, a schedule ticks. Instead of a person prompting an AI by hand in their editor, the agent runs as part of your pipeline. It's the same shift that CI/CD brought to building and deploying — versioned, governed, automatic — now applied to the work an AI agent does. GitHub calls this pattern *Continuous AI*; the principle holds on any runner. **A good agentic workflow has three traits:** * **A clear trigger** that maps to real work — a PR, a webhook, a cron, an issue label. * **A well-bounded task** with specific inputs and a clear question to answer — not "improve the code," but "score this PR's production risk." * **A structured output** that keeps a human in the loop — a draft PR, a scored comment, a report — rather than silent changes. The workflows in this section connect the agent to the **Hud MCP server**, so it reasons over your real runtime data — invocation counts, latency percentiles, error rates, and call graphs — instead of inferring impact from source and diffs alone. This section is a library of ready-to-run agentic workflows, plus the instructions to set them up in your own repos. > 📘 New to the Hud MCP server? > > Agentic workflows are built on top of the [Hud MCP Server](https://docs.hud.io/docs/hud-mcp-server). If you've only used Hud inside your IDE so far, start there to understand how an agent queries your runtime data — then come back here to automate it.
*** ## How it works Every workflow is the combination of two things: * **A use case** — *what* the agent does (e.g. score a PR's blast radius, clean up dead code). * **A runner** — *where* it executes (GitHub Actions, Cursor, a Claude routine, …). Any use case can run on any runner. You pick one of each, copy a few files into your repo, set a secret, and ship. ``` USE CASE RUNNER RESULT ┌──────────────┐ ┌──────────────────┐ ┌──────────────────┐ │ Blast radius │ × │ GitHub Actions │ → │ PR comment with │ │ Weekly report│ │ gh-aw │ │ a 0–100 score, │ │ Dead code │ │ Cursor │ │ a Slack report, │ │ Rollback │ │ Claude routine │ │ a draft PR, … │ └──────────────┘ └──────────────────┘ └──────────────────┘ ``` Every workflow authenticates to Hud with a single `HUD_MCP_KEY` secret, passed to `npx -y hud-mcp@v2`.
*** ## How this differs from Hud in your IDE | | Hud in your IDE / MCP | Agentic workflows | | --------------------- | -------------------------------- | --------------------------------------------------- | | **Who triggers it** | You, interactively, while coding | An event (PR, cron, deploy) or a one-line command | | **Where it runs** | Your editor | CI, the cloud, or a scheduled runner | | **Human in the loop** | Always | Optional — can run fully hands-off | | **Typical output** | An answer in chat | A PR comment, Slack post, draft PR, or GitHub issue | Same runtime data, same MCP. The difference is automation: workflows let the agent act without you prompting it each time.
*** ## Prerequisites Before setting up any workflow, make sure you have: 1. **Instrumented services reporting to Hud.** Workflows query your *production runtime data*, so your services must already have the Hud SDK installed and be sending data. See [Node.js Installation](https://docs.hud.io/docs/nodejs-installation-guide), [Python Installation](https://docs.hud.io/docs/hud-python-installation) or [Java Installation](https://docs.hud.io/docs/java-installation). 2. **A Hud MCP key.** Get one at [app.hud.io → Settings → API keys](https://www.app.hud.io/settings/api-keys?environment=production). You'll set it as the `HUD_MCP_KEY` secret in your runner. 3. **A model provider key** for the agent — typically an `ANTHROPIC_API_KEY` from [console.anthropic.com](https://console.anthropic.com), or AWS Bedrock credentials. See [model authentication in the FAQ](https://docs.hud.io/docs/agentic-workflows-faq).
*** ## The recipe catalog Four ready-made use cases ship today. Each is runner-agnostic — it uses environment variables and generic instructions, so you can pair it with any runner. See the full [Recipe Catalog](https://docs.hud.io/docs/agentic-workflows-recipes) for env vars, outputs, and examples. | Recipe | What it does | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Blast radius** | Scores the production blast radius of a PR (0–100) by mapping changed code to affected functions and endpoints, then posts a ranked report. | | **Weekly report** | A multi-phase deep-insights report on production health — proposes fixes, attributes contributors, optionally opens a self-heal PR, and posts to Slack. | | **Dead-code cleanup** | Finds functions with zero production invocations over a lookback window and opens a PR removing them (with an optional Jira ticket). | | **Rollback check** | Compares current vs. previous release health per version and returns a structured verdict: `ROLLBACK` / `INVESTIGATE` / `WARN` / `CLEAN`. |
### Use case × runner matrix Each cell pairs a recipe with a runner. **See example** cells link to a fully worked, install-ready combo; the rest you assemble yourself by pairing the recipe prompt with the runner template (see [Choosing a Runner](https://docs.hud.io/docs/agentic-workflows-runners)). | | GitHub Actions | gh-aw | Cursor | Claude routine | | --------------------- | :----------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------: | | **Blast radius** | ✅ [see example](https://github.com/code-hud/hud-agentic-workflows-recipes/tree/main/full-examples/blast-radius-github-actions) | mix & match | mix & match | mix & match | | **Weekly report** | mix & match | ✅ [see example](https://github.com/code-hud/hud-agentic-workflows-recipes/tree/main/full-examples/weekly-report-gh-aw) | mix & match | mix & match | | **Dead-code cleanup** | mix & match | mix & match | ✅ [see example](https://github.com/code-hud/hud-agentic-workflows-recipes/tree/main/full-examples/dead-code-cleanup-cursor) | mix & match | | **Rollback check** | mix & match | mix & match | mix & match | ✅ [see example](https://github.com/code-hud/hud-agentic-workflows-recipes/tree/main/full-examples/rollback-check-claude-routine) |
*** ## Where everything lives All recipes, runner templates, and fully worked examples are open source in the [**hud-agentic-workflows-recipes**](https://github.com/code-hud/hud-agentic-workflows-recipes/tree/main) repository — the source of truth this documentation is based on. The repo is MIT-licensed and community-extensible.
## Next steps * **[Quick Start](https://docs.hud.io/docs/agentic-workflows-quick-start)** — set up your first workflow (PR blast-radius on GitHub Actions) in about 10 minutes. * **[Choosing a Runner](https://docs.hud.io/docs/agentic-workflows-runners)** — compare runners and get step-by-step setup for each. * **[Recipe Catalog](https://docs.hud.io/docs/agentic-workflows-recipes)** — the four use cases in detail. * **[FAQ & Best Practices](https://docs.hud.io/docs/agentic-workflows-faq)** — common questions, cost, security, scoping, model auth, and fixes.
{` Need Help? Chat with our support team or email us at support@hud.io. `}