Skills Development Scheduling and Automating Agent Deployments

Scheduling and Automating Agent Deployments

v20260826
run-without-you
This guide details Phase 4: transitioning an interactive agent into a persistent, automated workflow. It covers creating scheduled deployments (cron jobs) or event-driven triggers (cURL). Users learn to validate cron schedules, build the necessary deployment payloads, and follow best practices, including manual testing and DST consideration, ensuring the agent runs reliably without human intervention.
Get Skill
406 downloads
Overview

Phase 4 — Run Without You (the recurring loop)

A scheduled deployment fires a fresh session on a cron cadence — the agent
runs without you. Each firing can carry its own outcome, nesting the bounded
grade→iterate loop inside every recurring run.

See ../../references/loops-and-workflows.md.

Choose the trigger

AnswerShapeTool
"every morning / weekly / nightly"recurring cron deploymentdeployment_builder.py + cron_validator.py
"when X happens"event-driven curl (documented, not scheduled)deployment_builder.py (message only)
"only when I ask"on-demand (no deployment)none — just re-send a user.message

Workflow (recurring)

  1. Validate the schedule.

```bash
python3 scripts/cron_validator.py --cron "0 9 *" --timezone Europe/Berlin
```
Invalid cron/timezone → exit 1. Read the DST note: wall-clock semantics mean
spring-forward times are skipped and fall-back times fire twice — avoid
02:00–03:00 in DST zones if exactly-once matters.

  1. Build the deployment payload.

```bash
python3 scripts/deployment_builder.py \
--sheet ./my-agent/build-sheet.json --agent-id agent123 --env-id env456 \
--nest-outcome --out ./my-agent/payloads/deployment.json
```
--nest-outcome includes the rubric so each firing self-grades. The tool
prints the BYOK curl to create it and to test it once with the manual run
endpoint before trusting the schedule.

  1. Test before you trust. Fire one manual run, read the verdict, only then

leave the cron in place. Pin the agent version in the deployment once it passes.

  1. Finalize the roadmap.

```bash
python3 scripts/nextdirectionswriter.py \
--sheet ./my-agent/build-sheet.json --loop-shape cron-loop --last-verdict satisfied --out-dir ./my-agent
```

  1. Advance + hand to wrap-up. goal_state.py set --phase wrap-up, then invoke

the wrap-up skill.

Hard rules

  • Test with a manual run first. Never commit a schedule you haven't fired once.
  • Safety rails on by default. always_ask MCP, limited networking where you

can, read_only untrusted memory, max_iterations per firing, workspace spend
limit. There is no spend cap inside CMA.

  • DST is wall-clock. Surface the note; pick safe times.
  • ≤1,000 deployments/org.

Forcing-question library (recommend + cite)

  1. "Cadence, event, or on-request?" Recommend: on-request v0 → cadence once graded.

Cite: loops-and-workflows.md.

  1. "Should each firing self-grade?" Recommend: yes — nest the outcome. Cite:

loops-and-workflows.md (nesting rule).

  1. "Which timezone, and is the time DST-safe?" Recommend: avoid 02:00–03:00 in

DST zones. Cite: cma-primitives.md (wall-clock DST).

  1. "Did you fire one manual run first?" Recommend: always. Cite: this SKILL.

Tools

  • scripts/deployment_builder.py — POST /v1/deployments payload (+ test-run curl).
  • scripts/cron_validator.py — 5-field cron + IANA tz + DST note.
  • scripts/next_directions_writer.py — write/refresh NEXT-DIRECTIONS.md.
Info
Category Development
Name run-without-you
Version v20260826
Size 8.76KB
Updated At 2026-09-06
Language