Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
by PaperChaseWebb
A free self-check for agencies and small businesses. Score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule and three gate rules, read your band and what to do next, plus an interview prompt for Grok Bot, Claude Code, Codex or Hermes, a score sheet and a worked example.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 30 min
- Format
- .md file
agent-readiness-self-check-score-one-workflow-free.md · 23 KB · direct download, no signup
What you end up with
In about 30 minutes you know whether one workflow is ready for an AI agent, which area to fix first, and whether your next step is free fixes, a self-serve workbook or the Install sprint.
What you get
- Eight scored areas with 0 to 3 anchors
- An evidence rule so scores need proof
- Three gate rules for approvals, owners and security
- Four bands with what to do at each one
- A two-pass honesty test
- Approval steps for running the check with an agent
- An interview prompt for Grok Bot, Claude Code, Codex or Hermes, with harness notes
- A score sheet to copy
- A worked example, labeled as illustrative
- Where each band leads: free fixes, the $39 Agency AI Ops Workbook or the Install sprint
Who it is for
Owners of agencies and small businesses who want to put AI agents to work and want an honest read on one workflow first, including when the honest answer is not yet.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free. No signup.
Time to result: About 30 minutes for one workflow
How it works
Pick one workflow
One job that repeats, with a start and a finish. Bring the person who does it today.
Expected: A workflow named in one line.
Score the eight areas
0 to 3 per area using the anchors, with one line of evidence each. Or run the interview prompt with your agent.
Expected: A filled score sheet.
Apply the rules
Evidence rule first, then the three gate rules. The lower band wins.
Expected: One final band.
Run the skeptical pass
Rescore as a careful outsider would. Areas that drop are your first fixes.
Expected: Hopeful and skeptical bands, and the gap.
Do the first action
Follow your band's list, then rescore the same workflow in two weeks.
Expected: One fix done and a rescore date.
Sample prompts, free to use
You are running the Agent Readiness Self-Check with me for one workflow: [workflow]. You only ask questions and write the score sheet. Do not open accounts, connect tools, install anything, browse or contact anyone. Go through the eight areas in order, propose a 0 to 3 score for each from the anchors in this file, and ask what evidence I can open now. No evidence means 1. Apply the gate rules, run a skeptical pass, and ask me to approve each score before you write the final sheet.
The full prompt with output format and harness notes is in section 8 of the file.
Free preview of the file
# Agent Readiness Self-Check: score one workflow before you hand it to an AI agent A free self-check by PaperChaseWebb for owner-led agencies and small businesses. Pick one workflow, score it across eight areas with evidence, apply three gate rules, and read your band: not yet, draft-only pilot, ready to install one workflow, or ready to run more than one. Every band comes with what to do next, including the honest answer when the answer is "fix the basics first". Includes an interview prompt that has Grok Bot, Claude Code, Codex or Hermes run the self-check with you and score it, a score sheet to copy, and a worked example. Plain .md. No signup, no email gate, the whole thing is in this file. Most free AI readiness quizzes ask ten vague questions about your whole company, hand back a number like 62, and put the same "book a call" button under every result. This one is narrower on purpose. It scores one workflow, it asks for proof instead of feelings, and it checks the parts that decide whether agents help or hurt: who approves, who answers for each agent, how work passes between agents and people, what it costs and how you will know it worked. ## Contents 1. How to use this in 30 minutes 2. The eight areas and how to score them 3. The evidence rule 4. The three gate rules 5. Bands and what to do at each one 6. The two-pass honesty test 7. Approval steps for the self-check itself 8. The interview prompt (Grok Bot, Claude Code, Codex, Hermes) 9. The score sheet 10. Worked
Worth knowing
- A self-check, not an audit. The score is only as good as the evidence behind it.
- The worked example is invented to show the scoring. It is not a client and its numbers are not results.
- The Install sprint is scoped on a call; nothing here promises time saved or revenue.
Questions
Do I need an AI agent to use this?
No. It works on paper. The interview prompt is there if you want Grok Bot, Claude Code, Codex or Hermes to ask the questions and keep score.
Will the agent touch my accounts?
No. The prompt tells it to only ask and write the sheet. You describe your workflow in your own words and approve every score.
What if I score Not yet?
Then do not buy agent tooling for that workflow yet. The three fixes for that band are free and listed in the file. Rescore in two weeks.
What comes after the self-check?
Depending on your band: free fixes, the Agency AI Ops Workbook ($39) to do the install yourself, or the $5,000 Install sprint on the paperchasewebb.ai homepage (Book a call).
Details
Version 1.0 · Updated Oct 27, 2026 · Markdown version of this page
License: Personal and commercial use, including with your own clients. Do not resell or republish this file. Download terms
Related
Agency AI Ops Workbook: the Install sprint, self-serve
A two-week workbook for owner-led agencies and small businesses: install one AI agent workflow yourself with the same steps as our $5,000 Install sprint. Discovery and mapping, picking the first workflow from your Self-Check score, an agent card with an owner and a tested pause, data access and a test set, an approval gate register, handoff packets, cost limits, tool vetting, a baseline and stop rule, a dry run, a go-live checklist and a 30-day review. Ten worksheets, 13 prompts with harness notes.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.
Cross-Harness Relay: Grok Bot, Claude Code, Codex and Hermes on one job
A bot template and teaching guide for running more than one agent harness on the same work. Six seat cards (front desk, planner, builder, reviewer, tester, night shift), a RELAY.md seat map, a relay packet for every handoff, four loop shapes, routine-or-judgment routing with a fallback when limits run tight, a preflight check, the front desk and night shift split with a proof footer, shared memory rules, eight relay drills, a rules block and 14 prompts.
Agent Cost Levers: cut cost per solved task without cutting quality
A Markdown pack that measures what your coding agent spends per finished task, then works five levers one at a time: thinking depth, context curation, direct tool routing, cache and reuse, and a verified stop. Includes a baseline sheet, a rules block and 10 prompts.
Vet Before You Install: ten checks, a sandbox recipe and a skill for third-party agent code
A Markdown pack for deciding whether a skill, plugin, mod, MCP server or repo is safe to let into your agent setup: read it first, pin and vendor it, trial it in a sandbox with a planted fake key, then write the decision down.
Governed Agent Teams: subagent personas, authority maps and handoffs
A Markdown pack for running a team of coding and research agents with clear limits: 7 subagent personas for Claude Code with Codex AGENTS.md and Hermes skill versions, a Desk Authority Map, three role risk classes, a handoff packet the receiver verifies, an evidence standard, a decision ledger and a reach inventory.